system

Abstract

Provide a system. A plurality of terminals includes means for collecting environmental data; means for preprocessing data collected by the terminal; means for transmitting the pre-processed data to a central server; a means for the central server to receive data transmitted from the terminal; A central server aggregates the received data and performs AI processing; A means for broadcasting the results of AI processing to the terminal; The system includes a terminal that receives and displays the broadcasted results.

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] In recent years, advances in artificial intelligence (AI) have led to the use of AI in many fields. However, particularly when using high-performance generative AI, its processing requires a large amount of computational resources, making it unrealistic to run high-performance AI on every device. In particular, implementing high-performance AI on every device imposes significant cost and technical constraints, and simultaneous use by all humankind leads to a shortage of computational resources, resulting in reduced system availability and efficiency. The present invention aims to solve these problems by providing a system that efficiently executes high-performance AI calculations on a central server while distributing data collection and processing among devices. [Means for solving the problem]

[0005] The present invention solves the above problems by using the following means: a distributed AI system including: means for multiple terminals to collect environmental data; means for the terminals to preprocess the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive the data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting the results of the AI ​​processing to the terminals; and means for the terminals to receive and display the broadcasted results.

[0006] In this system, devices preprocess data locally and then send it to a central server, reducing the computational load on each device. When the central server receives a certain amount of data, it triggers AI processing and broadcasts the results to the devices. This allows for efficient use of high-performance AI functions even with limited resources, optimizing the use of overall computing resources. Furthermore, devices send data using HTTP POST requests, ensuring reliable communication.

[0007] A "terminal" is a device that collects environmental data, pre-processes the data and transmits it to a central server.

[0008] "Environmental data" refers to information collected from a particular environment, such as temperature, humidity, soil quality, etc.

[0009] "Preprocessing" refers to processing raw data by methods such as normalization, noise removal, and format conversion.

[0010] The "central server" is a server that receives data sent from terminals, aggregates the data, and performs AI processing.

[0011] "Receiving" means that the central server obtains data sent from the terminal.

[0012] "Aggregation" means combining data received from multiple terminals into one set.

[0013] "AI processing" refers to the use of data by artificial intelligence to analyze, predict, and learn.

[0014] "Broadcast" means that a central server sends the results of AI processing to multiple devices simultaneously.

[0015] An "HTTP POST request" is a type of communication protocol used by a terminal to send data to a central server. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that enables efficient data processing and the utilization of AI by having multiple terminals collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the terminals.

[0038] Program Overview

[0039] This system assigns specific roles to both the terminal and the central server, and they work together. The following is a natural language explanation of the program processing of this system.

[0040] Device behavior

[0041] Data collection

[0042] The device collects environmental data at regular intervals, including temperature, humidity, soil quality, etc.

[0043] Data Preprocessing

[0044] The devices preprocess the collected raw data, specifically normalizing it and removing noise, so that the data can be sent to a central server in a unified format.

[0045] Data transmission

[0046] The preprocessed data is sent to a central server using an HTTP POST request, formatted as JSON and containing the device ID and the normalized data.

[0047] Server Operation

[0048] Data reception

[0049] The central server receives the data sent from the terminal and temporarily stores the received data on the server.

[0050] Data Aggregation

[0051] When a certain amount of data is collected, the server aggregates the data. For example, if data is collected from five devices, the server will combine the data into one set.

[0052] AI processing

[0053] Using the aggregated data, the central server runs AI models, which include analysis, prediction, model training, etc. The results of the AI ​​processing include, for example, recognition of averages and patterns in the environmental data.

[0054] Broadcasting the Results

[0055] The results of the AI ​​processing are sent simultaneously from the server to each device, which then receives the broadcasted results and displays them to the user.

[0056] User operations

[0057] Data confirmation

[0058] The user checks the results sent from the device, which include analysis of the environmental data collected by each device and recommended actions.

[0059] Specific examples

[0060] Example 1: Agricultural sensors

[0061] Multiple environmental sensors (terminals) are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture and send the data to a central server. The central server receives and aggregates this data and uses an AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize crops.

[0062] Example 2: Smart city air quality monitor

[0063] Multiple sensors (terminals) placed throughout the city collect air quality data and send it to a central server. The server analyzes the data and determines the air quality status of each area in real time. The results are broadcast, and citizens (users) can use this information to decide whether or not to go outside.

[0064] In this way, the present invention provides a system for efficient data collection, pre-processing, aggregation, AI processing, and feedback of results. By dividing each step, the system optimizes computing resources and improves overall performance.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The devices collect environmental data. This is done periodically, and each device uses its own sensors to acquire data such as temperature, humidity, and soil moisture. For example, the temperature sensor measures the air temperature and stores the acquired data in memory.

[0068] Step 2:

[0069] The data collected by the device is preprocessed. Preprocessing includes normalizing the raw data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value.

[0070] Step 3:

[0071] The device sends the preprocessed data to the central server using an HTTP POST request, which includes the device ID and the normalized data. For example, the normalized data is sent to the server in JSON format.

[0072] Step 4:

[0073] The server receives the data sent from the terminal. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to store the data.

[0074] Step 5:

[0075] When the server receives a certain number of data, it aggregates the data. For example, if data is sent from five devices, the perform_central_processing() function is called and the data is aggregated into one set.

[0076] Step 6:

[0077] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it concatenates the incoming data and calculates the average value of that data.

[0078] Step 7:

[0079] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device simultaneously. At this time, the results are sent in a format that each device can understand.

[0080] Step 8:

[0081] The terminal receives the results broadcast from the server, and displays the results or stores them in a database or memory as needed. For example, the results are displayed on the terminal display.

[0082] Step 9:

[0083] The user can view the results displayed on the device. For example, farmers can use the data from the sensors to adjust their farming operations. The user can then adjust the irrigation system or perform other agricultural activities based on the results displayed.

[0084] Example 1

[0085] 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."

[0086] Conventional data collection systems have problems with the inefficient execution of processes from environmental data collection to analysis and feedback of results, leading to the inability to optimize computing resources. Another issue is that individually collected data is not preprocessed according to uniform standards, making accurate analysis difficult. Furthermore, they are unable to perform real-time analysis of collected data and provide rapid decision support based on that analysis.

[0087] 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.

[0088] In this invention, the server includes: means for multiple terminals to collect environmental data; means for the terminals to preprocess the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive the data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing using a generative AI model; means for the terminals to broadcast the results of the AI ​​processing; and means for the terminals to receive and display the broadcasted results. This allows the entire process from data collection to analysis and result feedback to be executed efficiently, optimizing computing resources and providing analysis results in real time.

[0089] "Terminal" refers to the electronic device that collects environmental data, pre-processes it, and transmits the data to a central server.

[0090] "Environmental Data" refers to information related to the natural environment, such as temperature, humidity, soil quality, etc.

[0091] "Preprocessing" refers to the process of removing noise, normalizing, and otherwise processing collected raw data.

[0092] "Central server" refers to a system with central computing resources that performs a series of functions, including receiving data sent from devices, aggregating it, and processing it using AI models.

[0093] "Receiving" refers to the process by which the central server receives data sent from the terminal.

[0094] "Aggregation" refers to the process of combining multiple pieces of received data into a single data set.

[0095] A "generative AI model" refers to a model that uses pre-trained artificial intelligence algorithms to analyze data and make predictions.

[0096] "Broadcast" refers to the process in which a central server simultaneously transmits the results of AI processing to multiple devices.

[0097] "HTTP POST request" refers to a web communication protocol that allows a device to send pre-processed data to a central server.

[0098] This invention is a system that enables efficient data processing and the utilization of generative AI models by having multiple devices collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the devices.

[0099] Device behavior

[0100] The device uses sensors to collect environmental data. These sensors acquire data such as temperature, humidity, and soil quality at regular intervals. The collected raw data is preprocessed using Python's NumPy library. Specifically, the data is normalized and noise is removed to generate unified format data. After preprocessing is complete, the data is sent to the central server via an HTTP POST request using Python's requests library. This process allows the device to efficiently and accurately provide environmental data to the central server.

[0101] Server Operation

[0102] The central server receives data sent from the devices using the Flask web framework. The received data is saved and temporarily stored in a MySQL® database. Once a certain amount of data has been collected, the server performs aggregation processing using the Pandas library. This aggregation process combines data from multiple devices into a single dataset. The combined dataset is then analyzed and predicted using generative AI models using libraries such as TENSORFLOW® and PyTorch. This AI processing enables statistical information and pattern recognition of environmental data. Finally, the results of the AI ​​processing are broadcast simultaneously to each device using the WebSocket library.

[0103] User operations

[0104] The user can view the results broadcast from the devices. These results include analysis results of the environmental data collected by each device and recommended actions. The user can view the details of the data through the device interface, for example, by operating a GUI using the Tkinter library.

[0105] Specific examples

[0106] Example 1: Agricultural sensors

[0107] Multiple agricultural environmental sensors are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture, and transmit the data to a central server after preprocessing. The central server aggregates this data and uses a generative AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize their crops.

[0108] Example 2: Smart city air quality monitor

[0109] Multiple air quality sensors located throughout the city collect air quality data, which is then preprocessed and sent to a central server. The server aggregates the data and uses a generative AI model to analyze local air quality. The results are broadcast to citizens in real time, providing reference information for deciding whether or not to go outside.

[0110] Prompt Sentence Examples

[0111] An example prompt to input to a generative AI model might be, "Please tell me how to optimize temperature and humidity on a farm."

[0112] Thus, the present invention provides a system for efficient data collection, preprocessing, aggregation, AI processing using generative AI models, and feedback of the results. By dividing each step, computing resources can be optimized and overall performance can be improved.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] The terminal collects environmental data. The input is raw data obtained from sensors such as temperature, humidity, and soil quality. The output is this raw data. Specifically, the temperature sensor measures the temperature, the humidity sensor measures the humidity, and the soil humidity sensor measures the moisture content of the soil.

[0116] Step 2:

[0117] The terminal preprocesses the raw data collected. The input is the raw data obtained in step 1. The output is the preprocessed data that has been denoised and normalised. Specifically, the terminal normalises the data using Python's NumPy library and uses filtering techniques to remove noise from the measurement data.

[0118] Step 3:

[0119] The terminal sends the preprocessed data to the central server. The input is the preprocessed data obtained in step 2. The output is the data sent to the central server via an HTTP POST request. Specifically, the terminal uses the Python requests library to convert the data into JSON format and send it to the central server via a POST request.

[0120] Step 4:

[0121] The server receives data sent from the device. The input is preprocessed data sent as an HTTP POST request. The output is the received data stored in a database. Specifically, the server uses the Flask web framework to receive the POST request and store the data in a MySQL database.

[0122] Step 5:

[0123] The server aggregates the data it receives. The input is data from multiple devices in a database. The output is an aggregated dataset. Specifically, the server uses the Pandas library to retrieve data from the database and organize it into a data frame. This data frame combines the data from multiple devices into a single dataset.

[0124] Step 6:

[0125] The server uses the aggregated data to perform AI processing using a generative AI model. The input is the aggregated data obtained in step 5. The output is analysis results and prediction results. Specifically, the server uses libraries such as TensorFlow and PyTorch to execute a pre-trained generative AI model to analyze and predict data.

[0126] Step 7:

[0127] The server broadcasts the results of the AI ​​processing to each device. The input is the AI ​​processing result obtained in step 6. The output is the broadcasted AI processing result. Specifically, the server uses the WebSocket library to simultaneously send the results of the AI ​​processing to each device.

[0128] Step 8:

[0129] The user checks the results sent from the device. The input is the broadcasted AI processing results. The output is the analysis results and recommended actions checked by the user. Specifically, the device uses a GUI library such as Tkinter to display the results to the user. The user decides on the appropriate action based on this information.

[0130] (Application example 1)

[0131] 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."

[0132] Logistics centers require optimal inventory management and efficient replenishment, but current systems make it difficult to collect and analyze data in real time, and the time it takes to consolidate and analyze data leads to problems such as stockouts and excess inventory.In addition, data collected by individual devices cannot be managed and analyzed in a unified manner, making it difficult to improve overall efficiency.

[0133] 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.

[0134] In this invention, the server includes: means for multiple terminals to collect environmental data; means for preprocessing the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for analyzing inventory data collected from multiple terminals in the logistics center and predicting optimal inventory allocation and replenishment timing. This enables real-time inventory management in the logistics center, preventing stockouts and excess inventory and improving overall efficiency.

[0135] A "terminal" is a device consisting of multiple environmental sensing devices and mobile devices for collecting and preprocessing environmental data.

[0136] "Environmental data" refers to various data that indicate the environmental conditions within the logistics center, such as temperature, humidity, weight, and air quality.

[0137] "Preprocessing" is the process of converting collected raw data using techniques such as noise removal and normalization to unify the data format.

[0138] The "central server" is a computer system that receives environmental data sent from multiple devices and aggregates and analyzes it.

[0139] "Aggregation" is the process of collecting and integrating data received from multiple devices into a single set.

[0140] "AI processing" is the process of running machine learning models and other AI models on aggregated data to perform analysis and make predictions.

[0141] "Broadcast" refers to the simultaneous transmission of the results of AI processing performed on a central server to multiple devices via a network.

[0142] "Inventory data" refers to data that indicates the inventory status of products managed within a logistics center, and includes attributes such as weight and quantity.

[0143] "Optimal placement" is a method for efficiently managing the placement of inventory items, with the aim of making effective use of space and improving work efficiency.

[0144] "Replenishment timing" is an indicator that indicates the optimal timing for appropriate replenishment before inventory runs out.

[0145] This invention is a system aimed at improving the efficiency of inventory management in logistics centers. The system includes multiple terminals, a central server, and analytical processing using an AI model. It also predicts optimal inventory placement and replenishment timing by coordinating real-time data collection, preprocessing, aggregation, analysis, and broadcasting.

[0146] The terminal collects inventory data using multiple environmental sensors in the distribution center. These environmental sensors periodically measure temperature, humidity, shelf weight (inventory status), etc. The measured data is preprocessed by the terminal to remove noise and normalize the data. The preprocessed data is sent to the central server in JSON format using an HTTP POST request.

[0147] The central server receives and temporarily stores data sent from the terminals. Next, once a certain amount of data has been collected, the server aggregates the data. The aggregated data is input into an AI model for analysis and prediction processing. The AI ​​model uses deep learning models and machine learning algorithms using Python. The analysis results include, for example, recommendations for optimal inventory placement and replenishment timing.

[0148] The results are broadcast from a central server to each terminal, which receives the results and displays them to the staff through a user interface, allowing staff to efficiently manage and replenish inventory based on real-time data.

[0149] As a concrete example, consider using this system in a distribution center. Smartphones are used within the center to collect temperature, humidity, and weight data from sensor devices on each product shelf. The collected data is preprocessed on the smartphone and sent to a central server. The central server analyzes the data and displays specific instructions on each device, such as "Product A is running low on stock, so it needs to be replenished immediately" or "Product B still has plenty of stock, so there is no need to replenish it."

[0150] The following sentences are used as examples of prompt sentences to input into the generative AI model:

[0151] "Please generate an AI model to predict the optimal replenishment timing using the current inventory status at the logistics center and the temperature and humidity data for each product as input data."

[0152] In this way, a system is realized that can streamline inventory management within the logistics center and prevent stockouts and excess inventory.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The device collects environmental data.

[0156] (Specific actions)

[0157] Environmental sensors connected to the devices periodically measure temperature, humidity, shelf weight, etc. The collected data is stored in the memory of each device.

[0158] (input)

[0159] Raw environmental data obtained from environmental sensors.

[0160] (output)

[0161] Raw environmental data stored on the device.

[0162] Step 2:

[0163] Preprocess the data collected by the device.

[0164] (Specific actions)

[0165] The device performs noise reduction and data normalization on the collected data, for example, detecting and removing outliers and converting the data into a unified format.

[0166] (input)

[0167] Raw environmental data.

[0168] (output)

[0169] Preprocessed and normalized data.

[0170] Step 3:

[0171] The pre-processed data is sent to a central server.

[0172] (Specific actions)

[0173] The device converts the preprocessed data into JSON format and sends it to the central server using an HTTP POST request.

[0174] (input)

[0175] Preprocessed normalized data.

[0176] (output)

[0177] Data requests sent to a central server.

[0178] Step 4:

[0179] A central server receives data from the terminals.

[0180] (Specific actions)

[0181] The server extracts data from the received HTTP POST request and stores it temporarily in a database.

[0182] (input)

[0183] The data request sent.

[0184] (output)

[0185] Raw data stored on the server.

[0186] Step 5:

[0187] A central server aggregates the received data.

[0188] (Specific actions)

[0189] When the server receives a certain amount of data, it aggregates the data, calculates averages and totals, and compiles them into a unified data set.

[0190] (input)

[0191] Raw data stored on the server.

[0192] (output)

[0193] Aggregated datasets.

[0194] Step 6:

[0195] A central server analyzes the data using an AI model.

[0196] (Specific actions)

[0197] The collected data is input into an AI model to predict optimal inventory placement and replenishment timing. The prediction results are stored on the server.

[0198] (input)

[0199] Aggregated datasets.

[0200] (output)

[0201] Analysis results (optimal inventory placement and replenishment timing).

[0202] Step 7:

[0203] The results of AI processing are broadcast to the device.

[0204] (Specific actions)

[0205] The server converts the analysis results into JSON format and sends them to all connected devices simultaneously.

[0206] (input)

[0207] Analysis results.

[0208] (output)

[0209] Data broadcast to the device.

[0210] Step 8:

[0211] The terminal receives and displays the results.

[0212] (Specific actions)

[0213] The terminal analyzes the received data and displays it to the person in charge through the user interface. The analyzed data is displayed in an appropriate format, and the user can refer to it to manage inventory.

[0214] (input)

[0215] Broadcast data.

[0216] (output)

[0217] Analysis results displayed on the device.

[0218] 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.

[0219] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[0220] Program Overview

[0221] This system operates efficiently and flexibly through the cooperation of the terminals, the central server, and the emotion engine. The following is a natural language explanation of the program processing of this system.

[0222] Device behavior

[0223] Data collection

[0224] The device collects environmental data (e.g., temperature, humidity, soil moisture) and user emotion data (e.g., facial expression analysis, voice tone analysis). The emotion engine analyzes the user's emotion from facial expression and voice data and uses the results.

[0225] Data Preprocessing

[0226] The device preprocesses the collected environmental and emotional data. The environmental data is normalized and denoised, and the emotional data is preprocessed in the same way. For example, if the environmental data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value. The emotional data is also converted from binary to numeric data.

[0227] Data transmission

[0228] The preprocessed data is sent to a central server using an HTTP POST request. The data includes the device ID, environmental data, and emotion data. For example, the normalized data is sent to the server in JSON format.

[0229] Server Operation

[0230] Data reception

[0231] The server receives the environmental data and emotion data sent from the device, and the received data is temporarily stored in the server's memory or database.

[0232] Data Aggregation

[0233] When the server receives more than a certain number of data, it aggregates the data. For example, if data is sent from five devices, it aggregates each data into one set.

[0234] AI processing

[0235] Using the aggregated data, the server performs AI processing of both environmental and emotional data. AI processing includes data analysis, prediction, modeling, etc. For example, it calculates the average value of environmental data and analyzes the user's overall mood from emotional data.

[0236] Broadcasting the Results

[0237] The results of the AI ​​processing are sent from the server to each device simultaneously. For example, the broadcast_results() function is called and the results are sent to each device in a format that each device can understand.

[0238] User operations

[0239] Data confirmation

[0240] The user then checks the results sent from the device, which include feedback based on the analysis of the environmental data and emotional data, and can use this information to adjust their behavior.

[0241] Specific examples

[0242] Example 1: Agricultural sensors and sentiment analysis

[0243] Multiple sensors (terminals) installed on farms collect data on temperature, humidity, and soil moisture, while also collecting emotional data from the farmer (user)'s facial expressions and voice. A central server receives this data and performs AI processing to predict optimal growing conditions for crops. As a result, the farmer's stress level is provided along with recommended environmental conditions. Farmers can then adjust watering and fertilizer application based on this information.

[0244] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[0245] Multiple sensors (terminals) placed throughout the city collect air quality data, and an emotion engine collects emotion data from citizens (users). A central server receives this data and analyzes the air quality in each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[0246] In this way, the present invention provides a distributed AI system that combines an emotion engine and realizes efficient data collection, preprocessing, aggregation, AI processing, and feedback of results, enabling advanced analysis and judgment using environmental data and user emotion data.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] The device collects environmental data and user emotional data. Environmental data is acquired using sensors, and emotional data is analyzed using an emotion engine based on facial expressions and voice. For example, a temperature sensor acquires the temperature, and a microphone and camera capture the user's voice and facial expressions.

[0250] Step 2:

[0251] Preprocessing the environmental data collected by the device. Preprocessing includes normalizing the data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], calculate the average value and then normalize each data point by dividing it by the average value.

[0252] Step 3:

[0253] The device preprocesses the emotion data. The emotion engine converts the binary data into numerical data. For example, it extracts a happiness score from the user's facial expression and stores it in numerical format.

[0254] Step 4:

[0255] The device sends the preprocessed environmental data and emotion data to the central server. The data is sent in JSON format using an HTTP POST request, which includes the device ID, the preprocessed environmental data, and the emotion data.

[0256] Step 5:

[0257] The server receives the environmental data and emotion data sent from the device. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to save the data.

[0258] Step 6:

[0259] When the server receives a certain amount of data, it aggregates the environmental data and emotional data. For example, if data is collected from five devices, the server will combine the data into one set.

[0260] Step 7:

[0261] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it can concatenate the incoming data, calculate the average value of environmental data, and analyze the user's overall mood using emotional data.

[0262] Step 8:

[0263] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device. The results include the analysis results of the environmental data and the user's emotional state.

[0264] Step 9:

[0265] The device receives the results broadcast from the server. The received results are stored in the device and displayed on the screen as needed. For example, the device may recommend temperature adjustments or provide information based on emotions.

[0266] Step 10:

[0267] The user sees the results displayed on their device and can adjust their behavior based on the results, for example, changing their work environment or adjusting irrigation systems in agriculture depending on their emotional state.

[0268] Example 2

[0269] 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."

[0270] Conventional AI systems have struggled to efficiently collect, preprocess, and analyze environmental and user emotional data, and provide rapid feedback. Ensuring the quality and consistency of data collected from individual devices in distributed systems also poses challenges. In particular, there is a need for systems to analyze diverse data in real time and provide useful feedback to users based on that data.

[0271] 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.

[0272] In this invention, the server includes: means for multiple terminals to collect environmental data and user emotional data; means for performing preprocessing, including normalization and noise removal, on the environmental data and emotional data collected by the terminals; means for the central server to receive the environmental data and emotional data transmitted from the terminals; means for the central server to aggregate the received environmental data and emotional data and trigger AI processing when a certain amount of data is received; means for executing AI processing and broadcasting the results to the terminals; and means for the terminals to receive and display the broadcasted results. This enables a series of processes of efficient data collection, preprocessing, analysis, and feedback in a distributed AI system.

[0273] A "terminal" is a device that collects environmental data and user emotion data, and transmits the data to a central server after preprocessing.

[0274] "Environmental data" is a collection of information that describes physical environmental conditions, such as temperature, humidity, and soil moisture.

[0275] "User emotion data" is a collection of information that indicates the user's emotional state, analyzed from facial expressions, tone of voice, and the like.

[0276] "Preprocessing" refers to data shaping operations such as normalization and noise removal that are performed on collected data.

[0277] The "central server" is a computer system that receives data sent from the terminals, aggregates it, performs AI processing, and broadcasts the results to the terminals.

[0278] "Aggregation" is the operation of combining data collected from multiple terminals into a single data set.

[0279] "AI processing" is the process of analyzing data using machine learning algorithms to make predictions and modeling.

[0280] "Broadcast" is an operation in which the central server transmits the processing results to all terminals simultaneously.

[0281] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[0282] System Configuration

[0283] Hardware and Software

[0284] The device includes a temperature sensor, humidity sensor, facial recognition camera, and microphone, and these devices collect environmental data and user emotional data in real time. Specifically, it uses DHT22 as a temperature sensor, OpenCV for facial recognition, and TensorFlow for voice recognition. These devices are connected to a single-board computer such as a Raspberry Pi.

[0285] The central server is a high-performance computer that aggregates the received data and uses machine learning frameworks such as PyTorch and Scikit-learn in Python to perform AI processing.

[0286] Program processing

[0287] The device collects environmental and emotional data and preprocesses it. Preprocessing includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. This process is performed using data processing libraries such as NumPy and Pandas.

[0288] The terminal sends the preprocessed data to the central server via an HTTP POST request, using JSON format.

[0289] The central server temporarily stores the received data in memory or a database (e.g., MySQL). When a certain amount of data is received, aggregation processing is triggered and AI processing is performed. This AI processing includes analysis and prediction of environmental data and modeling of emotional data. Specific processing examples include calculating the average value of environmental data and predicting the user's mood using emotional data.

[0290] The server broadcasts the results of the AI ​​processing to the devices, which then receive the results and display them to the user via a web interface or mobile application.

[0291] Specific examples

[0292] Example 1: Agricultural sensors and sentiment analysis

[0293] Agricultural sensors (terminals) collect data on the temperature, humidity, and soil moisture of the farm, while also collecting emotional data from the farmer's (user's) facial expressions and voice. A central server receives this data and performs AI processing to predict the optimal growing conditions for crops. As a result, it provides recommendations for environmental conditions and the farmer's stress level. Farmers can then adjust watering and fertilizer application based on this information.

[0294] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[0295] Multiple sensors (terminals) placed in the smart city collect air quality data and use an emotion engine to analyze the emotional data of citizens (users). A central server receives this data and analyzes the air quality of each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[0296] Prompt Sentence Examples

[0297] Agricultural sensors and sentiment analysis

[0298] Design a system that integrates agricultural sensors and an emotion engine to collect temperature, humidity, soil moisture data and user emotion data, analyze it through an AI model, and broadcast the results. As a concrete example, demonstrate how to predict crop growth conditions and provide farmers' stress levels.

[0299] Smart city air quality monitoring and citizen sentiment analysis

[0300] Integrate an emotion engine into a smart city's air quality monitoring system to design a system that monitors and analyzes citizen emotion data and air quality data in real time. As a concrete example, demonstrate how to analyze local air quality and the overall emotion state of citizens and broadcast the results to citizens.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1: Data collection

[0303] The device collects environmental data such as temperature, humidity, and soil moisture, as well as user emotional data (facial expressions and voice tone). Specifically, it uses temperature and humidity sensors, a facial recognition camera (using OpenCV), and a microphone for voice analysis (using TensorFlow).

[0304] Input: Temperature sensor, humidity sensor, facial recognition camera, voice analysis microphone

[0305] Output: Environmental data (temperature, humidity, soil moisture) and emotional data (facial expression analysis results, voice tone analysis results)

[0306] Step 2: Data Preprocessing

[0307] The device preprocesses the collected environmental and emotional data. This includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. For example, temperature data is normalized by dividing it by the average value, and facial expression data is converted to 1 for positive and 0 for negative.

[0308] Input: Collected environmental and emotional data

[0309] Output: Preprocessed environmental and emotional data

[0310] Step 3: Send data

[0311] The device sends the preprocessed data to the central server using an HTTP POST request, with the data structured in JSON format.

[0312] Input: Preprocessed environmental and emotion data

[0313] Output: JSON format data sent to the central server

[0314] Step 4: Receiving Data

[0315] The server receives the environmental data and emotion data sent from the device, and temporarily stores the received data in memory or a database (e.g., MySQL).

[0316] Input: Data sent from the terminal (JSON format)

[0317] Output: Data stored in memory or in a database

[0318] Step 5: Data Aggregation

[0319] When the server receives a certain number of data sets, it aggregates them. For example, it aggregates data sets from five devices into one set.

[0320] Input: Received data from multiple devices

[0321] Output: Aggregated dataset

[0322] Step 6: AI processing

[0323] The server uses the aggregated data to perform AI processing, including data analysis, prediction, and modeling. Specifically, it calculates the average value of environmental data and predicts the user's mood using emotional data. This processing is performed using PyTorch and Scikit-learn.

[0324] Input: Aggregated dataset (environmental and emotional data)

[0325] Output: Analysis results by AI processing

[0326] Step 7: Broadcasting the results

[0327] The server simultaneously sends the results of the AI ​​processing to each device in JSON format, which each device can receive and display to the user.

[0328] Input: Analysis results by AI processing

[0329] Output: Analysis results broadcast to the device

[0330] Step 8: Data verification

[0331] The user checks the results received by the device, which are displayed on the device's display or in a mobile application, and adjusts their actions based on the information.

[0332] Input: Analysis results displayed on the terminal

[0333] Output: User behavior adjustment

[0334] Through the above steps, the present invention achieves efficient data collection, pre-processing, analysis, and feedback, enabling advanced analysis and judgment.

[0335] (Application example 2)

[0336] 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."

[0337] Conventional customer experience optimization systems for brick-and-mortar stores were limited to collecting environmental data and had difficulty utilizing user emotional data. As a result, they were unable to respond to real-time changes in customer emotions, resulting in limited improvements in customer satisfaction. In addition, there was a lack of a mechanism to efficiently aggregate collected environmental and emotional data and take appropriate action, making it difficult for staff to utilize the information in real time.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for multiple terminals to collect environmental data and user emotion data; means for the terminals to preprocess the collected environmental data and emotion data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for the terminals to provide instructions for taking actions based on user operations. This makes it possible to utilize environmental data and user emotion data in real time and quickly provide specific actions to optimize the customer experience.

[0339] A "terminal" is a device that collects environmental data and user emotion data, and performs preprocessing and data transmission.

[0340] "Environmental data" refers to information about the physical environment, such as temperature and humidity.

[0341] "User emotional data" refers to information about the user's emotional state detected using facial expression analysis and voice tone analysis.

[0342] "Preprocessing" refers to performing processes such as normalization and noise removal on collected data.

[0343] The "central server" is a server that receives and aggregates data sent from terminals and then performs AI processing.

[0344] "AI processing" refers to the process of analyzing received data and making predictions and modeling.

[0345] "Broadcast" refers to sending AI-processed results to multiple devices simultaneously.

[0346] "Means for providing instructions for the terminal to take an action based on the user's operation" refers to a function in which the terminal indicates the action that the user should take based on the broadcasted results.

[0347] This invention is a system in which multiple devices collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the devices, thereby optimizing the customer experience in physical stores.

[0348] Overall system configuration

[0349] The system consists of the following components:

[0350] Device: Smart glasses or head-mounted display

[0351] Central Server

[0352] Emotion Engine

[0353] Network connection: Wi-Fi or LTE

[0354] Program processing flow

[0355] Hardware and Software

[0356] 1. Terminal

[0357] Devices used: smart glasses, head-mounted displays

[0358] Data collection: The device collects environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[0359] 2. Emotion Engine

[0360] Software: TensorFlow, Keras

[0361] Function: Analyzes facial expressions and voice tones to quantify the user's emotional state

[0362] 3. Central Server

[0363] Software used: Python, JavaScript (registered trademark), database management system

[0364] Functions: Data reception, preprocessing, aggregation, AI analysis, and broadcasting of results

[0365] Specific AI models: TensorFlow, Keras

[0366] Processing Details

[0367] 1. Data Collection

[0368] The device collects environmental and emotional data, such as temperature of 22 degrees, humidity of 45%, and customer emotions of 0.8 happiness and 0.2 stress.

[0369] 2. Data Preprocessing

[0370] The device normalizes and denoises the collected data and preprocesses it. For example, environmental data is normalized based on the average value, and emotion data is converted from binary to numerical data.

[0371] 3. Data Transmission

[0372] The pre-processed data is sent to a central server using an HTTP POST request.

[0373] 4. Data Reception and Aggregation

[0374] The central server receives the data and aggregates it over a certain number of devices, for example, combining data from five devices into one set.

[0375] 5. AI Processing

[0376] The aggregated data is then used by the AI ​​model to perform analysis, for example, calculating average values ​​for environmental data and analyzing the user's overall mood from emotional data.

[0377] 6. Broadcasting the Results

[0378] The results of the AI ​​processing are sent simultaneously from a central server to each device, which receives the results and displays them to the user.

[0379] Examples of concrete examples and prompts

[0380] Specific examples

[0381] After analyzing customer emotional data (happiness level 0.7, stress level 0.3) in a specific store area, the central server recommends deploying additional staff support in this area. When staff act on this instruction, the customer experience is improved.

[0382] Prompt Sentence Examples

[0383] Enter the following prompt into the generative AI model:

[0384] Based on the customer's facial expression data and in-store environmental data, recommend an action to optimize customer satisfaction. The specific customer's emotional state is as follows: Happiness level 0.5, Stress level 0.5. The environmental data is as follows: Temperature 22.0°C, Humidity 45%. Please specify the recommended action.

[0385] The above is an embodiment of the present invention, which makes it possible to optimize the customer experience in a physical store by utilizing environmental data and user emotion data.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] Data collection

[0389] The device uses smart glasses or a head-mounted display to collect environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[0390] Input: Real-time environmental and emotional data

[0391] Output: Collected raw data (e.g., temperature 22.0°C, humidity 45%, happiness level 0.8, stress level 0.2)

[0392] Step 2:

[0393] Data Preprocessing

[0394] The environmental data and emotion data collected by the device are pre-processed by normalizing and removing noise.

[0395] Input: Raw data collected

[0396] Data processing: Normalization of environmental data by the average value, conversion of emotion data from binary to numerical data

[0397] Output: Preprocessed data (e.g., normalized temperature data, sentiment analysis results as numerical data)

[0398] Step 3:

[0399] Data transmission

[0400] The device sends the pre-processed data to the central server using an HTTP POST request.

[0401] Input: Preprocessed data

[0402] Output: JSON format data sent to the central server

[0403] Step 4:

[0404] Data reception and aggregation

[0405] A central server receives the data sent from the terminals and temporarily stores it in a database or memory.

[0406] Input: Data sent from the terminal

[0407] Data processing: preparing data for storage and aggregation in a database

[0408] Output: Saved dataset

[0409] Step 5:

[0410] Triggering AI processing

[0411] When the central server receives a certain amount of data, it triggers AI processing.

[0412] Input: Aggregated dataset

[0413] Output: AI processing start instruction

[0414] Step 6:

[0415] Data aggregation and analysis

[0416] The central server analyzes the aggregated data using AI models (TensorFlow, Keras) and predicts the user's overall mood based on environmental and emotional data.

[0417] Input: Aggregated preprocessed dataset

[0418] Data calculation: Data analysis and mood prediction using AI models

[0419] Output: Analysis results (e.g., recommended actions, overall mood)

[0420] Step 7:

[0421] Broadcasting the Results

[0422] The central server broadcasts the results of AI processing to all devices simultaneously.

[0423] Input: AI analysis results

[0424] Output: Broadcast results sent to the device

[0425] Step 8:

[0426] Displaying results and prompting

[0427] The terminal receives the broadcasted results and displays them to the staff, and also provides instructions for taking action based on the user's actions.

[0428] Input: Broadcast result from server

[0429] Output: Instructions and data displayed on the terminal (e.g., "Deploy additional staff to Area B")

[0430] Step 9:

[0431] User Behavior

[0432] The user takes actual actions based on instructions from the terminal, such as allocating additional staff or presenting discount offers.

[0433] Input: Instructions from the terminal

[0434] Output: Specific actions aimed at improving customer experience

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Second embodiment]

[0439] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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."

[0451] This invention is a system that enables efficient data processing and the utilization of AI by having multiple terminals collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the terminals.

[0452] Program Overview

[0453] This system assigns specific roles to both the terminal and the central server, and they work together. The following is a natural language explanation of the program processing of this system.

[0454] Device behavior

[0455] Data collection

[0456] The device collects environmental data at regular intervals, including temperature, humidity, soil quality, etc.

[0457] Data Preprocessing

[0458] The devices preprocess the collected raw data, specifically normalizing it and removing noise, so that the data can be sent to a central server in a unified format.

[0459] Data transmission

[0460] The preprocessed data is sent to a central server using an HTTP POST request, formatted as JSON and containing the device ID and the normalized data.

[0461] Server Operation

[0462] Data reception

[0463] The central server receives the data sent from the terminal and temporarily stores the received data on the server.

[0464] Data Aggregation

[0465] When a certain amount of data is collected, the server aggregates the data. For example, if data is collected from five devices, the server will combine the data into one set.

[0466] AI processing

[0467] Using the aggregated data, the central server runs AI models, which include analysis, prediction, model training, etc. The results of the AI ​​processing include, for example, recognition of averages and patterns in the environmental data.

[0468] Broadcasting the Results

[0469] The results of the AI ​​processing are sent simultaneously from the server to each device, which then receives the broadcasted results and displays them to the user.

[0470] User operations

[0471] Data confirmation

[0472] The user checks the results sent from the device, which include analysis of the environmental data collected by each device and recommended actions.

[0473] Specific examples

[0474] Example 1: Agricultural sensors

[0475] Multiple environmental sensors (terminals) are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture and send the data to a central server. The central server receives and aggregates this data and uses an AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize crops.

[0476] Example 2: Smart city air quality monitor

[0477] Multiple sensors (terminals) placed throughout the city collect air quality data and send it to a central server. The server analyzes the data and determines the air quality status of each area in real time. The results are broadcast, and citizens (users) can use this information to decide whether or not to go outside.

[0478] In this way, the present invention provides a system for efficient data collection, pre-processing, aggregation, AI processing, and feedback of results. By dividing each step, the system optimizes computing resources and improves overall performance.

[0479] The processing flow will be explained below.

[0480] Step 1:

[0481] The devices collect environmental data. This is done periodically, and each device uses its own sensors to acquire data such as temperature, humidity, and soil moisture. For example, the temperature sensor measures the air temperature and stores the acquired data in memory.

[0482] Step 2:

[0483] The data collected by the device is preprocessed. Preprocessing includes normalizing the raw data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value.

[0484] Step 3:

[0485] The device sends the preprocessed data to the central server using an HTTP POST request, which includes the device ID and the normalized data. For example, the normalized data is sent to the server in JSON format.

[0486] Step 4:

[0487] The server receives the data sent from the terminal. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to store the data.

[0488] Step 5:

[0489] When the server receives a certain number of data, it aggregates the data. For example, if data is sent from five devices, the perform_central_processing() function is called and the data is aggregated into one set.

[0490] Step 6:

[0491] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it concatenates the incoming data and calculates the average value of that data.

[0492] Step 7:

[0493] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device simultaneously. At this time, the results are sent in a format that each device can understand.

[0494] Step 8:

[0495] The terminal receives the results broadcast from the server, and displays the results or stores them in a database or memory as needed. For example, the results are displayed on the terminal display.

[0496] Step 9:

[0497] The user can view the results displayed on the device. For example, farmers can use the data from the sensors to adjust their farming operations. The user can then adjust the irrigation system or perform other agricultural activities based on the results displayed.

[0498] Example 1

[0499] 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."

[0500] Conventional data collection systems have problems with the inefficient execution of processes from environmental data collection to analysis and feedback of results, leading to the inability to optimize computing resources. Another issue is that individually collected data is not preprocessed according to uniform standards, making accurate analysis difficult. Furthermore, they are unable to perform real-time analysis of collected data and provide rapid decision support based on that analysis.

[0501] 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.

[0502] In this invention, the server includes: means for multiple terminals to collect environmental data; means for the terminals to preprocess the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive the data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing using a generative AI model; means for the terminals to broadcast the results of the AI ​​processing; and means for the terminals to receive and display the broadcasted results. This allows the entire process from data collection to analysis and result feedback to be executed efficiently, optimizing computing resources and providing analysis results in real time.

[0503] "Terminal" refers to the electronic device that collects environmental data, pre-processes it, and transmits the data to a central server.

[0504] "Environmental Data" refers to information related to the natural environment, such as temperature, humidity, soil quality, etc.

[0505] "Preprocessing" refers to the process of removing noise, normalizing, and otherwise processing collected raw data.

[0506] "Central server" refers to a system with central computing resources that performs a series of functions, including receiving data sent from devices, aggregating it, and processing it using AI models.

[0507] "Receiving" refers to the process by which the central server receives data sent from the terminal.

[0508] "Aggregation" refers to the process of combining multiple pieces of received data into a single data set.

[0509] A "generative AI model" refers to a model that uses pre-trained artificial intelligence algorithms to analyze data and make predictions.

[0510] "Broadcast" refers to the process in which a central server simultaneously transmits the results of AI processing to multiple devices.

[0511] "HTTP POST request" refers to a web communication protocol that allows a device to send pre-processed data to a central server.

[0512] This invention is a system that enables efficient data processing and the utilization of generative AI models by having multiple devices collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the devices.

[0513] Device behavior

[0514] The device uses sensors to collect environmental data. These sensors acquire data such as temperature, humidity, and soil quality at regular intervals. The collected raw data is preprocessed using Python's NumPy library. Specifically, the data is normalized and noise is removed to generate unified format data. After preprocessing is complete, the data is sent to the central server via an HTTP POST request using Python's requests library. This process allows the device to efficiently and accurately provide environmental data to the central server.

[0515] Server Operation

[0516] The central server receives data sent from devices using the Flask web framework. The received data is saved and temporarily stored in a MySQL database. Once a certain amount of data has been collected, the server performs an aggregation process using the Pandas library. This aggregation process combines data from multiple devices into a single dataset. The combined dataset is then analyzed and predicted using a generative AI model using libraries such as TensorFlow and PyTorch. This AI processing enables statistical information and pattern recognition of environmental data. Finally, the results of the AI ​​processing are broadcast simultaneously to each device using the WebSocket library.

[0517] User operations

[0518] The user can view the results broadcast from the devices. These results include analysis results of the environmental data collected by each device and recommended actions. The user can view the details of the data through the device interface, for example, by operating a GUI using the Tkinter library.

[0519] Specific examples

[0520] Example 1: Agricultural sensors

[0521] Multiple agricultural environmental sensors are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture, and transmit the data to a central server after preprocessing. The central server aggregates this data and uses a generative AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize their crops.

[0522] Example 2: Smart city air quality monitor

[0523] Multiple air quality sensors located throughout the city collect air quality data, which is then preprocessed and sent to a central server. The server aggregates the data and uses a generative AI model to analyze local air quality. The results are broadcast to citizens in real time, providing reference information for deciding whether or not to go outside.

[0524] Prompt Sentence Examples

[0525] An example prompt to input to a generative AI model might be, "Please tell me how to optimize temperature and humidity on a farm."

[0526] Thus, the present invention provides a system for efficient data collection, preprocessing, aggregation, AI processing using generative AI models, and feedback of the results. By dividing each step, computing resources can be optimized and overall performance can be improved.

[0527] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0528] Step 1:

[0529] The terminal collects environmental data. The input is raw data obtained from sensors such as temperature, humidity, and soil quality. The output is this raw data. Specifically, the temperature sensor measures the temperature, the humidity sensor measures the humidity, and the soil humidity sensor measures the moisture content of the soil.

[0530] Step 2:

[0531] The terminal preprocesses the raw data collected. The input is the raw data obtained in step 1. The output is the preprocessed data that has been denoised and normalised. Specifically, the terminal normalises the data using Python's NumPy library and uses filtering techniques to remove noise from the measurement data.

[0532] Step 3:

[0533] The terminal sends the preprocessed data to the central server. The input is the preprocessed data obtained in step 2. The output is the data sent to the central server via an HTTP POST request. Specifically, the terminal uses the Python requests library to convert the data into JSON format and send it to the central server via a POST request.

[0534] Step 4:

[0535] The server receives data sent from the device. The input is preprocessed data sent as an HTTP POST request. The output is the received data stored in a database. Specifically, the server uses the Flask web framework to receive the POST request and store the data in a MySQL database.

[0536] Step 5:

[0537] The server aggregates the data it receives. The input is data from multiple devices in a database. The output is an aggregated dataset. Specifically, the server uses the Pandas library to retrieve data from the database and organize it into a data frame. This data frame combines the data from multiple devices into a single dataset.

[0538] Step 6:

[0539] The server uses the aggregated data to perform AI processing using a generative AI model. The input is the aggregated data obtained in step 5. The output is analysis results and prediction results. Specifically, the server uses libraries such as TensorFlow and PyTorch to execute a pre-trained generative AI model to analyze and predict data.

[0540] Step 7:

[0541] The server broadcasts the results of the AI ​​processing to each device. The input is the AI ​​processing result obtained in step 6. The output is the broadcasted AI processing result. Specifically, the server uses the WebSocket library to simultaneously send the results of the AI ​​processing to each device.

[0542] Step 8:

[0543] The user checks the results sent from the device. The input is the broadcasted AI processing results. The output is the analysis results and recommended actions checked by the user. Specifically, the device uses a GUI library such as Tkinter to display the results to the user. The user decides on the appropriate action based on this information.

[0544] (Application example 1)

[0545] 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."

[0546] Logistics centers require optimal inventory management and efficient replenishment, but current systems make it difficult to collect and analyze data in real time, and the time it takes to consolidate and analyze data leads to problems such as stockouts and excess inventory.In addition, data collected by individual devices cannot be managed and analyzed in a unified manner, making it difficult to improve overall efficiency.

[0547] 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.

[0548] In this invention, the server includes: means for multiple terminals to collect environmental data; means for preprocessing the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for analyzing inventory data collected from multiple terminals in the logistics center and predicting optimal inventory allocation and replenishment timing. This enables real-time inventory management in the logistics center, preventing stockouts and excess inventory and improving overall efficiency.

[0549] A "terminal" is a device consisting of multiple environmental sensing devices and mobile devices for collecting and preprocessing environmental data.

[0550] "Environmental data" refers to various data that indicate the environmental conditions within the logistics center, such as temperature, humidity, weight, and air quality.

[0551] "Preprocessing" is the process of converting collected raw data using techniques such as noise removal and normalization to unify the data format.

[0552] The "central server" is a computer system that receives environmental data sent from multiple devices and aggregates and analyzes it.

[0553] "Aggregation" is the process of collecting and integrating data received from multiple devices into a single set.

[0554] "AI processing" is the process of running machine learning models and other AI models on aggregated data to perform analysis and make predictions.

[0555] "Broadcast" refers to the simultaneous transmission of the results of AI processing performed on a central server to multiple devices via a network.

[0556] "Inventory data" refers to data that indicates the inventory status of products managed within a logistics center, and includes attributes such as weight and quantity.

[0557] "Optimal placement" is a method for efficiently managing the placement of inventory items, with the aim of making effective use of space and improving work efficiency.

[0558] "Replenishment timing" is an indicator that indicates the optimal timing for appropriate replenishment before inventory runs out.

[0559] This invention is a system aimed at improving the efficiency of inventory management in logistics centers. The system includes multiple terminals, a central server, and analytical processing using an AI model. It also predicts optimal inventory placement and replenishment timing by coordinating real-time data collection, preprocessing, aggregation, analysis, and broadcasting.

[0560] The terminal collects inventory data using multiple environmental sensors in the distribution center. These environmental sensors periodically measure temperature, humidity, shelf weight (inventory status), etc. The measured data is preprocessed by the terminal to remove noise and normalize the data. The preprocessed data is sent to the central server in JSON format using an HTTP POST request.

[0561] The central server receives and temporarily stores data sent from the terminals. Next, once a certain amount of data has been collected, the server aggregates the data. The aggregated data is input into an AI model for analysis and prediction processing. The AI ​​model uses deep learning models and machine learning algorithms using Python. The analysis results include, for example, recommendations for optimal inventory placement and replenishment timing.

[0562] The results are broadcast from a central server to each terminal, which receives the results and displays them to the staff through a user interface, allowing staff to efficiently manage and replenish inventory based on real-time data.

[0563] As a concrete example, consider using this system in a distribution center. Smartphones are used within the center to collect temperature, humidity, and weight data from sensor devices on each product shelf. The collected data is preprocessed on the smartphone and sent to a central server. The central server analyzes the data and displays specific instructions on each device, such as "Product A is running low on stock, so it needs to be replenished immediately" or "Product B still has plenty of stock, so there is no need to replenish it."

[0564] The following sentences are used as examples of prompt sentences to input into the generative AI model:

[0565] "Please generate an AI model to predict the optimal replenishment timing using the current inventory status at the logistics center and the temperature and humidity data for each product as input data."

[0566] In this way, a system is realized that can streamline inventory management within the logistics center and prevent stockouts and excess inventory.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1:

[0569] The device collects environmental data.

[0570] (Specific actions)

[0571] Environmental sensors connected to the devices periodically measure temperature, humidity, shelf weight, etc. The collected data is stored in the memory of each device.

[0572] (input)

[0573] Raw environmental data obtained from environmental sensors.

[0574] (output)

[0575] Raw environmental data stored on the device.

[0576] Step 2:

[0577] Preprocess the data collected by the device.

[0578] (Specific actions)

[0579] The device performs noise reduction and data normalization on the collected data, for example, detecting and removing outliers and converting the data into a unified format.

[0580] (input)

[0581] Raw environmental data.

[0582] (output)

[0583] Preprocessed and normalized data.

[0584] Step 3:

[0585] The pre-processed data is sent to a central server.

[0586] (Specific actions)

[0587] The device converts the preprocessed data into JSON format and sends it to the central server using an HTTP POST request.

[0588] (input)

[0589] Preprocessed normalized data.

[0590] (output)

[0591] Data requests sent to a central server.

[0592] Step 4:

[0593] A central server receives data from the terminals.

[0594] (Specific actions)

[0595] The server extracts data from the received HTTP POST request and stores it temporarily in a database.

[0596] (input)

[0597] The data request sent.

[0598] (output)

[0599] Raw data stored on the server.

[0600] Step 5:

[0601] A central server aggregates the received data.

[0602] (Specific actions)

[0603] When the server receives a certain amount of data, it aggregates the data, calculates averages and totals, and compiles them into a unified data set.

[0604] (input)

[0605] Raw data stored on the server.

[0606] (output)

[0607] Aggregated datasets.

[0608] Step 6:

[0609] A central server analyzes the data using an AI model.

[0610] (Specific actions)

[0611] The collected data is input into an AI model to predict optimal inventory placement and replenishment timing. The prediction results are stored on the server.

[0612] (input)

[0613] Aggregated datasets.

[0614] (output)

[0615] Analysis results (optimal inventory placement and replenishment timing).

[0616] Step 7:

[0617] The results of AI processing are broadcast to the device.

[0618] (Specific actions)

[0619] The server converts the analysis results into JSON format and sends them to all connected devices simultaneously.

[0620] (input)

[0621] Analysis results.

[0622] (output)

[0623] Data broadcast to the device.

[0624] Step 8:

[0625] The terminal receives and displays the results.

[0626] (Specific actions)

[0627] The terminal analyzes the received data and displays it to the person in charge through the user interface. The analyzed data is displayed in an appropriate format, and the user can refer to it to manage inventory.

[0628] (input)

[0629] Broadcast data.

[0630] (output)

[0631] Analysis results displayed on the device.

[0632] 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.

[0633] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[0634] Program Overview

[0635] This system operates efficiently and flexibly through the cooperation of the terminals, the central server, and the emotion engine. The following is a natural language explanation of the program processing of this system.

[0636] Device behavior

[0637] Data collection

[0638] The device collects environmental data (e.g., temperature, humidity, soil moisture) and user emotion data (e.g., facial expression analysis, voice tone analysis). The emotion engine analyzes the user's emotion from facial expression and voice data and uses the results.

[0639] Data Preprocessing

[0640] The device preprocesses the collected environmental and emotional data. The environmental data is normalized and denoised, and the emotional data is preprocessed in the same way. For example, if the environmental data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value. The emotional data is also converted from binary to numeric data.

[0641] Data transmission

[0642] The preprocessed data is sent to a central server using an HTTP POST request. The data includes the device ID, environmental data, and emotion data. For example, the normalized data is sent to the server in JSON format.

[0643] Server Operation

[0644] Data reception

[0645] The server receives the environmental data and emotion data sent from the device, and the received data is temporarily stored in the server's memory or database.

[0646] Data Aggregation

[0647] When the server receives more than a certain number of data, it aggregates the data. For example, if data is sent from five devices, it aggregates each data into one set.

[0648] AI processing

[0649] Using the aggregated data, the server performs AI processing of both environmental and emotional data. AI processing includes data analysis, prediction, modeling, etc. For example, it calculates the average value of environmental data and analyzes the user's overall mood from emotional data.

[0650] Broadcasting the Results

[0651] The results of the AI ​​processing are sent from the server to each device simultaneously. For example, the broadcast_results() function is called and the results are sent to each device in a format that each device can understand.

[0652] User operations

[0653] Data confirmation

[0654] The user then checks the results sent from the device, which include feedback based on the analysis of the environmental data and emotional data, and can use this information to adjust their behavior.

[0655] Specific examples

[0656] Example 1: Agricultural sensors and sentiment analysis

[0657] Multiple sensors (terminals) installed on farms collect data on temperature, humidity, and soil moisture, while also collecting emotional data from the farmer (user)'s facial expressions and voice. A central server receives this data and performs AI processing to predict optimal growing conditions for crops. As a result, the farmer's stress level is provided along with recommended environmental conditions. Farmers can then adjust watering and fertilizer application based on this information.

[0658] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[0659] Multiple sensors (terminals) placed throughout the city collect air quality data, and an emotion engine collects emotion data from citizens (users). A central server receives this data and analyzes the air quality in each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[0660] In this way, the present invention provides a distributed AI system that combines an emotion engine and realizes efficient data collection, preprocessing, aggregation, AI processing, and feedback of results, enabling advanced analysis and judgment using environmental data and user emotion data.

[0661] The processing flow will be explained below.

[0662] Step 1:

[0663] The device collects environmental data and user emotional data. Environmental data is acquired using sensors, and emotional data is analyzed using an emotion engine based on facial expressions and voice. For example, a temperature sensor acquires the temperature, and a microphone and camera capture the user's voice and facial expressions.

[0664] Step 2:

[0665] Preprocessing the environmental data collected by the device. Preprocessing includes normalizing the data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], calculate the average value and then normalize each data point by dividing it by the average value.

[0666] Step 3:

[0667] The device preprocesses the emotion data. The emotion engine converts the binary data into numerical data. For example, it extracts a happiness score from the user's facial expression and stores it in numerical format.

[0668] Step 4:

[0669] The device sends the preprocessed environmental data and emotion data to the central server. The data is sent in JSON format using an HTTP POST request, which includes the device ID, the preprocessed environmental data, and the emotion data.

[0670] Step 5:

[0671] The server receives the environmental data and emotion data sent from the device. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to save the data.

[0672] Step 6:

[0673] When the server receives a certain amount of data, it aggregates the environmental data and emotional data. For example, if data is collected from five devices, the server will combine the data into one set.

[0674] Step 7:

[0675] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it can concatenate the incoming data, calculate the average value of environmental data, and analyze the user's overall mood using emotional data.

[0676] Step 8:

[0677] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device. The results include the analysis results of the environmental data and the user's emotional state.

[0678] Step 9:

[0679] The device receives the results broadcast from the server. The received results are stored in the device and displayed on the screen as needed. For example, the device may recommend temperature adjustments or provide information based on emotions.

[0680] Step 10:

[0681] The user sees the results displayed on their device and can adjust their behavior based on the results, for example, changing their work environment or adjusting irrigation systems in agriculture depending on their emotional state.

[0682] Example 2

[0683] 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."

[0684] Conventional AI systems have struggled to efficiently collect, preprocess, and analyze environmental and user emotional data, and provide rapid feedback. Ensuring the quality and consistency of data collected from individual devices in distributed systems also poses challenges. In particular, there is a need for systems to analyze diverse data in real time and provide useful feedback to users based on that data.

[0685] 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.

[0686] In this invention, the server includes: means for multiple terminals to collect environmental data and user emotional data; means for performing preprocessing, including normalization and noise removal, on the environmental data and emotional data collected by the terminals; means for the central server to receive the environmental data and emotional data transmitted from the terminals; means for the central server to aggregate the received environmental data and emotional data and trigger AI processing when a certain amount of data is received; means for executing AI processing and broadcasting the results to the terminals; and means for the terminals to receive and display the broadcasted results. This enables a series of processes of efficient data collection, preprocessing, analysis, and feedback in a distributed AI system.

[0687] A "terminal" is a device that collects environmental data and user emotion data, and transmits the data to a central server after preprocessing.

[0688] "Environmental data" is a collection of information that describes physical environmental conditions, such as temperature, humidity, and soil moisture.

[0689] "User emotion data" is a collection of information that indicates the user's emotional state, analyzed from facial expressions, tone of voice, and the like.

[0690] "Preprocessing" refers to data shaping operations such as normalization and noise removal that are performed on collected data.

[0691] The "central server" is a computer system that receives data sent from the terminals, aggregates it, performs AI processing, and broadcasts the results to the terminals.

[0692] "Aggregation" is the operation of combining data collected from multiple terminals into a single data set.

[0693] "AI processing" is the process of analyzing data using machine learning algorithms to make predictions and modeling.

[0694] "Broadcast" is an operation in which the central server transmits the processing results to all terminals simultaneously.

[0695] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[0696] System Configuration

[0697] Hardware and Software

[0698] The device includes a temperature sensor, humidity sensor, facial recognition camera, and microphone, and these devices collect environmental data and user emotional data in real time. Specifically, it uses DHT22 as a temperature sensor, OpenCV for facial recognition, and TensorFlow for voice recognition. These devices are connected to a single-board computer such as a Raspberry Pi.

[0699] The central server is a high-performance computer that aggregates the received data and uses machine learning frameworks such as PyTorch and Scikit-learn in Python to perform AI processing.

[0700] Program processing

[0701] The device collects environmental and emotional data and preprocesses it. Preprocessing includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. This process is performed using data processing libraries such as NumPy and Pandas.

[0702] The terminal sends the preprocessed data to the central server via an HTTP POST request, using JSON format.

[0703] The central server temporarily stores the received data in memory or a database (e.g., MySQL). When a certain amount of data is received, aggregation processing is triggered and AI processing is performed. This AI processing includes analysis and prediction of environmental data and modeling of emotional data. Specific processing examples include calculating the average value of environmental data and predicting the user's mood using emotional data.

[0704] The server broadcasts the results of the AI ​​processing to the devices, which then receive the results and display them to the user via a web interface or mobile application.

[0705] Specific examples

[0706] Example 1: Agricultural sensors and sentiment analysis

[0707] Agricultural sensors (terminals) collect data on the temperature, humidity, and soil moisture of the farm, while also collecting emotional data from the farmer's (user's) facial expressions and voice. A central server receives this data and performs AI processing to predict the optimal growing conditions for crops. As a result, it provides recommendations for environmental conditions and the farmer's stress level. Farmers can then adjust watering and fertilizer application based on this information.

[0708] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[0709] Multiple sensors (terminals) placed in the smart city collect air quality data and use an emotion engine to analyze the emotional data of citizens (users). A central server receives this data and analyzes the air quality of each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[0710] Prompt Sentence Examples

[0711] Agricultural sensors and sentiment analysis

[0712] Design a system that integrates agricultural sensors and an emotion engine to collect temperature, humidity, soil moisture data and user emotion data, analyze it through an AI model, and broadcast the results. As a concrete example, demonstrate how to predict crop growth conditions and provide farmers' stress levels.

[0713] Smart city air quality monitoring and citizen sentiment analysis

[0714] Integrate an emotion engine into a smart city's air quality monitoring system to design a system that monitors and analyzes citizen emotion data and air quality data in real time. As a concrete example, demonstrate how to analyze local air quality and the overall emotion state of citizens and broadcast the results to citizens.

[0715] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0716] Step 1: Data collection

[0717] The device collects environmental data such as temperature, humidity, and soil moisture, as well as user emotional data (facial expressions and voice tone). Specifically, it uses temperature and humidity sensors, a facial recognition camera (using OpenCV), and a microphone for voice analysis (using TensorFlow).

[0718] Input: Temperature sensor, humidity sensor, facial recognition camera, voice analysis microphone

[0719] Output: Environmental data (temperature, humidity, soil moisture) and emotional data (facial expression analysis results, voice tone analysis results)

[0720] Step 2: Data Preprocessing

[0721] The device preprocesses the collected environmental and emotional data. This includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. For example, temperature data is normalized by dividing it by the average value, and facial expression data is converted to 1 for positive and 0 for negative.

[0722] Input: Collected environmental and emotional data

[0723] Output: Preprocessed environmental and emotional data

[0724] Step 3: Send data

[0725] The device sends the preprocessed data to the central server using an HTTP POST request, with the data structured in JSON format.

[0726] Input: Preprocessed environmental and emotion data

[0727] Output: JSON format data sent to the central server

[0728] Step 4: Receiving Data

[0729] The server receives the environmental data and emotion data sent from the device, and temporarily stores the received data in memory or a database (e.g., MySQL).

[0730] Input: Data sent from the terminal (JSON format)

[0731] Output: Data stored in memory or in a database

[0732] Step 5: Data Aggregation

[0733] When the server receives a certain number of data sets, it aggregates them. For example, it aggregates data sets from five devices into one set.

[0734] Input: Received data from multiple devices

[0735] Output: Aggregated dataset

[0736] Step 6: AI processing

[0737] The server uses the aggregated data to perform AI processing, including data analysis, prediction, and modeling. Specifically, it calculates the average value of environmental data and predicts the user's mood using emotional data. This processing is performed using PyTorch and Scikit-learn.

[0738] Input: Aggregated dataset (environmental and emotional data)

[0739] Output: Analysis results by AI processing

[0740] Step 7: Broadcasting the results

[0741] The server simultaneously sends the results of the AI ​​processing to each device in JSON format, which each device can receive and display to the user.

[0742] Input: Analysis results by AI processing

[0743] Output: Analysis results broadcast to the device

[0744] Step 8: Data verification

[0745] The user checks the results received by the device, which are displayed on the device's display or in a mobile application, and adjusts their actions based on the information.

[0746] Input: Analysis results displayed on the terminal

[0747] Output: User behavior adjustment

[0748] Through the above steps, the present invention achieves efficient data collection, pre-processing, analysis, and feedback, enabling advanced analysis and judgment.

[0749] (Application example 2)

[0750] 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."

[0751] Conventional customer experience optimization systems for brick-and-mortar stores were limited to collecting environmental data and had difficulty utilizing user emotional data. As a result, they were unable to respond to real-time changes in customer emotions, resulting in limited improvements in customer satisfaction. In addition, there was a lack of a mechanism to efficiently aggregate collected environmental and emotional data and take appropriate action, making it difficult for staff to utilize the information in real time.

[0752] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for multiple terminals to collect environmental data and user emotion data; means for the terminals to preprocess the collected environmental data and emotion data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for the terminals to provide instructions for taking actions based on user operations. This makes it possible to utilize environmental data and user emotion data in real time and quickly provide specific actions to optimize the customer experience.

[0753] A "terminal" is a device that collects environmental data and user emotion data, and performs preprocessing and data transmission.

[0754] "Environmental data" refers to information about the physical environment, such as temperature and humidity.

[0755] "User emotional data" refers to information about the user's emotional state detected using facial expression analysis and voice tone analysis.

[0756] "Preprocessing" refers to performing processes such as normalization and noise removal on collected data.

[0757] The "central server" is a server that receives and aggregates data sent from terminals and then performs AI processing.

[0758] "AI processing" refers to the process of analyzing received data and making predictions and modeling.

[0759] "Broadcast" refers to sending AI-processed results to multiple devices simultaneously.

[0760] "Means for providing instructions for the terminal to take an action based on the user's operation" refers to a function in which the terminal indicates the action that the user should take based on the broadcasted results.

[0761] This invention is a system in which multiple devices collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the devices, thereby optimizing the customer experience in physical stores.

[0762] Overall system configuration

[0763] The system consists of the following components:

[0764] Device: Smart glasses or head-mounted display

[0765] Central Server

[0766] Emotion Engine

[0767] Network connection: Wi-Fi or LTE

[0768] Program processing flow

[0769] Hardware and Software

[0770] 1. Terminal

[0771] Devices used: smart glasses, head-mounted displays

[0772] Data collection: The device collects environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[0773] 2. Emotion Engine

[0774] Software: TensorFlow, Keras

[0775] Function: Analyzes facial expressions and voice tones to quantify the user's emotional state

[0776] 3. Central Server

[0777] Software used: Python, JavaScript, Database Management System

[0778] Functions: Data reception, preprocessing, aggregation, AI analysis, and broadcasting of results

[0779] Specific AI models: TensorFlow, Keras

[0780] Processing Details

[0781] 1. Data Collection

[0782] The device collects environmental and emotional data, such as temperature of 22 degrees, humidity of 45%, and customer emotions of 0.8 happiness and 0.2 stress.

[0783] 2. Data Preprocessing

[0784] The device normalizes and denoises the collected data and preprocesses it. For example, environmental data is normalized based on the average value, and emotion data is converted from binary to numerical data.

[0785] 3. Data Transmission

[0786] The pre-processed data is sent to a central server using an HTTP POST request.

[0787] 4. Data Reception and Aggregation

[0788] The central server receives the data and aggregates it over a certain number of devices, for example, combining data from five devices into one set.

[0789] 5. AI Processing

[0790] The aggregated data is then used by the AI ​​model to perform analysis, for example, calculating average values ​​for environmental data and analyzing the user's overall mood from emotional data.

[0791] 6. Broadcasting the Results

[0792] The results of the AI ​​processing are sent simultaneously from a central server to each device, which receives the results and displays them to the user.

[0793] Examples of concrete examples and prompts

[0794] Specific examples

[0795] After analyzing customer emotional data (happiness level 0.7, stress level 0.3) in a specific store area, the central server recommends deploying additional staff support in this area. When staff act on this instruction, the customer experience is improved.

[0796] Prompt Sentence Examples

[0797] Enter the following prompt into the generative AI model:

[0798] Based on the customer's facial expression data and in-store environmental data, recommend an action to optimize customer satisfaction. The specific customer's emotional state is as follows: Happiness level 0.5, Stress level 0.5. The environmental data is as follows: Temperature 22.0°C, Humidity 45%. Please specify the recommended action.

[0799] The above is an embodiment of the present invention, which makes it possible to optimize the customer experience in a physical store by utilizing environmental data and user emotion data.

[0800] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0801] Step 1:

[0802] Data collection

[0803] The device uses smart glasses or a head-mounted display to collect environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[0804] Input: Real-time environmental and emotional data

[0805] Output: Collected raw data (e.g., temperature 22.0°C, humidity 45%, happiness level 0.8, stress level 0.2)

[0806] Step 2:

[0807] Data Preprocessing

[0808] The environmental data and emotion data collected by the device are pre-processed by normalizing and removing noise.

[0809] Input: Raw data collected

[0810] Data processing: Normalization of environmental data by the average value, conversion of emotion data from binary to numerical data

[0811] Output: Preprocessed data (e.g., normalized temperature data, sentiment analysis results as numerical data)

[0812] Step 3:

[0813] Data transmission

[0814] The device sends the pre-processed data to the central server using an HTTP POST request.

[0815] Input: Preprocessed data

[0816] Output: JSON format data sent to the central server

[0817] Step 4:

[0818] Data reception and aggregation

[0819] A central server receives the data sent from the terminals and temporarily stores it in a database or memory.

[0820] Input: Data sent from the terminal

[0821] Data processing: preparing data for storage and aggregation in a database

[0822] Output: Saved dataset

[0823] Step 5:

[0824] Triggering AI processing

[0825] When the central server receives a certain amount of data, it triggers AI processing.

[0826] Input: Aggregated dataset

[0827] Output: AI processing start instruction

[0828] Step 6:

[0829] Data aggregation and analysis

[0830] The central server analyzes the aggregated data using AI models (TensorFlow, Keras) and predicts the user's overall mood based on environmental and emotional data.

[0831] Input: Aggregated preprocessed dataset

[0832] Data calculation: Data analysis and mood prediction using AI models

[0833] Output: Analysis results (e.g., recommended actions, overall mood)

[0834] Step 7:

[0835] Broadcasting the Results

[0836] The central server broadcasts the results of AI processing to all devices simultaneously.

[0837] Input: AI analysis results

[0838] Output: Broadcast results sent to the device

[0839] Step 8:

[0840] Displaying results and prompting

[0841] The terminal receives the broadcasted results and displays them to the staff, and also provides instructions for taking action based on the user's actions.

[0842] Input: Broadcast result from server

[0843] Output: Instructions and data displayed on the terminal (e.g., "Deploy additional staff to Area B")

[0844] Step 9:

[0845] User Behavior

[0846] The user takes actual actions based on instructions from the terminal, such as allocating additional staff or presenting discount offers.

[0847] Input: Instructions from the terminal

[0848] Output: Specific actions aimed at improving customer experience

[0849] 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.

[0850] 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.

[0851] 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.

[0852] [Third embodiment]

[0853] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0854] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0855] 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).

[0856] 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.

[0857] 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.

[0858] 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).

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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."

[0865] This invention is a system that enables efficient data processing and the utilization of AI by having multiple terminals collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the terminals.

[0866] Program Overview

[0867] This system assigns specific roles to both the terminal and the central server, and they work together. The following is a natural language explanation of the program processing of this system.

[0868] Device behavior

[0869] Data collection

[0870] The device collects environmental data at regular intervals, including temperature, humidity, soil quality, etc.

[0871] Data Preprocessing

[0872] The devices preprocess the collected raw data, specifically normalizing it and removing noise, so that the data can be sent to a central server in a unified format.

[0873] Data transmission

[0874] The preprocessed data is sent to a central server using an HTTP POST request, formatted as JSON and containing the device ID and the normalized data.

[0875] Server Operation

[0876] Data reception

[0877] The central server receives the data sent from the terminal and temporarily stores the received data on the server.

[0878] Data Aggregation

[0879] When a certain amount of data is collected, the server aggregates the data. For example, if data is collected from five devices, the server will combine the data into one set.

[0880] AI processing

[0881] Using the aggregated data, the central server runs AI models, which include analysis, prediction, model training, etc. The results of the AI ​​processing include, for example, recognition of averages and patterns in the environmental data.

[0882] Broadcasting the Results

[0883] The results of the AI ​​processing are sent simultaneously from the server to each device, which then receives the broadcasted results and displays them to the user.

[0884] User operations

[0885] Data confirmation

[0886] The user checks the results sent from the device, which include analysis of the environmental data collected by each device and recommended actions.

[0887] Specific examples

[0888] Example 1: Agricultural sensors

[0889] Multiple environmental sensors (terminals) are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture and send the data to a central server. The central server receives and aggregates this data and uses an AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize crops.

[0890] Example 2: Smart city air quality monitor

[0891] Multiple sensors (terminals) placed throughout the city collect air quality data and send it to a central server. The server analyzes the data and determines the air quality status of each area in real time. The results are broadcast, and citizens (users) can use this information to decide whether or not to go outside.

[0892] In this way, the present invention provides a system for efficient data collection, pre-processing, aggregation, AI processing, and feedback of results. By dividing each step, the system optimizes computing resources and improves overall performance.

[0893] The processing flow will be explained below.

[0894] Step 1:

[0895] The devices collect environmental data. This is done periodically, and each device uses its own sensors to acquire data such as temperature, humidity, and soil moisture. For example, the temperature sensor measures the air temperature and stores the acquired data in memory.

[0896] Step 2:

[0897] The data collected by the device is preprocessed. Preprocessing includes normalizing the raw data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value.

[0898] Step 3:

[0899] The device sends the preprocessed data to the central server using an HTTP POST request, which includes the device ID and the normalized data. For example, the normalized data is sent to the server in JSON format.

[0900] Step 4:

[0901] The server receives the data sent from the terminal. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to store the data.

[0902] Step 5:

[0903] When the server receives a certain number of data, it aggregates the data. For example, if data is sent from five devices, the perform_central_processing() function is called and the data is aggregated into one set.

[0904] Step 6:

[0905] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it concatenates the incoming data and calculates the average value of that data.

[0906] Step 7:

[0907] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device simultaneously. At this time, the results are sent in a format that each device can understand.

[0908] Step 8:

[0909] The terminal receives the results broadcast from the server, and displays the results or stores them in a database or memory as needed. For example, the results are displayed on the terminal display.

[0910] Step 9:

[0911] The user can view the results displayed on the device. For example, farmers can use the data from the sensors to adjust their farming operations. The user can then adjust the irrigation system or perform other agricultural activities based on the results displayed.

[0912] Example 1

[0913] 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."

[0914] Conventional data collection systems have problems with the inefficient execution of processes from environmental data collection to analysis and feedback of results, leading to the inability to optimize computing resources. Another issue is that individually collected data is not preprocessed according to uniform standards, making accurate analysis difficult. Furthermore, they are unable to perform real-time analysis of collected data and provide rapid decision support based on that analysis.

[0915] 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.

[0916] In this invention, the server includes: means for multiple terminals to collect environmental data; means for the terminals to preprocess the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive the data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing using a generative AI model; means for the terminals to broadcast the results of the AI ​​processing; and means for the terminals to receive and display the broadcasted results. This allows the entire process from data collection to analysis and result feedback to be executed efficiently, optimizing computing resources and providing analysis results in real time.

[0917] "Terminal" refers to the electronic device that collects environmental data, pre-processes it, and transmits the data to a central server.

[0918] "Environmental Data" refers to information related to the natural environment, such as temperature, humidity, soil quality, etc.

[0919] "Preprocessing" refers to the process of removing noise, normalizing, and otherwise processing collected raw data.

[0920] "Central server" refers to a system with central computing resources that performs a series of functions, including receiving data sent from devices, aggregating it, and processing it using AI models.

[0921] "Receiving" refers to the process by which the central server receives data sent from the terminal.

[0922] "Aggregation" refers to the process of combining multiple pieces of received data into a single data set.

[0923] A "generative AI model" refers to a model that uses pre-trained artificial intelligence algorithms to analyze data and make predictions.

[0924] "Broadcast" refers to the process in which a central server simultaneously transmits the results of AI processing to multiple devices.

[0925] "HTTP POST request" refers to a web communication protocol that allows a device to send pre-processed data to a central server.

[0926] This invention is a system that enables efficient data processing and the utilization of generative AI models by having multiple devices collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the devices.

[0927] Device behavior

[0928] The device uses sensors to collect environmental data. These sensors acquire data such as temperature, humidity, and soil quality at regular intervals. The collected raw data is preprocessed using Python's NumPy library. Specifically, the data is normalized and noise is removed to generate unified format data. After preprocessing is complete, the data is sent to the central server via an HTTP POST request using Python's requests library. This process allows the device to efficiently and accurately provide environmental data to the central server.

[0929] Server Operation

[0930] The central server receives data sent from devices using the Flask web framework. The received data is saved and temporarily stored in a MySQL database. Once a certain amount of data has been collected, the server performs an aggregation process using the Pandas library. This aggregation process combines data from multiple devices into a single dataset. The combined dataset is then analyzed and predicted using a generative AI model using libraries such as TensorFlow and PyTorch. This AI processing enables statistical information and pattern recognition of environmental data. Finally, the results of the AI ​​processing are broadcast simultaneously to each device using the WebSocket library.

[0931] User operations

[0932] The user can view the results broadcast from the devices. These results include analysis results of the environmental data collected by each device and recommended actions. The user can view the details of the data through the device interface, for example, by operating a GUI using the Tkinter library.

[0933] Specific examples

[0934] Example 1: Agricultural sensors

[0935] Multiple agricultural environmental sensors are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture, and transmit the data to a central server after preprocessing. The central server aggregates this data and uses a generative AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize their crops.

[0936] Example 2: Smart city air quality monitor

[0937] Multiple air quality sensors located throughout the city collect air quality data, which is then preprocessed and sent to a central server. The server aggregates the data and uses a generative AI model to analyze local air quality. The results are broadcast to citizens in real time, providing reference information for deciding whether or not to go outside.

[0938] Prompt Sentence Examples

[0939] An example prompt to input to a generative AI model might be, "Please tell me how to optimize temperature and humidity on a farm."

[0940] Thus, the present invention provides a system for efficient data collection, preprocessing, aggregation, AI processing using generative AI models, and feedback of the results. By dividing each step, computing resources can be optimized and overall performance can be improved.

[0941] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0942] Step 1:

[0943] The terminal collects environmental data. The input is raw data obtained from sensors such as temperature, humidity, and soil quality. The output is this raw data. Specifically, the temperature sensor measures the temperature, the humidity sensor measures the humidity, and the soil humidity sensor measures the moisture content of the soil.

[0944] Step 2:

[0945] The terminal preprocesses the raw data collected. The input is the raw data obtained in step 1. The output is the preprocessed data that has been denoised and normalised. Specifically, the terminal normalises the data using Python's NumPy library and uses filtering techniques to remove noise from the measurement data.

[0946] Step 3:

[0947] The terminal sends the preprocessed data to the central server. The input is the preprocessed data obtained in step 2. The output is the data sent to the central server via an HTTP POST request. Specifically, the terminal uses the Python requests library to convert the data into JSON format and send it to the central server via a POST request.

[0948] Step 4:

[0949] The server receives data sent from the device. The input is preprocessed data sent as an HTTP POST request. The output is the received data stored in a database. Specifically, the server uses the Flask web framework to receive the POST request and store the data in a MySQL database.

[0950] Step 5:

[0951] The server aggregates the data it receives. The input is data from multiple devices in a database. The output is an aggregated dataset. Specifically, the server uses the Pandas library to retrieve data from the database and organize it into a data frame. This data frame combines the data from multiple devices into a single dataset.

[0952] Step 6:

[0953] The server uses the aggregated data to perform AI processing using a generative AI model. The input is the aggregated data obtained in step 5. The output is analysis results and prediction results. Specifically, the server uses libraries such as TensorFlow and PyTorch to execute a pre-trained generative AI model to analyze and predict data.

[0954] Step 7:

[0955] The server broadcasts the results of the AI ​​processing to each device. The input is the AI ​​processing result obtained in step 6. The output is the broadcasted AI processing result. Specifically, the server uses the WebSocket library to simultaneously send the results of the AI ​​processing to each device.

[0956] Step 8:

[0957] The user checks the results sent from the device. The input is the broadcasted AI processing results. The output is the analysis results and recommended actions checked by the user. Specifically, the device uses a GUI library such as Tkinter to display the results to the user. The user decides on the appropriate action based on this information.

[0958] (Application example 1)

[0959] 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."

[0960] Logistics centers require optimal inventory management and efficient replenishment, but current systems make it difficult to collect and analyze data in real time, and the time it takes to consolidate and analyze data leads to problems such as stockouts and excess inventory.In addition, data collected by individual devices cannot be managed and analyzed in a unified manner, making it difficult to improve overall efficiency.

[0961] 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.

[0962] In this invention, the server includes: means for multiple terminals to collect environmental data; means for preprocessing the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for analyzing inventory data collected from multiple terminals in the logistics center and predicting optimal inventory allocation and replenishment timing. This enables real-time inventory management in the logistics center, preventing stockouts and excess inventory and improving overall efficiency.

[0963] A "terminal" is a device consisting of multiple environmental sensing devices and mobile devices for collecting and preprocessing environmental data.

[0964] "Environmental data" refers to various data that indicate the environmental conditions within the logistics center, such as temperature, humidity, weight, and air quality.

[0965] "Preprocessing" is the process of converting collected raw data using techniques such as noise removal and normalization to unify the data format.

[0966] The "central server" is a computer system that receives environmental data sent from multiple devices and aggregates and analyzes it.

[0967] "Aggregation" is the process of collecting and integrating data received from multiple devices into a single set.

[0968] "AI processing" is the process of running machine learning models and other AI models on aggregated data to perform analysis and make predictions.

[0969] "Broadcast" refers to the simultaneous transmission of the results of AI processing performed on a central server to multiple devices via a network.

[0970] "Inventory data" refers to data that indicates the inventory status of products managed within a logistics center, and includes attributes such as weight and quantity.

[0971] "Optimal placement" is a method for efficiently managing the placement of inventory items, with the aim of making effective use of space and improving work efficiency.

[0972] "Replenishment timing" is an indicator that indicates the optimal timing for appropriate replenishment before inventory runs out.

[0973] This invention is a system aimed at improving the efficiency of inventory management in logistics centers. The system includes multiple terminals, a central server, and analytical processing using an AI model. It also predicts optimal inventory placement and replenishment timing by coordinating real-time data collection, preprocessing, aggregation, analysis, and broadcasting.

[0974] The terminal collects inventory data using multiple environmental sensors in the distribution center. These environmental sensors periodically measure temperature, humidity, shelf weight (inventory status), etc. The measured data is preprocessed by the terminal to remove noise and normalize the data. The preprocessed data is sent to the central server in JSON format using an HTTP POST request.

[0975] The central server receives and temporarily stores data sent from the terminals. Next, once a certain amount of data has been collected, the server aggregates the data. The aggregated data is input into an AI model for analysis and prediction processing. The AI ​​model uses deep learning models and machine learning algorithms using Python. The analysis results include, for example, recommendations for optimal inventory placement and replenishment timing.

[0976] The results are broadcast from a central server to each terminal, which receives the results and displays them to the staff through a user interface, allowing staff to efficiently manage and replenish inventory based on real-time data.

[0977] As a concrete example, consider using this system in a distribution center. Smartphones are used within the center to collect temperature, humidity, and weight data from sensor devices on each product shelf. The collected data is preprocessed on the smartphone and sent to a central server. The central server analyzes the data and displays specific instructions on each device, such as "Product A is running low on stock, so it needs to be replenished immediately" or "Product B still has plenty of stock, so there is no need to replenish it."

[0978] The following sentences are used as examples of prompt sentences to input into the generative AI model:

[0979] "Please generate an AI model to predict the optimal replenishment timing using the current inventory status at the logistics center and the temperature and humidity data for each product as input data."

[0980] In this way, a system is realized that can streamline inventory management within the logistics center and prevent stockouts and excess inventory.

[0981] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0982] Step 1:

[0983] The device collects environmental data.

[0984] (Specific actions)

[0985] Environmental sensors connected to the devices periodically measure temperature, humidity, shelf weight, etc. The collected data is stored in the memory of each device.

[0986] (input)

[0987] Raw environmental data obtained from environmental sensors.

[0988] (output)

[0989] Raw environmental data stored on the device.

[0990] Step 2:

[0991] Preprocess the data collected by the device.

[0992] (Specific actions)

[0993] The device performs noise reduction and data normalization on the collected data, for example, detecting and removing outliers and converting the data into a unified format.

[0994] (input)

[0995] Raw environmental data.

[0996] (output)

[0997] Preprocessed and normalized data.

[0998] Step 3:

[0999] The pre-processed data is sent to a central server.

[1000] (Specific actions)

[1001] The device converts the preprocessed data into JSON format and sends it to the central server using an HTTP POST request.

[1002] (input)

[1003] Preprocessed normalized data.

[1004] (output)

[1005] Data requests sent to a central server.

[1006] Step 4:

[1007] A central server receives data from the terminals.

[1008] (Specific actions)

[1009] The server extracts data from the received HTTP POST request and stores it temporarily in a database.

[1010] (input)

[1011] The data request sent.

[1012] (output)

[1013] Raw data stored on the server.

[1014] Step 5:

[1015] A central server aggregates the received data.

[1016] (Specific actions)

[1017] When the server receives a certain amount of data, it aggregates the data, calculates averages and totals, and compiles them into a unified data set.

[1018] (input)

[1019] Raw data stored on the server.

[1020] (output)

[1021] Aggregated datasets.

[1022] Step 6:

[1023] A central server analyzes the data using an AI model.

[1024] (Specific actions)

[1025] The collected data is input into an AI model to predict optimal inventory placement and replenishment timing. The prediction results are stored on the server.

[1026] (input)

[1027] Aggregated datasets.

[1028] (output)

[1029] Analysis results (optimal inventory placement and replenishment timing).

[1030] Step 7:

[1031] The results of AI processing are broadcast to the device.

[1032] (Specific actions)

[1033] The server converts the analysis results into JSON format and sends them to all connected devices simultaneously.

[1034] (input)

[1035] Analysis results.

[1036] (output)

[1037] Data broadcast to the device.

[1038] Step 8:

[1039] The terminal receives and displays the results.

[1040] (Specific actions)

[1041] The terminal analyzes the received data and displays it to the person in charge through the user interface. The analyzed data is displayed in an appropriate format, and the user can refer to it to manage inventory.

[1042] (input)

[1043] Broadcast data.

[1044] (output)

[1045] Analysis results displayed on the device.

[1046] 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.

[1047] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[1048] Program Overview

[1049] This system operates efficiently and flexibly through the cooperation of the terminals, the central server, and the emotion engine. The following is a natural language explanation of the program processing of this system.

[1050] Device behavior

[1051] Data collection

[1052] The device collects environmental data (e.g., temperature, humidity, soil moisture) and user emotion data (e.g., facial expression analysis, voice tone analysis). The emotion engine analyzes the user's emotion from facial expression and voice data and uses the results.

[1053] Data Preprocessing

[1054] The device preprocesses the collected environmental and emotional data. The environmental data is normalized and denoised, and the emotional data is preprocessed in the same way. For example, if the environmental data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value. The emotional data is also converted from binary to numeric data.

[1055] Data transmission

[1056] The preprocessed data is sent to a central server using an HTTP POST request. The data includes the device ID, environmental data, and emotion data. For example, the normalized data is sent to the server in JSON format.

[1057] Server Operation

[1058] Data reception

[1059] The server receives the environmental data and emotion data sent from the device, and the received data is temporarily stored in the server's memory or database.

[1060] Data Aggregation

[1061] When the server receives more than a certain number of data, it aggregates the data. For example, if data is sent from five devices, it aggregates each data into one set.

[1062] AI processing

[1063] Using the aggregated data, the server performs AI processing of both environmental and emotional data. AI processing includes data analysis, prediction, modeling, etc. For example, it calculates the average value of environmental data and analyzes the user's overall mood from emotional data.

[1064] Broadcasting the Results

[1065] The results of the AI ​​processing are sent from the server to each device simultaneously. For example, the broadcast_results() function is called and the results are sent to each device in a format that each device can understand.

[1066] User operations

[1067] Data confirmation

[1068] The user then checks the results sent from the device, which include feedback based on the analysis of the environmental data and emotional data, and can use this information to adjust their behavior.

[1069] Specific examples

[1070] Example 1: Agricultural sensors and sentiment analysis

[1071] Multiple sensors (terminals) installed on farms collect data on temperature, humidity, and soil moisture, while also collecting emotional data from the farmer (user)'s facial expressions and voice. A central server receives this data and performs AI processing to predict optimal growing conditions for crops. As a result, the farmer's stress level is provided along with recommended environmental conditions. Farmers can then adjust watering and fertilizer application based on this information.

[1072] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[1073] Multiple sensors (terminals) placed throughout the city collect air quality data, and an emotion engine collects emotion data from citizens (users). A central server receives this data and analyzes the air quality in each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[1074] In this way, the present invention provides a distributed AI system that combines an emotion engine and realizes efficient data collection, preprocessing, aggregation, AI processing, and feedback of results, enabling advanced analysis and judgment using environmental data and user emotion data.

[1075] The processing flow will be explained below.

[1076] Step 1:

[1077] The device collects environmental data and user emotional data. Environmental data is acquired using sensors, and emotional data is analyzed using an emotion engine based on facial expressions and voice. For example, a temperature sensor acquires the temperature, and a microphone and camera capture the user's voice and facial expressions.

[1078] Step 2:

[1079] Preprocessing the environmental data collected by the device. Preprocessing includes normalizing the data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], calculate the average value and then normalize each data point by dividing it by the average value.

[1080] Step 3:

[1081] The device preprocesses the emotion data. The emotion engine converts the binary data into numerical data. For example, it extracts a happiness score from the user's facial expression and stores it in numerical format.

[1082] Step 4:

[1083] The device sends the preprocessed environmental data and emotion data to the central server. The data is sent in JSON format using an HTTP POST request, which includes the device ID, the preprocessed environmental data, and the emotion data.

[1084] Step 5:

[1085] The server receives the environmental data and emotion data sent from the device. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to save the data.

[1086] Step 6:

[1087] When the server receives a certain amount of data, it aggregates the environmental data and emotional data. For example, if data is collected from five devices, the server will combine the data into one set.

[1088] Step 7:

[1089] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it can concatenate the incoming data, calculate the average value of environmental data, and analyze the user's overall mood using emotional data.

[1090] Step 8:

[1091] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device. The results include the analysis results of the environmental data and the user's emotional state.

[1092] Step 9:

[1093] The device receives the results broadcast from the server. The received results are stored in the device and displayed on the screen as needed. For example, the device may recommend temperature adjustments or provide information based on emotions.

[1094] Step 10:

[1095] The user sees the results displayed on their device and can adjust their behavior based on the results, for example, changing their work environment or adjusting irrigation systems in agriculture depending on their emotional state.

[1096] Example 2

[1097] 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."

[1098] Conventional AI systems have struggled to efficiently collect, preprocess, and analyze environmental and user emotional data, and provide rapid feedback. Ensuring the quality and consistency of data collected from individual devices in distributed systems also poses challenges. In particular, there is a need for systems to analyze diverse data in real time and provide useful feedback to users based on that data.

[1099] 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.

[1100] In this invention, the server includes: means for multiple terminals to collect environmental data and user emotional data; means for performing preprocessing, including normalization and noise removal, on the environmental data and emotional data collected by the terminals; means for the central server to receive the environmental data and emotional data transmitted from the terminals; means for the central server to aggregate the received environmental data and emotional data and trigger AI processing when a certain amount of data is received; means for executing AI processing and broadcasting the results to the terminals; and means for the terminals to receive and display the broadcasted results. This enables a series of processes of efficient data collection, preprocessing, analysis, and feedback in a distributed AI system.

[1101] A "terminal" is a device that collects environmental data and user emotion data, and transmits the data to a central server after preprocessing.

[1102] "Environmental data" is a collection of information that describes physical environmental conditions, such as temperature, humidity, and soil moisture.

[1103] "User emotion data" is a collection of information that indicates the user's emotional state, analyzed from facial expressions, tone of voice, and the like.

[1104] "Preprocessing" refers to data shaping operations such as normalization and noise removal that are performed on collected data.

[1105] The "central server" is a computer system that receives data sent from the terminals, aggregates it, performs AI processing, and broadcasts the results to the terminals.

[1106] "Aggregation" is the operation of combining data collected from multiple terminals into a single data set.

[1107] "AI processing" is the process of analyzing data using machine learning algorithms to make predictions and modeling.

[1108] "Broadcast" is an operation in which the central server transmits the processing results to all terminals simultaneously.

[1109] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[1110] System Configuration

[1111] Hardware and Software

[1112] The device includes a temperature sensor, humidity sensor, facial recognition camera, and microphone, and these devices collect environmental data and user emotional data in real time. Specifically, it uses DHT22 as a temperature sensor, OpenCV for facial recognition, and TensorFlow for voice recognition. These devices are connected to a single-board computer such as a Raspberry Pi.

[1113] The central server is a high-performance computer that aggregates the received data and uses machine learning frameworks such as PyTorch and Scikit-learn in Python to perform AI processing.

[1114] Program processing

[1115] The device collects environmental and emotional data and preprocesses it. Preprocessing includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. This process is performed using data processing libraries such as NumPy and Pandas.

[1116] The terminal sends the preprocessed data to the central server via an HTTP POST request, using JSON format.

[1117] The central server temporarily stores the received data in memory or a database (e.g., MySQL). When a certain amount of data is received, aggregation processing is triggered and AI processing is performed. This AI processing includes analysis and prediction of environmental data and modeling of emotional data. Specific processing examples include calculating the average value of environmental data and predicting the user's mood using emotional data.

[1118] The server broadcasts the results of the AI ​​processing to the devices, which then receive the results and display them to the user via a web interface or mobile application.

[1119] Specific examples

[1120] Example 1: Agricultural sensors and sentiment analysis

[1121] Agricultural sensors (terminals) collect data on the temperature, humidity, and soil moisture of the farm, while also collecting emotional data from the farmer's (user's) facial expressions and voice. A central server receives this data and performs AI processing to predict the optimal growing conditions for crops. As a result, it provides recommendations for environmental conditions and the farmer's stress level. Farmers can then adjust watering and fertilizer application based on this information.

[1122] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[1123] Multiple sensors (terminals) placed in the smart city collect air quality data and use an emotion engine to analyze the emotional data of citizens (users). A central server receives this data and analyzes the air quality of each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[1124] Prompt Sentence Examples

[1125] Agricultural sensors and sentiment analysis

[1126] Design a system that integrates agricultural sensors and an emotion engine to collect temperature, humidity, soil moisture data and user emotion data, analyze it through an AI model, and broadcast the results. As a concrete example, demonstrate how to predict crop growth conditions and provide farmers' stress levels.

[1127] Smart city air quality monitoring and citizen sentiment analysis

[1128] Integrate an emotion engine into a smart city's air quality monitoring system to design a system that monitors and analyzes citizen emotion data and air quality data in real time. As a concrete example, demonstrate how to analyze local air quality and the overall emotion state of citizens and broadcast the results to citizens.

[1129] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1130] Step 1: Data collection

[1131] The device collects environmental data such as temperature, humidity, and soil moisture, as well as user emotional data (facial expressions and voice tone). Specifically, it uses temperature and humidity sensors, a facial recognition camera (using OpenCV), and a microphone for voice analysis (using TensorFlow).

[1132] Input: Temperature sensor, humidity sensor, facial recognition camera, voice analysis microphone

[1133] Output: Environmental data (temperature, humidity, soil moisture) and emotional data (facial expression analysis results, voice tone analysis results)

[1134] Step 2: Data Preprocessing

[1135] The device preprocesses the collected environmental and emotional data. This includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. For example, temperature data is normalized by dividing it by the average value, and facial expression data is converted to 1 for positive and 0 for negative.

[1136] Input: Collected environmental and emotional data

[1137] Output: Preprocessed environmental and emotional data

[1138] Step 3: Send data

[1139] The device sends the preprocessed data to the central server using an HTTP POST request, with the data structured in JSON format.

[1140] Input: Preprocessed environmental and emotion data

[1141] Output: JSON format data sent to the central server

[1142] Step 4: Receiving Data

[1143] The server receives the environmental data and emotion data sent from the device, and temporarily stores the received data in memory or a database (e.g., MySQL).

[1144] Input: Data sent from the terminal (JSON format)

[1145] Output: Data stored in memory or in a database

[1146] Step 5: Data Aggregation

[1147] When the server receives a certain number of data sets, it aggregates them. For example, it aggregates data sets from five devices into one set.

[1148] Input: Received data from multiple devices

[1149] Output: Aggregated dataset

[1150] Step 6: AI processing

[1151] The server uses the aggregated data to perform AI processing, including data analysis, prediction, and modeling. Specifically, it calculates the average value of environmental data and predicts the user's mood using emotional data. This processing is performed using PyTorch and Scikit-learn.

[1152] Input: Aggregated dataset (environmental and emotional data)

[1153] Output: Analysis results by AI processing

[1154] Step 7: Broadcasting the results

[1155] The server simultaneously sends the results of the AI ​​processing to each device in JSON format, which each device can receive and display to the user.

[1156] Input: Analysis results by AI processing

[1157] Output: Analysis results broadcast to the device

[1158] Step 8: Data verification

[1159] The user checks the results received by the device, which are displayed on the device's display or in a mobile application, and adjusts their actions based on the information.

[1160] Input: Analysis results displayed on the terminal

[1161] Output: User behavior adjustment

[1162] Through the above steps, the present invention achieves efficient data collection, pre-processing, analysis, and feedback, enabling advanced analysis and judgment.

[1163] (Application example 2)

[1164] 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."

[1165] Conventional customer experience optimization systems for brick-and-mortar stores were limited to collecting environmental data and had difficulty utilizing user emotional data. As a result, they were unable to respond to real-time changes in customer emotions, resulting in limited improvements in customer satisfaction. In addition, there was a lack of a mechanism to efficiently aggregate collected environmental and emotional data and take appropriate action, making it difficult for staff to utilize the information in real time.

[1166] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for multiple terminals to collect environmental data and user emotion data; means for the terminals to preprocess the collected environmental data and emotion data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for the terminals to provide instructions for taking actions based on user operations. This makes it possible to utilize environmental data and user emotion data in real time and quickly provide specific actions to optimize the customer experience.

[1167] A "terminal" is a device that collects environmental data and user emotion data, and performs preprocessing and data transmission.

[1168] "Environmental data" refers to information about the physical environment, such as temperature and humidity.

[1169] "User emotional data" refers to information about the user's emotional state detected using facial expression analysis and voice tone analysis.

[1170] "Preprocessing" refers to performing processes such as normalization and noise removal on collected data.

[1171] The "central server" is a server that receives and aggregates data sent from terminals and then performs AI processing.

[1172] "AI processing" refers to the process of analyzing received data and making predictions and modeling.

[1173] "Broadcast" refers to sending AI-processed results to multiple devices simultaneously.

[1174] "Means for providing instructions for the terminal to take an action based on the user's operation" refers to a function in which the terminal indicates the action that the user should take based on the broadcasted results.

[1175] This invention is a system in which multiple devices collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the devices, thereby optimizing the customer experience in physical stores.

[1176] Overall system configuration

[1177] The system consists of the following components:

[1178] Device: Smart glasses or head-mounted display

[1179] Central Server

[1180] Emotion Engine

[1181] Network connection: Wi-Fi or LTE

[1182] Program processing flow

[1183] Hardware and Software

[1184] 1. Terminal

[1185] Devices used: smart glasses, head-mounted displays

[1186] Data collection: The device collects environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[1187] 2. Emotion Engine

[1188] Software: TensorFlow, Keras

[1189] Function: Analyzes facial expressions and voice tones to quantify the user's emotional state

[1190] 3. Central Server

[1191] Software used: Python, JavaScript, Database Management System

[1192] Functions: Data reception, preprocessing, aggregation, AI analysis, and broadcasting of results

[1193] Specific AI models: TensorFlow, Keras

[1194] Processing Details

[1195] 1. Data Collection

[1196] The device collects environmental and emotional data, such as temperature of 22 degrees, humidity of 45%, and customer emotions of 0.8 happiness and 0.2 stress.

[1197] 2. Data Preprocessing

[1198] The device normalizes and denoises the collected data and preprocesses it. For example, environmental data is normalized based on the average value, and emotion data is converted from binary to numerical data.

[1199] 3. Data Transmission

[1200] The pre-processed data is sent to a central server using an HTTP POST request.

[1201] 4. Data Reception and Aggregation

[1202] The central server receives the data and aggregates it over a certain number of devices, for example, combining data from five devices into one set.

[1203] 5. AI Processing

[1204] The aggregated data is then used by the AI ​​model to perform analysis, for example, calculating average values ​​for environmental data and analyzing the user's overall mood from emotional data.

[1205] 6. Broadcasting the Results

[1206] The results of the AI ​​processing are sent simultaneously from a central server to each device, which receives the results and displays them to the user.

[1207] Examples of concrete examples and prompts

[1208] Specific examples

[1209] After analyzing customer emotional data (happiness level 0.7, stress level 0.3) in a specific store area, the central server recommends deploying additional staff support in this area. When staff act on this instruction, the customer experience is improved.

[1210] Prompt Sentence Examples

[1211] Enter the following prompt into the generative AI model:

[1212] Based on the customer's facial expression data and in-store environmental data, recommend an action to optimize customer satisfaction. The specific customer's emotional state is as follows: Happiness level 0.5, Stress level 0.5. The environmental data is as follows: Temperature 22.0°C, Humidity 45%. Please specify the recommended action.

[1213] The above is an embodiment of the present invention, which makes it possible to optimize the customer experience in a physical store by utilizing environmental data and user emotion data.

[1214] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1215] Step 1:

[1216] Data collection

[1217] The device uses smart glasses or a head-mounted display to collect environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[1218] Input: Real-time environmental and emotional data

[1219] Output: Collected raw data (e.g., temperature 22.0°C, humidity 45%, happiness level 0.8, stress level 0.2)

[1220] Step 2:

[1221] Data Preprocessing

[1222] The environmental data and emotion data collected by the device are pre-processed by normalizing and removing noise.

[1223] Input: Raw data collected

[1224] Data processing: Normalization of environmental data by the average value, conversion of emotion data from binary to numerical data

[1225] Output: Preprocessed data (e.g., normalized temperature data, sentiment analysis results as numerical data)

[1226] Step 3:

[1227] Data transmission

[1228] The device sends the pre-processed data to the central server using an HTTP POST request.

[1229] Input: Preprocessed data

[1230] Output: JSON format data sent to the central server

[1231] Step 4:

[1232] Data reception and aggregation

[1233] A central server receives the data sent from the terminals and temporarily stores it in a database or memory.

[1234] Input: Data sent from the terminal

[1235] Data processing: preparing data for storage and aggregation in a database

[1236] Output: Saved dataset

[1237] Step 5:

[1238] Triggering AI processing

[1239] When the central server receives a certain amount of data, it triggers AI processing.

[1240] Input: Aggregated dataset

[1241] Output: AI processing start instruction

[1242] Step 6:

[1243] Data aggregation and analysis

[1244] The central server analyzes the aggregated data using AI models (TensorFlow, Keras) and predicts the user's overall mood based on environmental and emotional data.

[1245] Input: Aggregated preprocessed dataset

[1246] Data calculation: Data analysis and mood prediction using AI models

[1247] Output: Analysis results (e.g., recommended actions, overall mood)

[1248] Step 7:

[1249] Broadcasting the Results

[1250] The central server broadcasts the results of AI processing to all devices simultaneously.

[1251] Input: AI analysis results

[1252] Output: Broadcast results sent to the device

[1253] Step 8:

[1254] Displaying results and prompting

[1255] The terminal receives the broadcasted results and displays them to the staff, and also provides instructions for taking action based on the user's actions.

[1256] Input: Broadcast result from server

[1257] Output: Instructions and data displayed on the terminal (e.g., "Deploy additional staff to Area B")

[1258] Step 9:

[1259] User Behavior

[1260] The user takes actual actions based on instructions from the terminal, such as allocating additional staff or presenting discount offers.

[1261] Input: Instructions from the terminal

[1262] Output: Specific actions aimed at improving customer experience

[1263] 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.

[1264] 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.

[1265] 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.

[1266] [Fourth embodiment]

[1267] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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.

[1272] 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).

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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."

[1280] This invention is a system that enables efficient data processing and the utilization of AI by having multiple terminals collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the terminals.

[1281] Program Overview

[1282] This system assigns specific roles to both the terminal and the central server, and they work together. The following is a natural language explanation of the program processing of this system.

[1283] Device behavior

[1284] Data collection

[1285] The device collects environmental data at regular intervals, including temperature, humidity, soil quality, etc.

[1286] Data Preprocessing

[1287] The devices preprocess the collected raw data, specifically normalizing it and removing noise, so that the data can be sent to a central server in a unified format.

[1288] Data transmission

[1289] The preprocessed data is sent to a central server using an HTTP POST request, formatted as JSON and containing the device ID and the normalized data.

[1290] Server Operation

[1291] Data reception

[1292] The central server receives the data sent from the terminal and temporarily stores the received data on the server.

[1293] Data Aggregation

[1294] When a certain amount of data is collected, the server aggregates the data. For example, if data is collected from five devices, the server will combine the data into one set.

[1295] AI processing

[1296] Using the aggregated data, the central server runs AI models, which include analysis, prediction, model training, etc. The results of the AI ​​processing include, for example, recognition of averages and patterns in the environmental data.

[1297] Broadcasting the Results

[1298] The results of the AI ​​processing are sent simultaneously from the server to each device, which then receives the broadcasted results and displays them to the user.

[1299] User operations

[1300] Data confirmation

[1301] The user checks the results sent from the device, which include analysis of the environmental data collected by each device and recommended actions.

[1302] Specific examples

[1303] Example 1: Agricultural sensors

[1304] Multiple environmental sensors (terminals) are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture and send the data to a central server. The central server receives and aggregates this data and uses an AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize crops.

[1305] Example 2: Smart city air quality monitor

[1306] Multiple sensors (terminals) placed throughout the city collect air quality data and send it to a central server. The server analyzes the data and determines the air quality status of each area in real time. The results are broadcast, and citizens (users) can use this information to decide whether or not to go outside.

[1307] In this way, the present invention provides a system for efficient data collection, pre-processing, aggregation, AI processing, and feedback of results. By dividing each step, the system optimizes computing resources and improves overall performance.

[1308] The processing flow will be explained below.

[1309] Step 1:

[1310] The devices collect environmental data. This is done periodically, and each device uses its own sensors to acquire data such as temperature, humidity, and soil moisture. For example, the temperature sensor measures the air temperature and stores the acquired data in memory.

[1311] Step 2:

[1312] The data collected by the device is preprocessed. Preprocessing includes normalizing the raw data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value.

[1313] Step 3:

[1314] The device sends the preprocessed data to the central server using an HTTP POST request, which includes the device ID and the normalized data. For example, the normalized data is sent to the server in JSON format.

[1315] Step 4:

[1316] The server receives the data sent from the terminal. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to store the data.

[1317] Step 5:

[1318] When the server receives a certain number of data, it aggregates the data. For example, if data is sent from five devices, the perform_central_processing() function is called and the data is aggregated into one set.

[1319] Step 6:

[1320] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it concatenates the incoming data and calculates the average value of that data.

[1321] Step 7:

[1322] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device simultaneously. At this time, the results are sent in a format that each device can understand.

[1323] Step 8:

[1324] The terminal receives the results broadcast from the server, and displays the results or stores them in a database or memory as needed. For example, the results are displayed on the terminal display.

[1325] Step 9:

[1326] The user can view the results displayed on the device. For example, farmers can use the data from the sensors to adjust their farming operations. The user can then adjust the irrigation system or perform other agricultural activities based on the results displayed.

[1327] Example 1

[1328] 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."

[1329] Conventional data collection systems have problems with the inefficient execution of processes from environmental data collection to analysis and feedback of results, leading to the inability to optimize computing resources. Another issue is that individually collected data is not preprocessed according to uniform standards, making accurate analysis difficult. Furthermore, they are unable to perform real-time analysis of collected data and provide rapid decision support based on that analysis.

[1330] 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.

[1331] In this invention, the server includes: means for multiple terminals to collect environmental data; means for the terminals to preprocess the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive the data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing using a generative AI model; means for the terminals to broadcast the results of the AI ​​processing; and means for the terminals to receive and display the broadcasted results. This allows the entire process from data collection to analysis and result feedback to be executed efficiently, optimizing computing resources and providing analysis results in real time.

[1332] "Terminal" refers to the electronic device that collects environmental data, pre-processes it, and transmits the data to a central server.

[1333] "Environmental Data" refers to information related to the natural environment, such as temperature, humidity, soil quality, etc.

[1334] "Preprocessing" refers to the process of removing noise, normalizing, and otherwise processing collected raw data.

[1335] "Central server" refers to a system with central computing resources that performs a series of functions, including receiving data sent from devices, aggregating it, and processing it using AI models.

[1336] "Receiving" refers to the process by which the central server receives data sent from the terminal.

[1337] "Aggregation" refers to the process of combining multiple pieces of received data into a single data set.

[1338] A "generative AI model" refers to a model that uses pre-trained artificial intelligence algorithms to analyze data and make predictions.

[1339] "Broadcast" refers to the process in which a central server simultaneously transmits the results of AI processing to multiple devices.

[1340] "HTTP POST request" refers to a web communication protocol that allows a device to send pre-processed data to a central server.

[1341] This invention is a system that enables efficient data processing and the utilization of generative AI models by having multiple devices collect environmental data, preprocessing the data, and sending it to a central server, which then aggregates and analyzes the received data and broadcasts the results to the devices.

[1342] Device behavior

[1343] The device uses sensors to collect environmental data. These sensors acquire data such as temperature, humidity, and soil quality at regular intervals. The collected raw data is preprocessed using Python's NumPy library. Specifically, the data is normalized and noise is removed to generate unified format data. After preprocessing is complete, the data is sent to the central server via an HTTP POST request using Python's requests library. This process allows the device to efficiently and accurately provide environmental data to the central server.

[1344] Server Operation

[1345] The central server receives data sent from devices using the Flask web framework. The received data is saved and temporarily stored in a MySQL database. Once a certain amount of data has been collected, the server performs an aggregation process using the Pandas library. This aggregation process combines data from multiple devices into a single dataset. The combined dataset is then analyzed and predicted using a generative AI model using libraries such as TensorFlow and PyTorch. This AI processing enables statistical information and pattern recognition of environmental data. Finally, the results of the AI ​​processing are broadcast simultaneously to each device using the WebSocket library.

[1346] User operations

[1347] The user can view the results broadcast from the devices. These results include analysis results of the environmental data collected by each device and recommended actions. The user can view the details of the data through the device interface, for example, by operating a GUI using the Tkinter library.

[1348] Specific examples

[1349] Example 1: Agricultural sensors

[1350] Multiple agricultural environmental sensors are installed on farms. These sensors periodically measure temperature, humidity, and soil moisture, and transmit the data to a central server after preprocessing. The central server aggregates this data and uses a generative AI model to predict optimal growing conditions for crops. The results are sent to each sensor, and farmers (users) use this information to water and fertilize their crops.

[1351] Example 2: Smart city air quality monitor

[1352] Multiple air quality sensors located throughout the city collect air quality data, which is then preprocessed and sent to a central server. The server aggregates the data and uses a generative AI model to analyze local air quality. The results are broadcast to citizens in real time, providing reference information for deciding whether or not to go outside.

[1353] Prompt Sentence Examples

[1354] An example prompt to input to a generative AI model might be, "Please tell me how to optimize temperature and humidity on a farm."

[1355] Thus, the present invention provides a system for efficient data collection, preprocessing, aggregation, AI processing using generative AI models, and feedback of the results. By dividing each step, computing resources can be optimized and overall performance can be improved.

[1356] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1357] Step 1:

[1358] The terminal collects environmental data. The input is raw data obtained from sensors such as temperature, humidity, and soil quality. The output is this raw data. Specifically, the temperature sensor measures the temperature, the humidity sensor measures the humidity, and the soil humidity sensor measures the moisture content of the soil.

[1359] Step 2:

[1360] The terminal preprocesses the raw data collected. The input is the raw data obtained in step 1. The output is the preprocessed data that has been denoised and normalised. Specifically, the terminal normalises the data using Python's NumPy library and uses filtering techniques to remove noise from the measurement data.

[1361] Step 3:

[1362] The terminal sends the preprocessed data to the central server. The input is the preprocessed data obtained in step 2. The output is the data sent to the central server via an HTTP POST request. Specifically, the terminal uses the Python requests library to convert the data into JSON format and send it to the central server via a POST request.

[1363] Step 4:

[1364] The server receives data sent from the device. The input is preprocessed data sent as an HTTP POST request. The output is the received data stored in a database. Specifically, the server uses the Flask web framework to receive the POST request and store the data in a MySQL database.

[1365] Step 5:

[1366] The server aggregates the data it receives. The input is data from multiple devices in a database. The output is an aggregated dataset. Specifically, the server uses the Pandas library to retrieve data from the database and organize it into a data frame. This data frame combines the data from multiple devices into a single dataset.

[1367] Step 6:

[1368] The server uses the aggregated data to perform AI processing using a generative AI model. The input is the aggregated data obtained in step 5. The output is analysis results and prediction results. Specifically, the server uses libraries such as TensorFlow and PyTorch to execute a pre-trained generative AI model to analyze and predict data.

[1369] Step 7:

[1370] The server broadcasts the results of the AI ​​processing to each device. The input is the AI ​​processing result obtained in step 6. The output is the broadcasted AI processing result. Specifically, the server uses the WebSocket library to simultaneously send the results of the AI ​​processing to each device.

[1371] Step 8:

[1372] The user checks the results sent from the device. The input is the broadcasted AI processing results. The output is the analysis results and recommended actions checked by the user. Specifically, the device uses a GUI library such as Tkinter to display the results to the user. The user decides on the appropriate action based on this information.

[1373] (Application example 1)

[1374] 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."

[1375] Logistics centers require optimal inventory management and efficient replenishment, but current systems make it difficult to collect and analyze data in real time, and the time it takes to consolidate and analyze data leads to problems such as stockouts and excess inventory.In addition, data collected by individual devices cannot be managed and analyzed in a unified manner, making it difficult to improve overall efficiency.

[1376] 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.

[1377] In this invention, the server includes: means for multiple terminals to collect environmental data; means for preprocessing the collected data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for analyzing inventory data collected from multiple terminals in the logistics center and predicting optimal inventory allocation and replenishment timing. This enables real-time inventory management in the logistics center, preventing stockouts and excess inventory and improving overall efficiency.

[1378] A "terminal" is a device consisting of multiple environmental sensing devices and mobile devices for collecting and preprocessing environmental data.

[1379] "Environmental data" refers to various data that indicate the environmental conditions within the logistics center, such as temperature, humidity, weight, and air quality.

[1380] "Preprocessing" is the process of converting collected raw data using techniques such as noise removal and normalization to unify the data format.

[1381] The "central server" is a computer system that receives environmental data sent from multiple devices and aggregates and analyzes it.

[1382] "Aggregation" is the process of collecting and integrating data received from multiple devices into a single set.

[1383] "AI processing" is the process of running machine learning models and other AI models on aggregated data to perform analysis and make predictions.

[1384] "Broadcast" refers to the simultaneous transmission of the results of AI processing performed on a central server to multiple devices via a network.

[1385] "Inventory data" refers to data that indicates the inventory status of products managed within a logistics center, and includes attributes such as weight and quantity.

[1386] "Optimal placement" is a method for efficiently managing the placement of inventory items, with the aim of making effective use of space and improving work efficiency.

[1387] "Replenishment timing" is an indicator that indicates the optimal timing for appropriate replenishment before inventory runs out.

[1388] This invention is a system aimed at improving the efficiency of inventory management in logistics centers. The system includes multiple terminals, a central server, and analytical processing using an AI model. It also predicts optimal inventory placement and replenishment timing by coordinating real-time data collection, preprocessing, aggregation, analysis, and broadcasting.

[1389] The terminal collects inventory data using multiple environmental sensors in the distribution center. These environmental sensors periodically measure temperature, humidity, shelf weight (inventory status), etc. The measured data is preprocessed by the terminal to remove noise and normalize the data. The preprocessed data is sent to the central server in JSON format using an HTTP POST request.

[1390] The central server receives and temporarily stores data sent from the terminals. Next, once a certain amount of data has been collected, the server aggregates the data. The aggregated data is input into an AI model for analysis and prediction processing. The AI ​​model uses deep learning models and machine learning algorithms using Python. The analysis results include, for example, recommendations for optimal inventory placement and replenishment timing.

[1391] The results are broadcast from a central server to each terminal, which receives the results and displays them to the staff through a user interface, allowing staff to efficiently manage and replenish inventory based on real-time data.

[1392] As a concrete example, consider using this system in a distribution center. Smartphones are used within the center to collect temperature, humidity, and weight data from sensor devices on each product shelf. The collected data is preprocessed on the smartphone and sent to a central server. The central server analyzes the data and displays specific instructions on each device, such as "Product A is running low on stock, so it needs to be replenished immediately" or "Product B still has plenty of stock, so there is no need to replenish it."

[1393] The following sentences are used as examples of prompt sentences to input into the generative AI model:

[1394] "Please generate an AI model to predict the optimal replenishment timing using the current inventory status at the logistics center and the temperature and humidity data for each product as input data."

[1395] In this way, a system is realized that can streamline inventory management within the logistics center and prevent stockouts and excess inventory.

[1396] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1397] Step 1:

[1398] The device collects environmental data.

[1399] (Specific actions)

[1400] Environmental sensors connected to the devices periodically measure temperature, humidity, shelf weight, etc. The collected data is stored in the memory of each device.

[1401] (input)

[1402] Raw environmental data obtained from environmental sensors.

[1403] (output)

[1404] Raw environmental data stored on the device.

[1405] Step 2:

[1406] Preprocess the data collected by the device.

[1407] (Specific actions)

[1408] The device performs noise reduction and data normalization on the collected data, for example, detecting and removing outliers and converting the data into a unified format.

[1409] (input)

[1410] Raw environmental data.

[1411] (output)

[1412] Preprocessed and normalized data.

[1413] Step 3:

[1414] The pre-processed data is sent to a central server.

[1415] (Specific actions)

[1416] The device converts the preprocessed data into JSON format and sends it to the central server using an HTTP POST request.

[1417] (input)

[1418] Preprocessed normalized data.

[1419] (output)

[1420] Data requests sent to a central server.

[1421] Step 4:

[1422] A central server receives data from the terminals.

[1423] (Specific actions)

[1424] The server extracts data from the received HTTP POST request and stores it temporarily in a database.

[1425] (input)

[1426] The data request sent.

[1427] (output)

[1428] Raw data stored on the server.

[1429] Step 5:

[1430] A central server aggregates the received data.

[1431] (Specific actions)

[1432] When the server receives a certain amount of data, it aggregates the data, calculates averages and totals, and compiles them into a unified data set.

[1433] (input)

[1434] Raw data stored on the server.

[1435] (output)

[1436] Aggregated datasets.

[1437] Step 6:

[1438] A central server analyzes the data using an AI model.

[1439] (Specific actions)

[1440] The collected data is input into an AI model to predict optimal inventory placement and replenishment timing. The prediction results are stored on the server.

[1441] (input)

[1442] Aggregated datasets.

[1443] (output)

[1444] Analysis results (optimal inventory placement and replenishment timing).

[1445] Step 7:

[1446] The results of AI processing are broadcast to the device.

[1447] (Specific actions)

[1448] The server converts the analysis results into JSON format and sends them to all connected devices simultaneously.

[1449] (input)

[1450] Analysis results.

[1451] (output)

[1452] Data broadcast to the device.

[1453] Step 8:

[1454] The terminal receives and displays the results.

[1455] (Specific actions)

[1456] The terminal analyzes the received data and displays it to the person in charge through the user interface. The analyzed data is displayed in an appropriate format, and the user can refer to it to manage inventory.

[1457] (input)

[1458] Broadcast data.

[1459] (output)

[1460] Analysis results displayed on the device.

[1461] 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.

[1462] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[1463] Program Overview

[1464] This system operates efficiently and flexibly through the cooperation of the terminals, the central server, and the emotion engine. The following is a natural language explanation of the program processing of this system.

[1465] Device behavior

[1466] Data collection

[1467] The device collects environmental data (e.g., temperature, humidity, soil moisture) and user emotion data (e.g., facial expression analysis, voice tone analysis). The emotion engine analyzes the user's emotion from facial expression and voice data and uses the results.

[1468] Data Preprocessing

[1469] The device preprocesses the collected environmental and emotional data. The environmental data is normalized and denoised, and the emotional data is preprocessed in the same way. For example, if the environmental data is [20.1, 21.5, 19.8, 22.3, 20.9], the data is normalized by dividing it by the average value. The emotional data is also converted from binary to numeric data.

[1470] Data transmission

[1471] The preprocessed data is sent to a central server using an HTTP POST request. The data includes the device ID, environmental data, and emotion data. For example, the normalized data is sent to the server in JSON format.

[1472] Server Operation

[1473] Data reception

[1474] The server receives the environmental data and emotion data sent from the device, and the received data is temporarily stored in the server's memory or database.

[1475] Data Aggregation

[1476] When the server receives more than a certain number of data, it aggregates the data. For example, if data is sent from five devices, it aggregates each data into one set.

[1477] AI processing

[1478] Using the aggregated data, the server performs AI processing of both environmental and emotional data. AI processing includes data analysis, prediction, modeling, etc. For example, it calculates the average value of environmental data and analyzes the user's overall mood from emotional data.

[1479] Broadcasting the Results

[1480] The results of the AI ​​processing are sent from the server to each device simultaneously. For example, the broadcast_results() function is called and the results are sent to each device in a format that each device can understand.

[1481] User operations

[1482] Data confirmation

[1483] The user then checks the results sent from the device, which include feedback based on the analysis of the environmental data and emotional data, and can use this information to adjust their behavior.

[1484] Specific examples

[1485] Example 1: Agricultural sensors and sentiment analysis

[1486] Multiple sensors (terminals) installed on farms collect data on temperature, humidity, and soil moisture, while also collecting emotional data from the farmer (user)'s facial expressions and voice. A central server receives this data and performs AI processing to predict optimal growing conditions for crops. As a result, the farmer's stress level is provided along with recommended environmental conditions. Farmers can then adjust watering and fertilizer application based on this information.

[1487] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[1488] Multiple sensors (terminals) placed throughout the city collect air quality data, and an emotion engine collects emotion data from citizens (users). A central server receives this data and analyzes the air quality in each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[1489] In this way, the present invention provides a distributed AI system that combines an emotion engine and realizes efficient data collection, preprocessing, aggregation, AI processing, and feedback of results, enabling advanced analysis and judgment using environmental data and user emotion data.

[1490] The processing flow will be explained below.

[1491] Step 1:

[1492] The device collects environmental data and user emotional data. Environmental data is acquired using sensors, and emotional data is analyzed using an emotion engine based on facial expressions and voice. For example, a temperature sensor acquires the temperature, and a microphone and camera capture the user's voice and facial expressions.

[1493] Step 2:

[1494] Preprocessing the environmental data collected by the device. Preprocessing includes normalizing the data and removing noise. For example, if the acquired temperature data is [20.1, 21.5, 19.8, 22.3, 20.9], calculate the average value and then normalize each data point by dividing it by the average value.

[1495] Step 3:

[1496] The device preprocesses the emotion data. The emotion engine converts the binary data into numerical data. For example, it extracts a happiness score from the user's facial expression and stores it in numerical format.

[1497] Step 4:

[1498] The device sends the preprocessed environmental data and emotion data to the central server. The data is sent in JSON format using an HTTP POST request, which includes the device ID, the preprocessed environmental data, and the emotion data.

[1499] Step 5:

[1500] The server receives the environmental data and emotion data sent from the device. The received data is temporarily stored in the server's memory or database. For example, the receive_data() function is called to save the data.

[1501] Step 6:

[1502] When the server receives a certain amount of data, it aggregates the environmental data and emotional data. For example, if data is collected from five devices, the server will combine the data into one set.

[1503] Step 7:

[1504] The server processes the aggregated data using AI, which includes data analysis, prediction, model learning, etc. For example, it can concatenate the incoming data, calculate the average value of environmental data, and analyze the user's overall mood using emotional data.

[1505] Step 8:

[1506] The server broadcasts the results of the AI ​​processing to each device. For example, the broadcast_results() function is called, and the results are sent to each device. The results include the analysis results of the environmental data and the user's emotional state.

[1507] Step 9:

[1508] The device receives the results broadcast from the server. The received results are stored in the device and displayed on the screen as needed. For example, the device may recommend temperature adjustments or provide information based on emotions.

[1509] Step 10:

[1510] The user sees the results displayed on their device and can adjust their behavior based on the results, for example, changing their work environment or adjusting irrigation systems in agriculture depending on their emotional state.

[1511] Example 2

[1512] 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."

[1513] Conventional AI systems have struggled to efficiently collect, preprocess, and analyze environmental and user emotional data, and provide rapid feedback. Ensuring the quality and consistency of data collected from individual devices in distributed systems also poses challenges. In particular, there is a need for systems to analyze diverse data in real time and provide useful feedback to users based on that data.

[1514] 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.

[1515] In this invention, the server includes: means for multiple terminals to collect environmental data and user emotional data; means for performing preprocessing, including normalization and noise removal, on the environmental data and emotional data collected by the terminals; means for the central server to receive the environmental data and emotional data transmitted from the terminals; means for the central server to aggregate the received environmental data and emotional data and trigger AI processing when a certain amount of data is received; means for executing AI processing and broadcasting the results to the terminals; and means for the terminals to receive and display the broadcasted results. This enables a series of processes of efficient data collection, preprocessing, analysis, and feedback in a distributed AI system.

[1516] A "terminal" is a device that collects environmental data and user emotion data, and transmits the data to a central server after preprocessing.

[1517] "Environmental data" is a collection of information that describes physical environmental conditions, such as temperature, humidity, and soil moisture.

[1518] "User emotion data" is a collection of information that indicates the user's emotional state, analyzed from facial expressions, tone of voice, and the like.

[1519] "Preprocessing" refers to data shaping operations such as normalization and noise removal that are performed on collected data.

[1520] The "central server" is a computer system that receives data sent from the terminals, aggregates it, performs AI processing, and broadcasts the results to the terminals.

[1521] "Aggregation" is the operation of combining data collected from multiple terminals into a single data set.

[1522] "AI processing" is the process of analyzing data using machine learning algorithms to make predictions and modeling.

[1523] "Broadcast" is an operation in which the central server transmits the processing results to all terminals simultaneously.

[1524] This invention is a distributed AI system that combines an emotion engine, in which multiple terminals collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the terminals, thereby achieving efficient data processing and utilization of AI.

[1525] System Configuration

[1526] Hardware and Software

[1527] The device includes a temperature sensor, humidity sensor, facial recognition camera, and microphone, and these devices collect environmental data and user emotional data in real time. Specifically, it uses DHT22 as a temperature sensor, OpenCV for facial recognition, and TensorFlow for voice recognition. These devices are connected to a single-board computer such as a Raspberry Pi.

[1528] The central server is a high-performance computer that aggregates the received data and uses machine learning frameworks such as PyTorch and Scikit-learn in Python to perform AI processing.

[1529] Program processing

[1530] The device collects environmental and emotional data and preprocesses it. Preprocessing includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. This process is performed using data processing libraries such as NumPy and Pandas.

[1531] The terminal sends the preprocessed data to the central server via an HTTP POST request, using JSON format.

[1532] The central server temporarily stores the received data in memory or a database (e.g., MySQL). When a certain amount of data is received, aggregation processing is triggered and AI processing is performed. This AI processing includes analysis and prediction of environmental data and modeling of emotional data. Specific processing examples include calculating the average value of environmental data and predicting the user's mood using emotional data.

[1533] The server broadcasts the results of the AI ​​processing to the devices, which then receive the results and display them to the user via a web interface or mobile application.

[1534] Specific examples

[1535] Example 1: Agricultural sensors and sentiment analysis

[1536] Agricultural sensors (terminals) collect data on the temperature, humidity, and soil moisture of the farm, while also collecting emotional data from the farmer's (user's) facial expressions and voice. A central server receives this data and performs AI processing to predict the optimal growing conditions for crops. As a result, it provides recommendations for environmental conditions and the farmer's stress level. Farmers can then adjust watering and fertilizer application based on this information.

[1537] Example 2: Smart city air quality monitoring and citizen sentiment analysis

[1538] Multiple sensors (terminals) placed in the smart city collect air quality data and use an emotion engine to analyze the emotional data of citizens (users). A central server receives this data and analyzes the air quality of each area and the overall emotional state of citizens in real time. The results are broadcast, and citizens use this information to decide whether to go outside and what measures to take.

[1539] Prompt Sentence Examples

[1540] Agricultural sensors and sentiment analysis

[1541] Design a system that integrates agricultural sensors and an emotion engine to collect temperature, humidity, soil moisture data and user emotion data, analyze it through an AI model, and broadcast the results. As a concrete example, demonstrate how to predict crop growth conditions and provide farmers' stress levels.

[1542] Smart city air quality monitoring and citizen sentiment analysis

[1543] Integrate an emotion engine into a smart city's air quality monitoring system to design a system that monitors and analyzes citizen emotion data and air quality data in real time. As a concrete example, demonstrate how to analyze local air quality and the overall emotion state of citizens and broadcast the results to citizens.

[1544] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1545] Step 1: Data collection

[1546] The device collects environmental data such as temperature, humidity, and soil moisture, as well as user emotional data (facial expressions and voice tone). Specifically, it uses temperature and humidity sensors, a facial recognition camera (using OpenCV), and a microphone for voice analysis (using TensorFlow).

[1547] Input: Temperature sensor, humidity sensor, facial recognition camera, voice analysis microphone

[1548] Output: Environmental data (temperature, humidity, soil moisture) and emotional data (facial expression analysis results, voice tone analysis results)

[1549] Step 2: Data Preprocessing

[1550] The device preprocesses the collected environmental and emotional data. This includes normalizing and denoising the environmental data, and converting the emotional data from binary to numerical format. For example, temperature data is normalized by dividing it by the average value, and facial expression data is converted to 1 for positive and 0 for negative.

[1551] Input: Collected environmental and emotional data

[1552] Output: Preprocessed environmental and emotional data

[1553] Step 3: Send data

[1554] The device sends the preprocessed data to the central server using an HTTP POST request, with the data structured in JSON format.

[1555] Input: Preprocessed environmental and emotion data

[1556] Output: JSON format data sent to the central server

[1557] Step 4: Receiving Data

[1558] The server receives the environmental data and emotion data sent from the device, and temporarily stores the received data in memory or a database (e.g., MySQL).

[1559] Input: Data sent from the terminal (JSON format)

[1560] Output: Data stored in memory or in a database

[1561] Step 5: Data Aggregation

[1562] When the server receives a certain number of data sets, it aggregates them. For example, it aggregates data sets from five devices into one set.

[1563] Input: Received data from multiple devices

[1564] Output: Aggregated dataset

[1565] Step 6: AI processing

[1566] The server uses the aggregated data to perform AI processing, including data analysis, prediction, and modeling. Specifically, it calculates the average value of environmental data and predicts the user's mood using emotional data. This processing is performed using PyTorch and Scikit-learn.

[1567] Input: Aggregated dataset (environmental and emotional data)

[1568] Output: Analysis results by AI processing

[1569] Step 7: Broadcasting the results

[1570] The server simultaneously sends the results of the AI ​​processing to each device in JSON format, which each device can receive and display to the user.

[1571] Input: Analysis results by AI processing

[1572] Output: Analysis results broadcast to the device

[1573] Step 8: Data verification

[1574] The user checks the results received by the device, which are displayed on the device's display or in a mobile application, and adjusts their actions based on the information.

[1575] Input: Analysis results displayed on the terminal

[1576] Output: User behavior adjustment

[1577] Through the above steps, the present invention achieves efficient data collection, pre-processing, analysis, and feedback, enabling advanced analysis and judgment.

[1578] (Application example 2)

[1579] 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."

[1580] Conventional customer experience optimization systems for brick-and-mortar stores were limited to collecting environmental data and had difficulty utilizing user emotional data. As a result, they were unable to respond to real-time changes in customer emotions, resulting in limited improvements in customer satisfaction. In addition, there was a lack of a mechanism to efficiently aggregate collected environmental and emotional data and take appropriate action, making it difficult for staff to utilize the information in real time.

[1581] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for multiple terminals to collect environmental data and user emotion data; means for the terminals to preprocess the collected environmental data and emotion data; means for the central server to transmit the preprocessed data to a central server; means for the central server to receive data transmitted from the terminals; means for the central server to aggregate the received data and perform AI processing; means for broadcasting results of the AI ​​processing to the terminals; means for the terminals to receive and display the broadcast results; and means for the terminals to provide instructions for taking actions based on user operations. This makes it possible to utilize environmental data and user emotion data in real time and quickly provide specific actions to optimize the customer experience.

[1582] A "terminal" is a device that collects environmental data and user emotion data, and performs preprocessing and data transmission.

[1583] "Environmental data" refers to information about the physical environment, such as temperature and humidity.

[1584] "User emotional data" refers to information about the user's emotional state detected using facial expression analysis and voice tone analysis.

[1585] "Preprocessing" refers to performing processes such as normalization and noise removal on collected data.

[1586] The "central server" is a server that receives and aggregates data sent from terminals and then performs AI processing.

[1587] "AI processing" refers to the process of analyzing received data and making predictions and modeling.

[1588] "Broadcast" refers to sending AI-processed results to multiple devices simultaneously.

[1589] "Means for providing instructions for the terminal to take an action based on the user's operation" refers to a function in which the terminal indicates the action that the user should take based on the broadcasted results.

[1590] This invention is a system in which multiple devices collect environmental data and user emotion data, preprocess the data, and send it to a central server, which then performs AI processing and broadcasts the results to the devices, thereby optimizing the customer experience in physical stores.

[1591] Overall system configuration

[1592] The system consists of the following components:

[1593] Device: Smart glasses or head-mounted display

[1594] Central Server

[1595] Emotion Engine

[1596] Network connection: Wi-Fi or LTE

[1597] Program processing flow

[1598] Hardware and Software

[1599] 1. Terminal

[1600] Devices used: smart glasses, head-mounted displays

[1601] Data collection: The device collects environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[1602] 2. Emotion Engine

[1603] Software: TensorFlow, Keras

[1604] Function: Analyzes facial expressions and voice tones to quantify the user's emotional state

[1605] 3. Central Server

[1606] Software used: Python, JavaScript, Database Management System

[1607] Functions: Data reception, preprocessing, aggregation, AI analysis, and broadcasting of results

[1608] Specific AI models: TensorFlow, Keras

[1609] Processing Details

[1610] 1. Data Collection

[1611] The device collects environmental and emotional data, such as temperature of 22 degrees, humidity of 45%, and customer emotions of 0.8 happiness and 0.2 stress.

[1612] 2. Data Preprocessing

[1613] The device normalizes and denoises the collected data and preprocesses it. For example, environmental data is normalized based on the average value, and emotion data is converted from binary to numerical data.

[1614] 3. Data Transmission

[1615] The pre-processed data is sent to a central server using an HTTP POST request.

[1616] 4. Data Reception and Aggregation

[1617] The central server receives the data and aggregates it over a certain number of devices, for example, combining data from five devices into one set.

[1618] 5. AI Processing

[1619] The aggregated data is then used by the AI ​​model to perform analysis, for example, calculating average values ​​for environmental data and analyzing the user's overall mood from emotional data.

[1620] 6. Broadcasting the Results

[1621] The results of the AI ​​processing are sent simultaneously from a central server to each device, which receives the results and displays them to the user.

[1622] Examples of concrete examples and prompts

[1623] Specific examples

[1624] After analyzing customer emotional data (happiness level 0.7, stress level 0.3) in a specific store area, the central server recommends deploying additional staff support in this area. When staff act on this instruction, the customer experience is improved.

[1625] Prompt Sentence Examples

[1626] Enter the following prompt into the generative AI model:

[1627] Based on the customer's facial expression data and in-store environmental data, recommend an action to optimize customer satisfaction. The specific customer's emotional state is as follows: Happiness level 0.5, Stress level 0.5. The environmental data is as follows: Temperature 22.0°C, Humidity 45%. Please specify the recommended action.

[1628] The above is an embodiment of the present invention, which makes it possible to optimize the customer experience in a physical store by utilizing environmental data and user emotion data.

[1629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1630] Step 1:

[1631] Data collection

[1632] The device uses smart glasses or a head-mounted display to collect environmental data (temperature, humidity) and user emotional data (facial expression analysis, voice tone analysis) in real time.

[1633] Input: Real-time environmental and emotional data

[1634] Output: Collected raw data (e.g., temperature 22.0°C, humidity 45%, happiness level 0.8, stress level 0.2)

[1635] Step 2:

[1636] Data Preprocessing

[1637] The environmental data and emotion data collected by the device are pre-processed by normalizing and removing noise.

[1638] Input: Raw data collected

[1639] Data processing: Normalization of environmental data by the average value, conversion of emotion data from binary to numerical data

[1640] Output: Preprocessed data (e.g., normalized temperature data, sentiment analysis results as numerical data)

[1641] Step 3:

[1642] Data transmission

[1643] The device sends the pre-processed data to the central server using an HTTP POST request.

[1644] Input: Preprocessed data

[1645] Output: JSON format data sent to the central server

[1646] Step 4:

[1647] Data reception and aggregation

[1648] A central server receives the data sent from the terminals and temporarily stores it in a database or memory.

[1649] Input: Data sent from the terminal

[1650] Data processing: preparing data for storage and aggregation in a database

[1651] Output: Saved dataset

[1652] Step 5:

[1653] Triggering AI processing

[1654] When the central server receives a certain amount of data, it triggers AI processing.

[1655] Input: Aggregated dataset

[1656] Output: AI processing start instruction

[1657] Step 6:

[1658] Data aggregation and analysis

[1659] The central server analyzes the aggregated data using AI models (TensorFlow, Keras) and predicts the user's overall mood based on environmental and emotional data.

[1660] Input: Aggregated preprocessed dataset

[1661] Data calculation: Data analysis and mood prediction using AI models

[1662] Output: Analysis results (e.g., recommended actions, overall mood)

[1663] Step 7:

[1664] Broadcasting the Results

[1665] The central server broadcasts the results of AI processing to all devices simultaneously.

[1666] Input: AI analysis results

[1667] Output: Broadcast results sent to the device

[1668] Step 8:

[1669] Displaying results and prompting

[1670] The terminal receives the broadcasted results and displays them to the staff, and also provides instructions for taking action based on the user's actions.

[1671] Input: Broadcast result from server

[1672] Output: Instructions and data displayed on the terminal (e.g., "Deploy additional staff to Area B")

[1673] Step 9:

[1674] User Behavior

[1675] The user takes actual actions based on instructions from the terminal, such as allocating additional staff or presenting discount offers.

[1676] Input: Instructions from the terminal

[1677] Output: Specific actions aimed at improving customer experience

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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).

[1685] 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.

[1686] 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."

[1687] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1688] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1689] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1690] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1691] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1692] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1693] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1694] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1695] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1696] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1697] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1698] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1699] The following is further disclosed regarding the above embodiment.

[1700] (Claim 1)

[1701] a means for collecting environmental data by a plurality of terminals;

[1702] means for preprocessing data collected by the terminal;

[1703] means for transmitting the pre-processed data to a central server;

[1704] a means for the central server to receive data transmitted from the terminal;

[1705] A central server aggregates the received data and performs AI processing;

[1706] A means for broadcasting the results of AI processing to the terminal;

[1707] The system includes a terminal that receives and displays the broadcasted results.

[1708] (Claim 2)

[1709] 10. The system of claim 1, further comprising means for triggering AI processing when the central server receives a certain number of pieces of data or more.

[1710] (Claim 3)

[1711] 10. The system of claim 1, further comprising means for the terminal to transmit the preprocessed data to the central server using an HTTP POST request.

[1712] "Example 1"

[1713] (Claim 1)

[1714] a means for collecting environmental data by a plurality of terminals;

[1715] means for preprocessing data collected by the terminal;

[1716] means for transmitting the pre-processed data to a central server;

[1717] a means for the central server to receive data transmitted from the terminal;

[1718] a central server aggregating the received data and performing AI processing using the generative AI model;

[1719] A means for broadcasting the results of AI processing to the terminal;

[1720] The system includes a terminal that receives and displays the broadcasted results.

[1721] (Claim 2)

[1722] 10. The system of claim 1, further comprising means for triggering AI processing when the central server receives a certain number of pieces of data or more.

[1723] (Claim 3)

[1724] 10. The system of claim 1, further comprising means for the terminal to transmit the preprocessed data to the central server using an HTTP POST request.

[1725] "Application Example 1"

[1726] (Claim 1)

[1727] a means for collecting environmental data by a plurality of terminals;

[1728] means for preprocessing data collected by the terminal;

[1729] means for transmitting the pre-processed data to a central server;

[1730] a means for the central server to receive data transmitted from the terminal;

[1731] A central server aggregates the received data and performs AI processing;

[1732] A means for broadcasting the results of AI processing to the terminal;

[1733] a means for the terminal to receive and display the broadcasted results;

[1734] A system that analyzes inventory data collected from multiple terminals within a logistics center and includes a means to predict optimal inventory placement and replenishment timing.

[1735] (Claim 2)

[1736] 10. The system of claim 1, further comprising means for triggering AI processing when the central server receives a certain number of pieces of data or more.

[1737] (Claim 3)

[1738] 10. The system of claim 1, further comprising means for the terminal to transmit the preprocessed data to the central server using an HTTP POST request.

[1739] "Example 2: Combining Emotion Engines"

[1740] (Claim 1)

[1741] A means for collecting environmental data and user emotion data by a plurality of terminals;

[1742] A means for pre-processing the environmental data and emotion data collected by the device, including normalization and noise removal;

[1743] means for transmitting the pre-processed environmental data and emotion data to a central server;

[1744] A means for a central server to receive environmental data and emotion data transmitted from the terminal;

[1745] a central server for aggregating the received environmental data and emotion data and performing AI processing;

[1746] A means for broadcasting the results of AI processing to the terminal;

[1747] The system includes a terminal that receives and displays the broadcasted results.

[1748] (Claim 2)

[1749] 10. The system of claim 1, further comprising means for triggering AI processing when the central server receives a predetermined number of environmental data and emotion data.

[1750] (Claim 3)

[1751] 10. The system of claim 1, further comprising means for the terminal to transmit the preprocessed environmental data and emotion data to the central server using an HTTP POST request.

[1752] "Application example 2 when combining emotion engines"

[1753] (Claim 1)

[1754] A means for collecting environmental data and user emotion data by a plurality of terminals;

[1755] means for preprocessing the environmental data and emotion data collected by the terminal;

[1756] means for transmitting the pre-processed data to a central server;

[1757] a means for the central server to receive data transmitted from the terminal;

[1758] A central server aggregates the received data and performs AI processing;

[1759] A means for broadcasting the results of AI processing to the terminal;

[1760] a means for the terminal to receive and display the broadcasted results;

[1761] means for providing instructions for the terminal to take an action based on a user's operation;

[1762] A system including:

[1763] (Claim 2)

[1764] 10. The system of claim 1, further comprising means for triggering AI processing when the central server receives a certain number of pieces of data or more.

[1765] (Claim 3)

[1766] 10. The system of claim 1, further comprising means for the terminal to transmit the preprocessed data to the central server using an HTTP POST request. [Explanation of symbols]

[1767] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting environmental data by a plurality of terminals; means for preprocessing data collected by the terminal; means for transmitting the pre-processed data to a central server; a means for the central server to receive data transmitted from the terminal; A central server aggregates the received data and performs AI processing; A means for broadcasting the results of AI processing to the terminal; The system includes a terminal that receives and displays the broadcasted results.

2. The system of claim 1 , further comprising means for triggering AI processing when the central server receives a certain number of data or more.

3. 10. The system of claim 1, further comprising means for the terminal to transmit the pre-processed data to the central server using an HTTP POST request.

Images