System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to upload an image; means for receiving and temporarily storing the image; an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, shape; a cost calculation engine for calculating a rough estimate based on the extracted feature data; and means for providing the rough estimate to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] For many companies, the process of creating estimates for product manufacturing is time-consuming and labor-intensive. In particular, the creation of estimates often does not lead to orders, resulting in an inefficient use of resources. Given this background, there is a need for a method to reduce the labor required for creating estimates and quickly provide accurate estimates that lead to orders. [Means for solving the problem]

[0005] The present invention provides a system in which a user uploads an image, and a server receives and temporarily stores the image. The system uses an artificial intelligence model to analyze the image and extract feature data such as pattern, size, and shape. A cost calculation engine then calculates a rough estimate based on the extracted feature data and provides it to the user. After the rough estimate is provided to the user, the system also includes a means for requesting confirmation of the exact estimate from the vendor. The artificial intelligence model is fine-tuned based on past estimate information and product data, enabling highly accurate analysis and estimation.

[0006] "User" refers to a person who accesses the system and performs the action of uploading images.

[0007] "Means for uploading images" refers to the functions and interfaces for sending image data held by the user to the online system.

[0008] "Means for receiving and temporarily storing" refers to the function of temporarily storing and holding image data sent by the user.

[0009] "Analysis" refers to the act of processing received image data to extract characteristic data such as pattern, size, shape, etc.

[0010] "Artificial intelligence model" refers to machine learning algorithms and neural networks used to extract specific features from image data.

[0011] "Feature data" refers to specific information such as pattern, size, and shape extracted through image analysis.

[0012] "Cost calculation engine" refers to an algorithm or program that calculates production costs based on extracted feature data.

[0013] "Estimate" means the approximate production cost calculated by the cost calculation engine.

[0014] "Contractor" refers to the business entity that provides the specific quote and production for the actual production of the product.

[0015] "Fine tuning" refers to the process of adjusting an artificial intelligence model to optimize its performance based on past estimate information and product data. [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] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyzes the images, generates an estimate, and, if necessary, requests a more accurate estimate from a vendor.

[0038] User-uploaded images

[0039] After logging in to the system, the user uploads the image data for which they wish to make a quote. The user selects the image file from the upload screen and presses the upload button.

[0040] Receiving and temporarily storing image data

[0041] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0042] Image analysis

[0043] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0044] Calculating a rough estimate

[0045] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0046] Providing a rough estimate

[0047] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0048] Request an accurate quote

[0049] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0050] Providing a final quote

[0051] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0052] Specific examples

[0053] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0054] In this way, the present invention provides a system that provides fast and accurate product manufacturing quotes, streamlining the manufacturing process.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] A user logs in to the system and accesses the image upload screen.

[0058] Step 2:

[0059] The user selects the image file to be quoted and presses the upload button.

[0060] Step 3:

[0061] The terminal transmits the selected image file to the server.

[0062] Step 4:

[0063] The server temporarily stores the received image data.

[0064] Step 5:

[0065] The server performs validation checks on the image data (checking file format and size).

[0066] Step 6:

[0067] The server passes the temporarily stored image data to the artificial intelligence model.

[0068] Step 7:

[0069] The artificial intelligence model uses image processing algorithms to extract feature data such as pattern, size, and shape.

[0070] Step 8:

[0071] The AI ​​model structures the extracted feature data and returns it to the server.

[0072] Step 9:

[0073] The server inputs the feature data into the cost calculation engine.

[0074] Step 10:

[0075] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[0076] Step 11:

[0077] The server transmits the calculated rough estimate data to the terminal.

[0078] Step 12:

[0079] The terminal displays a rough estimate to the user.

[0080] Step 13:

[0081] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate.

[0082] Step 14:

[0083] The terminal sends a precise quote request to the server.

[0084] Step 15:

[0085] The server receives an accurate quotation request and makes an inquiry to partner companies.

[0086] Step 16:

[0087] The partner company checks the actual production conditions, costs, and delivery dates and returns them to the server.

[0088] Step 17:

[0089] The server returns the final quote information received from the vendor to the user.

[0090] Step 18:

[0091] The terminal displays the final quote information to the user.

[0092] Example 1

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

[0094] Conventional rough estimate systems have an inefficient process for extracting feature data from images uploaded by users and providing accurate estimates based on that data. In particular, the lack of validation checks for image format and size often resulted in inappropriate images being processed, resulting in incorrect estimates. Another issue is the speed with which an accurate estimate can be requested from a contractor. There is a need to solve these problems and provide fast, accurate estimates.

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

[0096] In this invention, the server includes means for a user to upload an image, means for receiving and temporarily storing the image, means for validating the format and size of the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, and means for providing the rough estimate to the user.

[0097] This ensures that the format and size of images uploaded by users are checked correctly, enabling the extraction of feature data and the calculation of rough estimates quickly and accurately using appropriate image data. It also makes it possible to efficiently request accurate estimates from vendors, improving the accuracy and efficiency of the entire system.

[0098] "User" means an individual or company that uses the system to upload images or request quotes.

[0099] A "server" is a computer system that receives, temporarily stores, analyzes, and calculates and provides estimates for image data sent by users.

[0100] "Terminal" means the device (e.g., computer, smartphone) used by a User to access the System and upload Images.

[0101] "Image data" is digital data that includes image information of the product or part that is the subject of the quotation.

[0102] A "validation check" is a process that verifies that the format and size of the received image data are appropriate.

[0103] An "artificial intelligence model" is a machine learning algorithm that analyzes image data and extracts feature data such as pattern, size, and shape.

[0104] "Feature data" refers to data that includes information such as the pattern, size, and shape of a product or part extracted through image analysis.

[0105] The "cost calculation engine" is a software module that calculates a rough estimate based on characteristic data, taking into account factors such as material costs, processing costs, and labor hours.

[0106] A "rough estimate" is a preliminary calculation result of the manufacturing cost of a product or part calculated based on the extracted feature data.

[0107] "Contractor" is the company or individual who confirms and provides the final production cost and delivery date.

[0108] An "accurate estimate" is an estimate that includes the final production cost and delivery date after confirmation from the contractor.

[0109] "Past estimate information" is historical information about estimates made based on previously analyzed image data.

[0110] "Product handling data" is detailed data on products and parts that the system has analyzed and handled in the past.

[0111] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyze the images, generate an estimate, and, if necessary, request a more accurate estimate from a vendor.

[0112] The system consists of three main elements: users, terminals, and servers. Users access the system using terminals and upload images of the items they wish to quote. Terminals are devices that can connect to the Internet, such as PCs or smartphones. The server is a computer system that receives the uploaded image data, analyzes it, and provides quotes.

[0113] Users log in to the system and use the interface to upload image data for quotation. They click the "Upload Image" button on the interface, select the image file, and then click the "Upload" button to send the image to the server.

[0114] The device sends the image file selected by the user to the server, which temporarily stores the image data. At the same time, a validation check is performed to confirm the file format (e.g., JPEG, PNG) and size (e.g., up to 5MB). If an image file of an inappropriate format or size is uploaded, the server returns an error message to the user.

[0115] The server passes the temporarily stored image data to an artificial intelligence (AI) model. This AI model (e.g., ResNet or YOLO) uses an image processing algorithm to extract feature data such as the pattern, size, and shape of the product or part. The AI ​​model then structures the feature data and returns it to the server.

[0116] Next, the server launches a cost calculation engine based on the feature data obtained from the AI ​​model. The cost calculation engine calculates a rough estimate taking into account factors such as material costs, processing costs, and labor hours. Specifically, it retrieves the necessary information from the database and performs the appropriate calculations.

[0117] Once the rough estimate is calculated, the server sends the data to the terminal. The user can check the rough estimate data through the terminal. If the user is satisfied with the estimate, he / she clicks the "Request an accurate estimate" button, and the terminal sends the request to the server. The server then checks the details with the partner company and provides the final estimate information from the company to the user.

[0118] For example, if a user wants to get a quote for a new electronic part, they first log in to the system and upload an image of the part. The server receives the image, temporarily stores it, and validates it. Next, an AI model analyzes the image and extracts feature data. Based on this feature data, a cost calculation engine calculates material and processing costs and provides a rough estimate. If the user is satisfied with this rough estimate, they can request a more accurate quote, and the server will request detailed confirmation from the supplier. The final quote information is then provided to the user.

[0119] Examples of prompts include:

[0120] "I would like to get a quote for a new electronic component. Please analyze the image below and extract features. Identify the component's pattern, size, and shape from this image and provide a rough estimate based on that."

[0121] In this way, the present invention provides fast and accurate product manufacturing quotes and streamlines the manufacturing process.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] The user logs in to the system and uploads an image of the item to be quoted.

[0125] Input: User login information and image file

[0126] Operation: The user enters their ID and password on the system login screen and moves to the upload screen. The user clicks the "Upload Image" button and selects the image file to be quoted. Then, they click the "Upload" button to send the image.

[0127] Output: The selected image file is sent from the device to the server.

[0128] Step 2:

[0129] The terminal transmits the image file selected by the user to the server.

[0130] Input: An image file selected by the user and saved on the device

[0131] Operation: When the device sends the image file selected by the user to the server, it attaches basic information such as the data format and file size. The server then obtains the metadata associated with the image data.

[0132] Output: The image files and their metadata are received and temporarily stored on the server.

[0133] Step 3:

[0134] The server performs a validation check on the received image data and temporarily stores it.

[0135] Input: Image file sent from the device

[0136] Operation: The server checks whether the image file format (e.g., JPEG, PNG) and size (e.g., maximum 5MB) are valid. If validation is successful, the image is saved in a temporary folder. On the other hand, if the image format or size is inappropriate, an error message is generated and sent to the terminal.

[0137] Output: Image files that pass validation are temporarily saved, and if validation fails, an error message is sent to the terminal.

[0138] Step 4:

[0139] The server passes image data that has been successfully validated to the artificial intelligence model.

[0140] Input: Image file that has been successfully validated

[0141] How it works: The server inputs the saved image files into an AI model (e.g., ResNet or YOLO). The AI ​​model uses machine learning algorithms to extract feature data such as patterns, size, and shape from the image data.

[0142] Output: The feature data extracted by the AI ​​model is returned to the server.

[0143] Step 5:

[0144] The server uses a cost calculation engine to calculate a rough estimate based on the feature data obtained from the AI ​​model.

[0145] Input: Feature data returned from the AI ​​model

[0146] Operation: The server runs a cost calculation engine based on the feature data. The cost calculation engine extracts necessary information such as material costs, processing costs, and labor hours from the database and uses this data to calculate a rough estimate.

[0147] Output: The calculated rough estimate data is saved on the server.

[0148] Step 6:

[0149] The server transmits the calculated rough estimate data to the terminal.

[0150] Input: Calculated rough estimate data

[0151] Operation: The server sends the rough estimate data to the terminal so that the user can check it. The user can check the estimate details and calculation results on the terminal.

[0152] Output: The estimated data is displayed on the terminal.

[0153] Step 7:

[0154] If the user is satisfied with the rough estimate, he or she requests a more accurate estimate.

[0155] Input: User requests accurate quote

[0156] How it works: When the user clicks the "Request an accurate quote" button, the request is sent from the device to the server. The server then requests detailed confirmation from partner vendors. Specifically, it sends the extracted feature data and the quotation conditions to the vendors.

[0157] Output: The server sends a request for an accurate quote to the vendor.

[0158] Step 8:

[0159] The server provides the user with the final quote information received from the vendor.

[0160] Input: Final quote information from vendor

[0161] How it works: The vendor sends information about the final production cost and delivery date to the server. The server temporarily stores this information and notifies the user via their device. The user then checks the final estimate on their device and decides whether to request production based on that information.

[0162] Output: The final quote information is displayed on the terminal and notified to the user.

[0163] (Application example 1)

[0164] 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."

[0165] In modern manufacturing, there is a need to quickly and accurately estimate the production costs of parts and products. However, traditional methods are time-consuming and labor-intensive. Furthermore, it is difficult to quickly calculate costs on-site, which hinders rapid decision-making. This hinders the efficiency of the production process and limits productivity improvements. Furthermore, the time required to confirm accurate estimates with contractors based on rough estimates is also required, so further efficiency improvements are required.

[0166] 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.

[0167] In this invention, the server includes a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and a means for taking images of parts or products using a smartphone and transmitting the images to the server. This enables rapid cost calculation on-site and improves the efficiency of the production process. Furthermore, requesting an accurate estimate from a contractor based on the rough estimate enables rapid decision-making and contributes to improved productivity.

[0168] "User" refers to a person who uses the system to upload images and request a quote.

[0169] "Image" refers to a data file that visually records the shape, size, and other characteristics of a part or product.

[0170] "Upload" refers to the act of a user sending image data they have to a server.

[0171] A "means" refers to a combination of hardware and software for achieving a specific function.

[0172] "Receiving" refers to the process in which the server captures image data sent by the user.

[0173] "Temporarily saving" refers to the operation of saving received image data for a certain period of time.

[0174] "Analysis" refers to the process by which the server uses an artificial intelligence model to extract feature data from image data.

[0175] "Feature data" refers to information such as pattern, size, and shape extracted from an image.

[0176] An "artificial intelligence model" refers to an algorithm that extracts feature data using technologies such as machine learning and deep learning.

[0177] "Rough estimate" refers to the result of calculating a rough production cost based on feature data.

[0178] A "cost calculation engine" refers to a system that calculates a rough estimate based on extracted feature data, taking into account material costs, processing costs, labor hours, etc.

[0179] "Means for providing" refers to the process of displaying or notifying the calculated rough estimate to the user.

[0180] "Smartphone" refers to a portable information terminal that has Internet connectivity and is capable of taking and sending images.

[0181] "Server" refers to a computer system that receives image data from users, analyzes it, and calculates and provides a rough estimate.

[0182] This invention provides a system that allows users to quickly obtain a rough estimate by sending images taken with their smartphone to a server, thereby significantly improving the efficiency of the quotation process for parts and products in the manufacturing industry.

[0183] In the basic system configuration, users use a smartphone application to take pictures of parts or products and upload them to a server. This application includes functions for uploading images, communicating with the server, and displaying quotation results.

[0184] The server receives images sent by users and temporarily stores them. The stored images are first subjected to a validation check, and any images that are deemed inappropriate are requested to be re-uploaded. Images that pass validation are then passed to an artificial intelligence model, which extracts feature data such as pattern, size, and shape. The artificial intelligence model used here uses image analysis technologies such as TensorFlow and OpenCV.

[0185] Once the feature data is extracted, a cost calculation engine uses it to calculate a rough estimate. The cost calculation engine takes into account factors such as material costs, processing costs, and labor hours to generate an estimate. This result is then sent back to the user's smartphone via the server and displayed.

[0186] Furthermore, if the user is satisfied with the rough estimate, they can request a more accurate estimate from the supplier. Based on the user's request, the server will confirm the details with the supplier and confirm the final production cost and delivery date. This allows the user to receive a confirmed estimate and request production based on it.

[0187] For example, when a worker wants to manufacture a new part, he or she takes a picture of the part with their smartphone and sends it through the application. Within seconds, a rough estimate is displayed. The user can then decide to start production based on this estimate. This process allows for fast and efficient calculation of production costs.

[0188] Example prompts for generative AI models

[0189] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0190] Image file: [uploaded image]

[0191] Parameters: size, shape, weight

[0192] Estimate requirements: material costs, processing costs, labor hours

[0193] The above is a mode for carrying out the invention, and the specific operating procedures can be modified in various ways, thereby enabling the invention to be adapted to different manufacturing environments without losing its essence.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The user takes a picture of a part or product using a smartphone. The captured image is saved in the smartphone's application. The input is image data obtained by the smartphone's camera, and the output is an image file temporarily saved within the application. Specifically, the user taps the camera button on the smartphone to take a picture.

[0197] Step 2:

[0198] The user operates the application to take a picture and upload it to the server. The input is the taken image file, and the output is the image data sent to the server. Specifically, the user taps the "Upload" button in the application to send the image to the server.

[0199] Step 3:

[0200] The server temporarily stores the images it receives. The input is the image data sent by the user, and the output is the image file stored in temporary storage on the server. Specifically, the server stores the image data in a specified folder and performs validation checks on the file format and size.

[0201] Step 4:

[0202] The server passes the temporarily stored images to an artificial intelligence model for image analysis. The input is the image data stored on the server, and the output is feature data such as pattern, size, and shape. Specifically, the server calls an AI model (such as TensorFlow or OpenCV), analyzes the image data, and extracts feature data.

[0203] Step 5:

[0204] The server launches a cost calculation engine based on the extracted feature data to calculate a rough estimate. The input is the feature data, and the output is the rough estimate data. Specifically, the server runs a cost calculation algorithm to evaluate material costs, processing costs, labor hours, etc. to generate an estimate.

[0205] Step 6:

[0206] The server sends the calculated rough estimate data to the user's smartphone. The input is the rough estimate data, and the output is the estimate information displayed on the user's smartphone. Specifically, the server generates an HTTP response and sends the estimate data to the user application.

[0207] Step 7:

[0208] If the user is satisfied with the rough estimate, the application requests confirmation of the exact estimate from the supplier. The input is a formal quote request based on the rough estimate, and the output is the final quote information returned by the supplier. Specifically, the user taps the "Request a formal quote" button in the application, and the entered data is sent to the supplier via the server.

[0209] Step 8:

[0210] The server provides the user with the final quote information received from the vendor. The input is the final quote data from the vendor, and the output is the final quote information displayed on the user's smartphone. Specifically, the server analyzes the data received from the vendor and sends it to the user application.

[0211] Example prompts for generative AI models

[0212] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0213] Image file: [uploaded image]

[0214] Parameters: size, shape, weight

[0215] Estimate requirements: material costs, processing costs, labor hours

[0216] 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.

[0217] The present invention is a system that uses image data and emotion data to quickly provide rough estimates for products and parts, optimizing the user experience. The system allows users to upload images, analyzes the images to generate estimates, and, if necessary, requests accurate estimates from vendors, recognizing the user's emotions to optimize the response.

[0218] User-uploaded images

[0219] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required and presses the upload button.

[0220] Receiving and temporarily storing image data

[0221] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0222] Image analysis

[0223] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0224] Calculating a rough estimate

[0225] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0226] Providing a rough estimate

[0227] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0228] Request an accurate quote

[0229] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0230] Providing a final quote

[0231] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0232] Emotion recognition and optimization

[0233] The server is equipped with an emotion engine that recognizes the user's emotions using facial, voice, and text analysis. Based on the emotion data recognized by the emotion engine, the system provides countermeasures to optimize the user experience. For example, if the user shows a dissatisfied expression, the system will provide additional support and detailed explanations.

[0234] Specific examples

[0235] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0236] Furthermore, if a user expresses doubt or anxiety while uploading an image, the emotion engine will recognize that emotion and the server will automatically provide the user with appropriate advice and support.

[0237] In this way, the present invention provides fast and accurate product production quotes throughout the system, optimizing the user experience.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required.

[0241] Step 2:

[0242] The user presses the upload button. The device sends the selected image file and the user's facial expression data (if using the camera) to the server.

[0243] Step 3:

[0244] The server temporarily stores the received image data and facial expression data.

[0245] Step 4:

[0246] The server performs a validation check on the image data, checking the file format and size to ensure it is in the correct format.

[0247] Step 5:

[0248] The server passes the temporarily stored image data to the artificial intelligence model.

[0249] Step 6:

[0250] The AI ​​model uses image processing algorithms to extract feature data such as pattern, size, shape, etc. The extracted feature data is structured and returned to the server.

[0251] Step 7:

[0252] The server inputs the feature data into the cost calculation engine.

[0253] Step 8:

[0254] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[0255] Step 9:

[0256] The server transmits the calculated rough estimate data to the terminal.

[0257] Step 10:

[0258] The terminal displays the estimated estimate data to the user.

[0259] Step 11:

[0260] If the user is satisfied with the rough estimate, he / she presses a button to request an accurate estimate, and the terminal sends data including a request for an accurate estimate to the server.

[0261] Step 12:

[0262] The server receives an accurate quotation request and makes an inquiry to partner companies.

[0263] Step 13:

[0264] The partner company checks the actual production conditions, costs, and delivery dates and sends them back to the server.

[0265] Step 14:

[0266] The server provides the user with the final quote information received from the vendor.

[0267] Step 15:

[0268] The terminal displays the final quote information to the user.

[0269] Step 16:

[0270] The emotion engine installed on the server analyzes the received user facial expression data, voice data, and text input data to recognize the user's emotions.

[0271] Step 17:

[0272] The server uses the emotion data generated by the emotion engine to determine countermeasures to optimize the user experience, for example, automatically providing additional support or detailed explanations when it recognizes a user's dissatisfaction.

[0273] Step 18:

[0274] The device will display solutions to the user, who can then seek additional support if needed.

[0275] The above is the specific flow of the process in the present invention. This system allows users to receive fast and accurate product manufacturing quotes, and provides an optimal user experience through emotion recognition.

[0276] Example 2

[0277] 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."

[0278] Conventional quotation systems require time-consuming image analysis, resulting in low accuracy of the estimates users receive. Furthermore, they lacked sufficient mechanisms for improving the user experience, leaving users feeling dissatisfied and anxious. Furthermore, they lacked the technology to recognize user emotions and automatically provide appropriate responses.

[0279] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to upload an image, means for receiving and temporarily saving the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, means for providing the rough estimate to the user, an emotion engine for recognizing emotion data by analyzing the user's facial expression or voice, and response means for providing a response based on the emotion data recognized by the emotion engine. This makes it possible to provide a quick and accurate estimate and provide optimal support according to the user's emotions.

[0280] "User" refers to a user who uses this system to upload images and receive estimates and support.

[0281] "Means for uploading images" refers to functionality including interfaces and programs that users use to send image files to the system.

[0282] The "means for receiving and temporarily storing" refers to a function used by the server to receive image data sent from the user and temporarily store it.

[0283] "Artificial intelligence model for analyzing images and extracting feature data such as pattern, size, and shape" refers to a model that includes algorithms and programs that analyze image data, identify the characteristics of the object, and digitize them.

[0284] "Cost calculation engine for calculating a rough estimate" refers to an algorithm or program for calculating a rough estimate based on extracted feature data, taking into account the necessary material costs, processing costs, labor hours, etc.

[0285] "Means for providing a quote to a user" refers to the functionality used to display or transmit the calculated rough quote to the user's terminal.

[0286] An "emotion engine" refers to an algorithm or program that analyzes a user's facial expressions, voice, text, etc. and recognizes their emotions.

[0287] "Response means" refers to a function for providing appropriate support and information to users based on the emotional data recognized by the emotion engine.

[0288] "Vendor" refers to an external service provider or manufacturer that works with the server to provide accurate quotes and production.

[0289] "Fine-tuning" refers to the process by which artificial intelligence models are optimized based on historical usage and product data.

[0290] The present invention is a system that uses image data and emotion data to provide rapid product or part quotes and optimize the user experience. The system is implemented in the following manner.

[0291] The overall system configuration involves users uploading images, which the server analyzes to generate quotes, and the system also recognizes the user's emotions and optimizes responses.

[0292] Required Hardware and Software

[0293] The system uses a common web browser, server, artificial intelligence model, and emotion engine. Specifically, it uses the following hardware and software:

[0294] User device: A computer, smartphone, tablet, etc. that runs a web browser

[0295] Server: Physical server or cloud service for data processing and storage

[0296] Artificial intelligence models: Deep learning frameworks such as TensorFlow

[0297] Emotion engine: AWS Amazon Rekognition and Emotion API

[0298] System Program Processing

[0299] The system performs a process that includes the following major steps:

[0300] 1. User image upload:

[0301] A user logs into the system through a web browser and uploads an image of the product or part for which they want to receive a quote. The user presses the upload button and selects the image file.

[0302] 2. Receiving and temporarily storing image data:

[0303] The device sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check.

[0304] 3. Image Analysis:

[0305] The server analyzes the image using an artificial intelligence model such as TensorFlow to extract feature data such as pattern, size, and shape, and the analysis results are returned to the server as structured data.

[0306] 4. Calculating a rough estimate:

[0307] The server then uses the extracted feature data to launch an in-house cost calculation engine to calculate a rough estimate, taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0308] 5. Providing a rough estimate:

[0309] The server transmits the calculated rough estimate to the user's terminal, where the user can view the estimate.

[0310] 6. Request an accurate quote:

[0311] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then confirms the details with the partner company and confirms the final production cost and delivery date.

[0312] 7. Providing a final quote:

[0313] The server sends the final quotation information received from the supplier to the user's terminal, where the user can confirm the final quotation and request production.

[0314] 8. Emotion recognition and optimization:

[0315] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. Based on the emotional data recognized by the emotion engine, the server automatically provides appropriate support and information.

[0316] Specific examples

[0317] For example, if a user wants to get a quote for a new electronic component, the system operates as follows:

[0318] 1. The user selects an image file of an electronic component (JPEG format, size 1.5MB) and presses the upload button.

[0319] 2. The device sends the selected image to the server as an HTTP POST request.

[0320] 3. The server receives the image, checks the format and size, and temporarily stores it.

[0321] 4. The server uses a TensorFlow model to analyze patterns, size, and shape from the image.

[0322] 5. Based on the analysis results, the cost calculation engine calculates material and processing costs.

[0323] 6. The server sends a rough estimate to the device, where the user can confirm it.

[0324] 7. The user presses the "Request an accurate quote" button.

[0325] 8. The server requests detailed estimates from the vendors and obtains the final estimate information.

[0326] 9. The server provides the final quote to the user.

[0327] 10. If the user shows signs of anxiety, the emotion engine will recognize this and display additional support information.

[0328] Prompt Sentence Examples

[0329] "Upload images of your new electronic components and begin the process of receiving a detailed quote."

[0330] In this way, the present invention aims to provide fast and accurate product production quotes and enhance the user experience.

[0331] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0332] Step 1: User uploads an image

[0333] The user logs in to the system and accesses the image upload screen. The user selects the image file to be quoted and presses the upload button. At this time, the image selected by the user is sent via a browser form. The input is the image file selected by the user, and the output is the image data sent to the server.

[0334] Step 2: Receiving and temporarily saving image data

[0335] The terminal sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check. Specifically, it verifies that the image format (e.g., JPEG, PNG) and size (e.g., 2MB or less) are appropriate. The input is the image data included in the HTTP POST request, and the output is the validated image data.

[0336] Step 3: Image analysis

[0337] The server passes the temporarily stored image data to an artificial intelligence model (e.g., TensorFlow). The model uses an image processing algorithm to extract feature data such as pattern, size, and shape. For example, it uses the model.predict(image data) method. The input is the validated image data, and the output is a structured list of feature data.

[0338] Step 4: Calculate a rough estimate

[0339] The server uses the extracted feature data to launch a cost calculation engine. This engine calculates a rough estimate by taking into account the cost of required materials, processing costs, labor hours, etc. For example, it calculates the cost by calling a function called calculate_cost(feature data). The input is a structured list of feature data, and the output is a numerical estimate.

[0340] Step 5: Provide a rough estimate

[0341] The server sends the calculated rough estimate data to the terminal. This communication is implemented as an HTTP response and displayed in the user's browser. The input is the numerical data of the rough estimate, and the output is the estimate information displayed in the browser.

[0342] Step 6: Request an accurate quote

[0343] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate. The device sends this request as an HTTP POST request to the server. The server receives this request, checks the details with the partner vendor, and confirms the final production cost and delivery date. The input is the user's request data, and the output is the final estimate information from the vendor.

[0344] Step 7: Providing a final quote

[0345] The server provides the final quote information received from the supplier to the user. This communication is also implemented as an HTTP response. The input is the final quote information, and the output is the final quote information displayed in the browser.

[0346] Step 8: Emotion recognition and optimization

[0347] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. When the emotion engine recognizes an emotion, the system provides appropriate support and information corresponding to that emotion. For example, if the user shows an anxious expression, the system provides additional support information. The input is the user's facial expression and voice data, and the output is information on countermeasures.

[0348] (Application example 2)

[0349] 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."

[0350] In modern manufacturing, fast and accurate product and component quotations are essential for efficient production management and cost reduction. However, existing systems do not consider user emotions during the quotation generation process using image data, resulting in a suboptimal user experience. Furthermore, more advanced analysis systems are needed to identify product deterioration and defects, as well as recognize the emotions of factory staff.

[0351] 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 a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and an emotion engine for acquiring emotion data and recognizing the user's emotion. This not only enables quick and accurate product estimates but also enables optimal responses that take user emotions into consideration. Furthermore, by checking products in the factory and monitoring staff emotions, the efficiency and quality of the entire manufacturing process can be improved.

[0352] "Means for users to upload images" means a function or interface that allows users to send image data to the system.

[0353] The "means for receiving and temporarily storing the image" refers to a module or device that has the function of temporarily storing image data sent from a user and further verifying the quality and format of the data.

[0354] "Artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape" refers to a software model that automatically analyzes and extracts features related to products and parts from image data using machine learning algorithms.

[0355] "Cost calculation engine that calculates a rough estimate based on the extracted feature data" refers to an algorithm and software engine that uses the extracted feature data to roughly calculate the manufacturing cost of a product.

[0356] The "means for providing the rough estimate to the user" refers to a function or interface for visually or audibly notifying the user of the calculated rough estimate information.

[0357] "Emotion engine for acquiring emotion data and recognizing a user's emotion" means an analytical algorithm and software engine for analyzing facial expressions, voice, and text data acquired from a user and identifying the user's emotional state.

[0358] This invention relates to a "robot assistant" system that checks products and calculates estimates in factories. The robot, equipped with smart glasses, mainly recognizes product images in real time, calculates estimates, and analyzes the emotions of factory staff to optimize work efficiency.

[0359] Hardware and software used

[0360] Hardware: Smart glasses, patrol robots

[0361] software:

[0362] Image analysis model (artificial intelligence model using TensorFlow / Keras)

[0363] Emotion recognition model (FER, MTCNN)

[0364] REST API (cost calculation engine)

[0365] System Flow

[0366] 1. Image upload and analysis:

[0367] The server receives the image data captured by the robot through the smart glasses and temporarily stores it.

[0368] This image data is then passed to an artificial intelligence model to extract feature data such as pattern, size, and shape.

[0369] 2. Acquiring and analyzing emotion data:

[0370] The server receives and temporarily stores facial images of factory staff taken with the smart glasses.

[0371] The emotional recognition model (FER) is used to analyze the emotional state of staff and generate the recognized emotions and their scores.

[0372] 3. Calculating a rough estimate:

[0373] The server sends the feature data obtained from the artificial intelligence model to the cost calculation engine.

[0374] The cost calculation engine calculates a rough estimate based on the acquired data, taking into account factors such as the cost of necessary materials, processing costs, and labor hours.

[0375] 4. Providing rough estimates and sentiment data:

[0376] The server transmits the calculated rough estimate data and the analyzed emotion data to the robot.

[0377] The robot provides this data to factory staff through display devices (display and audio output).

[0378] 5. Optimizing the user experience:

[0379] The server uses the emotion data to provide countermeasures to optimize the user experience, for example, providing additional support or detailed explanations if the user shows signs of dissatisfaction.

[0380] Specific examples

[0381] For example, a factory robot patrols an electronic parts production line, photographing any deterioration or defects in the product with smart glasses and analyzing the images. Based on the detection results, a cost calculation engine generates estimates and provides a list of defective products in real time. Furthermore, the system uses emotion analysis to observe the stress and fatigue of line workers, optimizing the speed of work and the timing of breaks.

[0382] Prompt Sentence Examples

[0383] "Please analyze this image (path_to_product_image.jpg), extract the product feature data, and get a rough estimate. Also, please analyze the emotion of the person in the image and provide the recognized emotion and its score."

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The user takes an image using a means for uploading images, and the robot sends the image data of the product taken through the smart glasses to a server. The server temporarily stores the received image data. In this process, the smart glasses act as an input device, and the server acts as a data storage device that temporarily stores the image data.

[0387] Step 2:

[0388] The server performs a validation check on the saved image data. Here, it checks to make sure that the image data format (JPEG, PNG, etc.), resolution, and size are appropriate. Image data that passes the validation check is sent to the next analysis step. If validation fails, an error message is output.

[0389] Step 3:

[0390] The server sends the image data that has passed validation to an artificial intelligence model for image analysis. The image analysis model (a model using TensorFlow / Keras) extracts feature data such as pattern, size, and shape from the image data. This process takes the image data as input and outputs feature data. Specifically, a Convolutional Neural Network (CNN) is used to identify specific parts of the image and extract characteristics as numerical data.

[0391] Step 4:

[0392] The server uses the extracted feature data to send data to a cost calculation engine. The cost calculation engine calculates a rough estimate based on the feature data, taking into account factors such as material costs, processing costs, and labor hours. The input here is the feature data, and the output is a rough estimate. The data is sent to an external cost calculation service using a REST API, and the results are obtained.

[0393] Step 5:

[0394] The server sends the calculated rough estimate data to the robot, which then displays the rough estimate to the factory staff through smart glasses. This process uses the estimate data as input and outputs the results using a display and audio output.

[0395] Step 6:

[0396] The server receives and temporarily stores facial images of factory staff taken with smart glasses. The received image data is sent to the emotion recognition model (FER) for analysis. The emotion recognition model analyzes facial expressions from the images, recognizes the emotional state, and generates corresponding data. In this process, the facial expression image is input and the recognized emotional data is output.

[0397] Step 7:

[0398] The server optimizes the user experience based on the emotional data obtained from the emotion recognition model. If the emotional data indicates dissatisfaction or fatigue, the system generates countermeasures offering additional support or detailed explanations, which are then provided to the factory staff via the robot. Specifically, this could include displaying detailed operating instructions or playing a voice message encouraging the staff to take a break.

[0399] This series of processes enables quick and accurate product estimates and optimal responses that take user feelings into consideration.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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. 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] In the smart glasses 214, 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.

[0415] 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."

[0416] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyzes the images, generates an estimate, and, if necessary, requests a more accurate estimate from a vendor.

[0417] User-uploaded images

[0418] After logging in to the system, the user uploads the image data for which they wish to make a quote. The user selects the image file from the upload screen and presses the upload button.

[0419] Receiving and temporarily storing image data

[0420] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0421] Image analysis

[0422] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0423] Calculating a rough estimate

[0424] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0425] Providing a rough estimate

[0426] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0427] Request an accurate quote

[0428] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0429] Providing a final quote

[0430] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0431] Specific examples

[0432] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0433] In this way, the present invention provides a system that provides fast and accurate product manufacturing quotes, streamlining the manufacturing process.

[0434] The processing flow will be explained below.

[0435] Step 1:

[0436] A user logs in to the system and accesses the image upload screen.

[0437] Step 2:

[0438] The user selects the image file to be quoted and presses the upload button.

[0439] Step 3:

[0440] The terminal transmits the selected image file to the server.

[0441] Step 4:

[0442] The server temporarily stores the received image data.

[0443] Step 5:

[0444] The server performs validation checks on the image data (checking file format and size).

[0445] Step 6:

[0446] The server passes the temporarily stored image data to the artificial intelligence model.

[0447] Step 7:

[0448] The artificial intelligence model uses image processing algorithms to extract feature data such as pattern, size, and shape.

[0449] Step 8:

[0450] The AI ​​model structures the extracted feature data and returns it to the server.

[0451] Step 9:

[0452] The server inputs the feature data into the cost calculation engine.

[0453] Step 10:

[0454] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[0455] Step 11:

[0456] The server transmits the calculated rough estimate data to the terminal.

[0457] Step 12:

[0458] The terminal displays a rough estimate to the user.

[0459] Step 13:

[0460] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate.

[0461] Step 14:

[0462] The terminal sends a precise quote request to the server.

[0463] Step 15:

[0464] The server receives an accurate quotation request and makes an inquiry to partner companies.

[0465] Step 16:

[0466] The partner company checks the actual production conditions, costs, and delivery dates and returns them to the server.

[0467] Step 17:

[0468] The server returns the final quote information received from the vendor to the user.

[0469] Step 18:

[0470] The terminal displays the final quote information to the user.

[0471] Example 1

[0472] 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."

[0473] Conventional rough estimate systems have an inefficient process for extracting feature data from images uploaded by users and providing accurate estimates based on that data. In particular, the lack of validation checks for image format and size often resulted in inappropriate images being processed, resulting in incorrect estimates. Another issue is the speed with which an accurate estimate can be requested from a contractor. There is a need to solve these problems and provide fast, accurate estimates.

[0474] 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.

[0475] In this invention, the server includes means for a user to upload an image, means for receiving and temporarily storing the image, means for validating the format and size of the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, and means for providing the rough estimate to the user.

[0476] This ensures that the format and size of images uploaded by users are checked correctly, enabling the extraction of feature data and the calculation of rough estimates quickly and accurately using appropriate image data. It also makes it possible to efficiently request accurate estimates from vendors, improving the accuracy and efficiency of the entire system.

[0477] "User" means an individual or company that uses the system to upload images or request quotes.

[0478] A "server" is a computer system that receives, temporarily stores, analyzes, and calculates and provides estimates for image data sent by users.

[0479] "Terminal" means the device (e.g., computer, smartphone) used by a User to access the System and upload Images.

[0480] "Image data" is digital data that includes image information of the product or part that is the subject of the quotation.

[0481] A "validation check" is a process that verifies that the format and size of the received image data are appropriate.

[0482] An "artificial intelligence model" is a machine learning algorithm that analyzes image data and extracts feature data such as pattern, size, and shape.

[0483] "Feature data" refers to data that includes information such as the pattern, size, and shape of a product or part extracted through image analysis.

[0484] The "cost calculation engine" is a software module that calculates a rough estimate based on characteristic data, taking into account factors such as material costs, processing costs, and labor hours.

[0485] A "rough estimate" is a preliminary calculation result of the manufacturing cost of a product or part calculated based on the extracted feature data.

[0486] "Contractor" is the company or individual who confirms and provides the final production cost and delivery date.

[0487] An "accurate estimate" is an estimate that includes the final production cost and delivery date after confirmation from the contractor.

[0488] "Past estimate information" is historical information about estimates made based on previously analyzed image data.

[0489] "Product handling data" is detailed data on products and parts that the system has analyzed and handled in the past.

[0490] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyze the images, generate an estimate, and, if necessary, request a more accurate estimate from a vendor.

[0491] The system consists of three main elements: users, terminals, and servers. Users access the system using terminals and upload images of the items they wish to quote. Terminals are devices that can connect to the Internet, such as PCs or smartphones. The server is a computer system that receives the uploaded image data, analyzes it, and provides quotes.

[0492] Users log in to the system and use the interface to upload image data for quotation. They click the "Upload Image" button on the interface, select the image file, and then click the "Upload" button to send the image to the server.

[0493] The device sends the image file selected by the user to the server, which temporarily stores the image data. At the same time, a validation check is performed to confirm the file format (e.g., JPEG, PNG) and size (e.g., up to 5MB). If an image file of an inappropriate format or size is uploaded, the server returns an error message to the user.

[0494] The server passes the temporarily stored image data to an artificial intelligence (AI) model. This AI model (e.g., ResNet or YOLO) uses an image processing algorithm to extract feature data such as the pattern, size, and shape of the product or part. The AI ​​model then structures the feature data and returns it to the server.

[0495] Next, the server launches a cost calculation engine based on the feature data obtained from the AI ​​model. The cost calculation engine calculates a rough estimate taking into account factors such as material costs, processing costs, and labor hours. Specifically, it retrieves the necessary information from the database and performs the appropriate calculations.

[0496] Once the rough estimate is calculated, the server sends the data to the terminal. The user can check the rough estimate data through the terminal. If the user is satisfied with the estimate, he / she clicks the "Request an accurate estimate" button, and the terminal sends the request to the server. The server then checks the details with the partner company and provides the final estimate information from the company to the user.

[0497] For example, if a user wants to get a quote for a new electronic part, they first log in to the system and upload an image of the part. The server receives the image, temporarily stores it, and validates it. Next, an AI model analyzes the image and extracts feature data. Based on this feature data, a cost calculation engine calculates material and processing costs and provides a rough estimate. If the user is satisfied with this rough estimate, they can request a more accurate quote, and the server will request detailed confirmation from the supplier. The final quote information is then provided to the user.

[0498] Examples of prompts include:

[0499] "I would like to get a quote for a new electronic component. Please analyze the image below and extract features. Identify the component's pattern, size, and shape from this image and provide a rough estimate based on that."

[0500] In this way, the present invention provides fast and accurate product manufacturing quotes and streamlines the manufacturing process.

[0501] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0502] Step 1:

[0503] The user logs in to the system and uploads an image of the item to be quoted.

[0504] Input: User login information and image file

[0505] Operation: The user enters their ID and password on the system login screen and moves to the upload screen. The user clicks the "Upload Image" button and selects the image file to be quoted. Then, they click the "Upload" button to send the image.

[0506] Output: The selected image file is sent from the device to the server.

[0507] Step 2:

[0508] The terminal transmits the image file selected by the user to the server.

[0509] Input: An image file selected by the user and saved on the device

[0510] Operation: When the device sends the image file selected by the user to the server, it attaches basic information such as the data format and file size. The server then obtains the metadata associated with the image data.

[0511] Output: The image files and their metadata are received and temporarily stored on the server.

[0512] Step 3:

[0513] The server performs a validation check on the received image data and temporarily stores it.

[0514] Input: Image file sent from the device

[0515] Operation: The server checks whether the image file format (e.g., JPEG, PNG) and size (e.g., maximum 5MB) are valid. If validation is successful, the image is saved in a temporary folder. On the other hand, if the image format or size is inappropriate, an error message is generated and sent to the terminal.

[0516] Output: Image files that pass validation are temporarily saved, and if validation fails, an error message is sent to the terminal.

[0517] Step 4:

[0518] The server passes image data that has been successfully validated to the artificial intelligence model.

[0519] Input: Image file that has been successfully validated

[0520] How it works: The server inputs the saved image files into an AI model (e.g., ResNet or YOLO). The AI ​​model uses machine learning algorithms to extract feature data such as patterns, size, and shape from the image data.

[0521] Output: The feature data extracted by the AI ​​model is returned to the server.

[0522] Step 5:

[0523] The server uses a cost calculation engine to calculate a rough estimate based on the feature data obtained from the AI ​​model.

[0524] Input: Feature data returned from the AI ​​model

[0525] Operation: The server runs a cost calculation engine based on the feature data. The cost calculation engine extracts necessary information such as material costs, processing costs, and labor hours from the database and uses this data to calculate a rough estimate.

[0526] Output: The calculated rough estimate data is saved on the server.

[0527] Step 6:

[0528] The server transmits the calculated rough estimate data to the terminal.

[0529] Input: Calculated rough estimate data

[0530] Operation: The server sends the rough estimate data to the terminal so that the user can check it. The user can check the estimate details and calculation results on the terminal.

[0531] Output: The estimated data is displayed on the terminal.

[0532] Step 7:

[0533] If the user is satisfied with the rough estimate, he or she requests a more accurate estimate.

[0534] Input: User requests accurate quote

[0535] How it works: When the user clicks the "Request an accurate quote" button, the request is sent from the device to the server. The server then requests detailed confirmation from partner vendors. Specifically, it sends the extracted feature data and the quotation conditions to the vendors.

[0536] Output: The server sends a request for an accurate quote to the vendor.

[0537] Step 8:

[0538] The server provides the user with the final quote information received from the vendor.

[0539] Input: Final quote information from vendor

[0540] How it works: The vendor sends information about the final production cost and delivery date to the server. The server temporarily stores this information and notifies the user via their device. The user then checks the final estimate on their device and decides whether to request production based on that information.

[0541] Output: The final quote information is displayed on the terminal and notified to the user.

[0542] (Application example 1)

[0543] 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."

[0544] In modern manufacturing, there is a need to quickly and accurately estimate the production costs of parts and products. However, traditional methods are time-consuming and labor-intensive. Furthermore, it is difficult to quickly calculate costs on-site, which hinders rapid decision-making. This hinders the efficiency of the production process and limits productivity improvements. Furthermore, the time required to confirm accurate estimates with contractors based on rough estimates is also required, so further efficiency improvements are required.

[0545] 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.

[0546] In this invention, the server includes a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and a means for taking images of parts or products using a smartphone and transmitting the images to the server. This enables rapid cost calculation on-site and improves the efficiency of the production process. Furthermore, requesting an accurate estimate from a contractor based on the rough estimate enables rapid decision-making and contributes to improved productivity.

[0547] "User" refers to a person who uses the system to upload images and request a quote.

[0548] "Image" refers to a data file that visually records the shape, size, and other characteristics of a part or product.

[0549] "Upload" refers to the act of a user sending image data they have to a server.

[0550] A "means" refers to a combination of hardware and software for achieving a specific function.

[0551] "Receiving" refers to the process in which the server captures image data sent by the user.

[0552] "Temporarily saving" refers to the operation of saving received image data for a certain period of time.

[0553] "Analysis" refers to the process by which the server uses an artificial intelligence model to extract feature data from image data.

[0554] "Feature data" refers to information such as pattern, size, and shape extracted from an image.

[0555] An "artificial intelligence model" refers to an algorithm that extracts feature data using technologies such as machine learning and deep learning.

[0556] "Rough estimate" refers to the result of calculating a rough production cost based on feature data.

[0557] A "cost calculation engine" refers to a system that calculates a rough estimate based on extracted feature data, taking into account material costs, processing costs, labor hours, etc.

[0558] "Means for providing" refers to the process of displaying or notifying the calculated rough estimate to the user.

[0559] "Smartphone" refers to a portable information terminal that has Internet connectivity and is capable of taking and sending images.

[0560] "Server" refers to a computer system that receives image data from users, analyzes it, and calculates and provides a rough estimate.

[0561] This invention provides a system that allows users to quickly obtain a rough estimate by sending images taken with their smartphone to a server, thereby significantly improving the efficiency of the quotation process for parts and products in the manufacturing industry.

[0562] In the basic system configuration, users use a smartphone application to take pictures of parts or products and upload them to a server. This application includes functions for uploading images, communicating with the server, and displaying quotation results.

[0563] The server receives images sent by users and temporarily stores them. The stored images are first subjected to a validation check, and any images that are deemed inappropriate are requested to be re-uploaded. Images that pass validation are then passed to an artificial intelligence model, which extracts feature data such as pattern, size, and shape. The artificial intelligence model used here uses image analysis technologies such as TensorFlow and OpenCV.

[0564] Once the feature data is extracted, a cost calculation engine uses it to calculate a rough estimate. The cost calculation engine takes into account factors such as material costs, processing costs, and labor hours to generate an estimate. This result is then sent back to the user's smartphone via the server and displayed.

[0565] Furthermore, if the user is satisfied with the rough estimate, they can request a more accurate estimate from the supplier. Based on the user's request, the server will confirm the details with the supplier and confirm the final production cost and delivery date. This allows the user to receive a confirmed estimate and request production based on it.

[0566] For example, when a worker wants to manufacture a new part, he or she takes a picture of the part with their smartphone and sends it through the application. Within seconds, a rough estimate is displayed. The user can then decide to start production based on this estimate. This process allows for fast and efficient calculation of production costs.

[0567] Example prompts for generative AI models

[0568] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0569] Image file: [uploaded image]

[0570] Parameters: size, shape, weight

[0571] Estimate requirements: material costs, processing costs, labor hours

[0572] The above is a mode for carrying out the invention, and the specific operating procedures can be modified in various ways, thereby enabling the invention to be adapted to different manufacturing environments without losing its essence.

[0573] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0574] Step 1:

[0575] The user takes a picture of a part or product using a smartphone. The captured image is saved in the smartphone's application. The input is image data obtained by the smartphone's camera, and the output is an image file temporarily saved within the application. Specifically, the user taps the camera button on the smartphone to take a picture.

[0576] Step 2:

[0577] The user operates the application to take a picture and upload it to the server. The input is the taken image file, and the output is the image data sent to the server. Specifically, the user taps the "Upload" button in the application to send the image to the server.

[0578] Step 3:

[0579] The server temporarily stores the images it receives. The input is the image data sent by the user, and the output is the image file stored in temporary storage on the server. Specifically, the server stores the image data in a specified folder and performs validation checks on the file format and size.

[0580] Step 4:

[0581] The server passes the temporarily stored images to an artificial intelligence model for image analysis. The input is the image data stored on the server, and the output is feature data such as pattern, size, and shape. Specifically, the server calls an AI model (such as TensorFlow or OpenCV), analyzes the image data, and extracts feature data.

[0582] Step 5:

[0583] The server launches a cost calculation engine based on the extracted feature data to calculate a rough estimate. The input is the feature data, and the output is the rough estimate data. Specifically, the server runs a cost calculation algorithm to evaluate material costs, processing costs, labor hours, etc. to generate an estimate.

[0584] Step 6:

[0585] The server sends the calculated rough estimate data to the user's smartphone. The input is the rough estimate data, and the output is the estimate information displayed on the user's smartphone. Specifically, the server generates an HTTP response and sends the estimate data to the user application.

[0586] Step 7:

[0587] If the user is satisfied with the rough estimate, the application requests confirmation of the exact estimate from the supplier. The input is a formal quote request based on the rough estimate, and the output is the final quote information returned by the supplier. Specifically, the user taps the "Request a formal quote" button in the application, and the entered data is sent to the supplier via the server.

[0588] Step 8:

[0589] The server provides the user with the final quote information received from the vendor. The input is the final quote data from the vendor, and the output is the final quote information displayed on the user's smartphone. Specifically, the server analyzes the data received from the vendor and sends it to the user application.

[0590] Example prompts for generative AI models

[0591] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0592] Image file: [uploaded image]

[0593] Parameters: size, shape, weight

[0594] Estimate requirements: material costs, processing costs, labor hours

[0595] 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.

[0596] The present invention is a system that uses image data and emotion data to quickly provide rough estimates for products and parts, optimizing the user experience. The system allows users to upload images, analyzes the images to generate estimates, and, if necessary, requests accurate estimates from vendors, recognizing the user's emotions to optimize the response.

[0597] User-uploaded images

[0598] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required and presses the upload button.

[0599] Receiving and temporarily storing image data

[0600] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0601] Image analysis

[0602] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0603] Calculating a rough estimate

[0604] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0605] Providing a rough estimate

[0606] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0607] Request an accurate quote

[0608] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0609] Providing a final quote

[0610] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0611] Emotion recognition and optimization

[0612] The server is equipped with an emotion engine that recognizes the user's emotions using facial, voice, and text analysis. Based on the emotion data recognized by the emotion engine, the system provides countermeasures to optimize the user experience. For example, if the user shows a dissatisfied expression, the system will provide additional support and detailed explanations.

[0613] Specific examples

[0614] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0615] Furthermore, if a user expresses doubt or anxiety while uploading an image, the emotion engine will recognize that emotion and the server will automatically provide the user with appropriate advice and support.

[0616] In this way, the present invention provides fast and accurate product production quotes throughout the system, optimizing the user experience.

[0617] The processing flow will be explained below.

[0618] Step 1:

[0619] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required.

[0620] Step 2:

[0621] The user presses the upload button. The device sends the selected image file and the user's facial expression data (if using the camera) to the server.

[0622] Step 3:

[0623] The server temporarily stores the received image data and facial expression data.

[0624] Step 4:

[0625] The server performs a validation check on the image data, checking the file format and size to ensure it is in the correct format.

[0626] Step 5:

[0627] The server passes the temporarily stored image data to the artificial intelligence model.

[0628] Step 6:

[0629] The AI ​​model uses image processing algorithms to extract feature data such as pattern, size, shape, etc. The extracted feature data is structured and returned to the server.

[0630] Step 7:

[0631] The server inputs the feature data into the cost calculation engine.

[0632] Step 8:

[0633] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[0634] Step 9:

[0635] The server transmits the calculated rough estimate data to the terminal.

[0636] Step 10:

[0637] The terminal displays the estimated estimate data to the user.

[0638] Step 11:

[0639] If the user is satisfied with the rough estimate, he / she presses a button to request an accurate estimate, and the terminal sends data including a request for an accurate estimate to the server.

[0640] Step 12:

[0641] The server receives an accurate quotation request and makes an inquiry to partner companies.

[0642] Step 13:

[0643] The partner company checks the actual production conditions, costs, and delivery dates and sends them back to the server.

[0644] Step 14:

[0645] The server provides the user with the final quote information received from the vendor.

[0646] Step 15:

[0647] The terminal displays the final quote information to the user.

[0648] Step 16:

[0649] The emotion engine installed on the server analyzes the received user facial expression data, voice data, and text input data to recognize the user's emotions.

[0650] Step 17:

[0651] The server uses the emotion data generated by the emotion engine to determine countermeasures to optimize the user experience, for example, automatically providing additional support or detailed explanations when it recognizes a user's dissatisfaction.

[0652] Step 18:

[0653] The device will display solutions to the user, who can then seek additional support if needed.

[0654] The above is the specific flow of the process in the present invention. This system allows users to receive fast and accurate product manufacturing quotes, and provides an optimal user experience through emotion recognition.

[0655] Example 2

[0656] 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."

[0657] Conventional quotation systems require time-consuming image analysis, resulting in low accuracy of the estimates users receive. Furthermore, they lacked sufficient mechanisms for improving the user experience, leaving users feeling dissatisfied and anxious. Furthermore, they lacked the technology to recognize user emotions and automatically provide appropriate responses.

[0658] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to upload an image, means for receiving and temporarily saving the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, means for providing the rough estimate to the user, an emotion engine for recognizing emotion data by analyzing the user's facial expression or voice, and response means for providing a response based on the emotion data recognized by the emotion engine. This makes it possible to provide a quick and accurate estimate and provide optimal support according to the user's emotions.

[0659] "User" refers to a user who uses this system to upload images and receive estimates and support.

[0660] "Means for uploading images" refers to functionality including interfaces and programs that users use to send image files to the system.

[0661] The "means for receiving and temporarily storing" refers to a function used by the server to receive image data sent from the user and temporarily store it.

[0662] "Artificial intelligence model for analyzing images and extracting feature data such as pattern, size, and shape" refers to a model that includes algorithms and programs that analyze image data, identify the characteristics of the object, and digitize them.

[0663] "Cost calculation engine for calculating a rough estimate" refers to an algorithm or program for calculating a rough estimate based on extracted feature data, taking into account the necessary material costs, processing costs, labor hours, etc.

[0664] "Means for providing a quote to a user" refers to the functionality used to display or transmit the calculated rough quote to the user's terminal.

[0665] An "emotion engine" refers to an algorithm or program that analyzes a user's facial expressions, voice, text, etc. and recognizes their emotions.

[0666] "Response means" refers to a function for providing appropriate support and information to users based on the emotional data recognized by the emotion engine.

[0667] "Vendor" refers to an external service provider or manufacturer that works with the server to provide accurate quotes and production.

[0668] "Fine-tuning" refers to the process by which artificial intelligence models are optimized based on historical usage and product data.

[0669] The present invention is a system that uses image data and emotion data to provide rapid product or part quotes and optimize the user experience. The system is implemented in the following manner.

[0670] The overall system configuration involves users uploading images, which the server analyzes to generate quotes, and the system also recognizes the user's emotions and optimizes responses.

[0671] Required Hardware and Software

[0672] The system uses a common web browser, server, artificial intelligence model, and emotion engine. Specifically, it uses the following hardware and software:

[0673] User device: A computer, smartphone, tablet, etc. that runs a web browser

[0674] Server: Physical server or cloud service for data processing and storage

[0675] Artificial intelligence models: Deep learning frameworks such as TensorFlow

[0676] Emotion engine: AWS Amazon Rekognition and Emotion API

[0677] System Program Processing

[0678] The system performs a process that includes the following major steps:

[0679] 1. User image upload:

[0680] A user logs into the system through a web browser and uploads an image of the product or part for which they want to receive a quote. The user presses the upload button and selects the image file.

[0681] 2. Receiving and temporarily storing image data:

[0682] The device sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check.

[0683] 3. Image Analysis:

[0684] The server analyzes the image using an artificial intelligence model such as TensorFlow to extract feature data such as pattern, size, and shape, and the analysis results are returned to the server as structured data.

[0685] 4. Calculating a rough estimate:

[0686] The server then uses the extracted feature data to launch an in-house cost calculation engine to calculate a rough estimate, taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0687] 5. Providing a rough estimate:

[0688] The server transmits the calculated rough estimate to the user's terminal, where the user can view the estimate.

[0689] 6. Request an accurate quote:

[0690] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then confirms the details with the partner company and confirms the final production cost and delivery date.

[0691] 7. Providing a final quote:

[0692] The server sends the final quotation information received from the supplier to the user's terminal, where the user can confirm the final quotation and request production.

[0693] 8. Emotion recognition and optimization:

[0694] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. Based on the emotional data recognized by the emotion engine, the server automatically provides appropriate support and information.

[0695] Specific examples

[0696] For example, if a user wants to get a quote for a new electronic component, the system operates as follows:

[0697] 1. The user selects an image file of an electronic component (JPEG format, size 1.5MB) and presses the upload button.

[0698] 2. The device sends the selected image to the server as an HTTP POST request.

[0699] 3. The server receives the image, checks the format and size, and temporarily stores it.

[0700] 4. The server uses a TensorFlow model to analyze patterns, size, and shape from the image.

[0701] 5. Based on the analysis results, the cost calculation engine calculates material and processing costs.

[0702] 6. The server sends a rough estimate to the device, where the user can confirm it.

[0703] 7. The user presses the "Request an accurate quote" button.

[0704] 8. The server requests detailed estimates from the vendors and obtains the final estimate information.

[0705] 9. The server provides the final quote to the user.

[0706] 10. If the user shows signs of anxiety, the emotion engine will recognize this and display additional support information.

[0707] Prompt Sentence Examples

[0708] "Upload images of your new electronic components and begin the process of receiving a detailed quote."

[0709] In this way, the present invention aims to provide fast and accurate product production quotes and enhance the user experience.

[0710] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0711] Step 1: User uploads an image

[0712] The user logs in to the system and accesses the image upload screen. The user selects the image file to be quoted and presses the upload button. At this time, the image selected by the user is sent via a browser form. The input is the image file selected by the user, and the output is the image data sent to the server.

[0713] Step 2: Receiving and temporarily saving image data

[0714] The terminal sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check. Specifically, it verifies that the image format (e.g., JPEG, PNG) and size (e.g., 2MB or less) are appropriate. The input is the image data included in the HTTP POST request, and the output is the validated image data.

[0715] Step 3: Image analysis

[0716] The server passes the temporarily stored image data to an artificial intelligence model (e.g., TensorFlow). The model uses an image processing algorithm to extract feature data such as pattern, size, and shape. For example, it uses the model.predict(image data) method. The input is the validated image data, and the output is a structured list of feature data.

[0717] Step 4: Calculate a rough estimate

[0718] The server uses the extracted feature data to launch a cost calculation engine. This engine calculates a rough estimate by taking into account the cost of required materials, processing costs, labor hours, etc. For example, it calculates the cost by calling a function called calculate_cost(feature data). The input is a structured list of feature data, and the output is a numerical estimate.

[0719] Step 5: Provide a rough estimate

[0720] The server sends the calculated rough estimate data to the terminal. This communication is implemented as an HTTP response and displayed in the user's browser. The input is the numerical data of the rough estimate, and the output is the estimate information displayed in the browser.

[0721] Step 6: Request an accurate quote

[0722] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate. The device sends this request as an HTTP POST request to the server. The server receives this request, checks the details with the partner vendor, and confirms the final production cost and delivery date. The input is the user's request data, and the output is the final estimate information from the vendor.

[0723] Step 7: Providing a final quote

[0724] The server provides the final quote information received from the supplier to the user. This communication is also implemented as an HTTP response. The input is the final quote information, and the output is the final quote information displayed in the browser.

[0725] Step 8: Emotion recognition and optimization

[0726] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. When the emotion engine recognizes an emotion, the system provides appropriate support and information corresponding to that emotion. For example, if the user shows an anxious expression, the system provides additional support information. The input is the user's facial expression and voice data, and the output is information on countermeasures.

[0727] (Application example 2)

[0728] 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."

[0729] In modern manufacturing, fast and accurate product and component quotations are essential for efficient production management and cost reduction. However, existing systems do not consider user emotions during the quotation generation process using image data, resulting in a suboptimal user experience. Furthermore, more advanced analysis systems are needed to identify product deterioration and defects, as well as recognize the emotions of factory staff.

[0730] 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 a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and an emotion engine for acquiring emotion data and recognizing the user's emotion. This not only enables quick and accurate product estimates but also enables optimal responses that take user emotions into consideration. Furthermore, by checking products in the factory and monitoring staff emotions, the efficiency and quality of the entire manufacturing process can be improved.

[0731] "Means for users to upload images" means a function or interface that allows users to send image data to the system.

[0732] The "means for receiving and temporarily storing the image" refers to a module or device that has the function of temporarily storing image data sent from a user and further verifying the quality and format of the data.

[0733] "Artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape" refers to a software model that automatically analyzes and extracts features related to products and parts from image data using machine learning algorithms.

[0734] "Cost calculation engine that calculates a rough estimate based on the extracted feature data" refers to an algorithm and software engine that uses the extracted feature data to roughly calculate the manufacturing cost of a product.

[0735] The "means for providing the rough estimate to the user" refers to a function or interface for visually or audibly notifying the user of the calculated rough estimate information.

[0736] "Emotion engine for acquiring emotion data and recognizing a user's emotion" means an analytical algorithm and software engine for analyzing facial expressions, voice, and text data acquired from a user and identifying the user's emotional state.

[0737] This invention relates to a "robot assistant" system that checks products and calculates estimates in factories. The robot, equipped with smart glasses, mainly recognizes product images in real time, calculates estimates, and analyzes the emotions of factory staff to optimize work efficiency.

[0738] Hardware and software used

[0739] Hardware: Smart glasses, patrol robots

[0740] software:

[0741] Image analysis model (artificial intelligence model using TensorFlow / Keras)

[0742] Emotion recognition model (FER, MTCNN)

[0743] REST API (cost calculation engine)

[0744] System Flow

[0745] 1. Image upload and analysis:

[0746] The server receives the image data captured by the robot through the smart glasses and temporarily stores it.

[0747] This image data is then passed to an artificial intelligence model to extract feature data such as pattern, size, and shape.

[0748] 2. Acquiring and analyzing emotion data:

[0749] The server receives and temporarily stores facial images of factory staff taken with the smart glasses.

[0750] The emotional recognition model (FER) is used to analyze the emotional state of staff and generate the recognized emotions and their scores.

[0751] 3. Calculating a rough estimate:

[0752] The server sends the feature data obtained from the artificial intelligence model to the cost calculation engine.

[0753] The cost calculation engine calculates a rough estimate based on the acquired data, taking into account factors such as the cost of necessary materials, processing costs, and labor hours.

[0754] 4. Providing rough estimates and sentiment data:

[0755] The server transmits the calculated rough estimate data and the analyzed emotion data to the robot.

[0756] The robot provides this data to factory staff through display devices (display and audio output).

[0757] 5. Optimizing the user experience:

[0758] The server uses the emotion data to provide countermeasures to optimize the user experience, for example, providing additional support or detailed explanations if the user shows signs of dissatisfaction.

[0759] Specific examples

[0760] For example, a factory robot patrols an electronic parts production line, photographing any deterioration or defects in the product with smart glasses and analyzing the images. Based on the detection results, a cost calculation engine generates estimates and provides a list of defective products in real time. Furthermore, the system uses emotion analysis to observe the stress and fatigue of line workers, optimizing the speed of work and the timing of breaks.

[0761] Prompt Sentence Examples

[0762] "Please analyze this image (path_to_product_image.jpg), extract the product feature data, and get a rough estimate. Also, please analyze the emotion of the person in the image and provide the recognized emotion and its score."

[0763] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0764] Step 1:

[0765] The user takes an image using a means for uploading images, and the robot sends the image data of the product taken through the smart glasses to a server. The server temporarily stores the received image data. In this process, the smart glasses act as an input device, and the server acts as a data storage device that temporarily stores the image data.

[0766] Step 2:

[0767] The server performs a validation check on the saved image data. Here, it checks to make sure that the image data format (JPEG, PNG, etc.), resolution, and size are appropriate. Image data that passes the validation check is sent to the next analysis step. If validation fails, an error message is output.

[0768] Step 3:

[0769] The server sends the image data that has passed validation to an artificial intelligence model for image analysis. The image analysis model (a model using TensorFlow / Keras) extracts feature data such as pattern, size, and shape from the image data. This process takes the image data as input and outputs feature data. Specifically, a Convolutional Neural Network (CNN) is used to identify specific parts of the image and extract characteristics as numerical data.

[0770] Step 4:

[0771] The server uses the extracted feature data to send data to a cost calculation engine. The cost calculation engine calculates a rough estimate based on the feature data, taking into account factors such as material costs, processing costs, and labor hours. The input here is the feature data, and the output is a rough estimate. The data is sent to an external cost calculation service using a REST API, and the results are obtained.

[0772] Step 5:

[0773] The server sends the calculated rough estimate data to the robot, which then displays the rough estimate to the factory staff through smart glasses. This process uses the estimate data as input and outputs the results using a display and audio output.

[0774] Step 6:

[0775] The server receives and temporarily stores facial images of factory staff taken with smart glasses. The received image data is sent to the emotion recognition model (FER) for analysis. The emotion recognition model analyzes facial expressions from the images, recognizes the emotional state, and generates corresponding data. In this process, the facial expression image is input and the recognized emotional data is output.

[0776] Step 7:

[0777] The server optimizes the user experience based on the emotional data obtained from the emotion recognition model. If the emotional data indicates dissatisfaction or fatigue, the system generates countermeasures offering additional support or detailed explanations, which are then provided to the factory staff via the robot. Specifically, this could include displaying detailed operating instructions or playing a voice message encouraging the staff to take a break.

[0778] This series of processes enables quick and accurate product estimates and optimal responses that take user feelings into consideration.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] [Third embodiment]

[0783] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0784] 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.

[0785] 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).

[0786] 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.

[0787] 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.

[0788] 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).

[0789] 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. 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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."

[0795] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyzes the images, generates an estimate, and, if necessary, requests a more accurate estimate from a vendor.

[0796] User-uploaded images

[0797] After logging in to the system, the user uploads the image data for which they wish to make a quote. The user selects the image file from the upload screen and presses the upload button.

[0798] Receiving and temporarily storing image data

[0799] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0800] Image analysis

[0801] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0802] Calculating a rough estimate

[0803] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0804] Providing a rough estimate

[0805] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0806] Request an accurate quote

[0807] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0808] Providing a final quote

[0809] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0810] Specific examples

[0811] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0812] In this way, the present invention provides a system that provides fast and accurate product manufacturing quotes, streamlining the manufacturing process.

[0813] The processing flow will be explained below.

[0814] Step 1:

[0815] A user logs in to the system and accesses the image upload screen.

[0816] Step 2:

[0817] The user selects the image file to be quoted and presses the upload button.

[0818] Step 3:

[0819] The terminal transmits the selected image file to the server.

[0820] Step 4:

[0821] The server temporarily stores the received image data.

[0822] Step 5:

[0823] The server performs validation checks on the image data (checking file format and size).

[0824] Step 6:

[0825] The server passes the temporarily stored image data to the artificial intelligence model.

[0826] Step 7:

[0827] The artificial intelligence model uses image processing algorithms to extract feature data such as pattern, size, and shape.

[0828] Step 8:

[0829] The AI ​​model structures the extracted feature data and returns it to the server.

[0830] Step 9:

[0831] The server inputs the feature data into the cost calculation engine.

[0832] Step 10:

[0833] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[0834] Step 11:

[0835] The server transmits the calculated rough estimate data to the terminal.

[0836] Step 12:

[0837] The terminal displays a rough estimate to the user.

[0838] Step 13:

[0839] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate.

[0840] Step 14:

[0841] The terminal sends a precise quote request to the server.

[0842] Step 15:

[0843] The server receives an accurate quotation request and makes an inquiry to partner companies.

[0844] Step 16:

[0845] The partner company checks the actual production conditions, costs, and delivery dates and returns them to the server.

[0846] Step 17:

[0847] The server returns the final quote information received from the vendor to the user.

[0848] Step 18:

[0849] The terminal displays the final quote information to the user.

[0850] Example 1

[0851] 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."

[0852] Conventional rough estimate systems have an inefficient process for extracting feature data from images uploaded by users and providing accurate estimates based on that data. In particular, the lack of validation checks for image format and size often resulted in inappropriate images being processed, resulting in incorrect estimates. Another issue is the speed with which an accurate estimate can be requested from a contractor. There is a need to solve these problems and provide fast, accurate estimates.

[0853] 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.

[0854] In this invention, the server includes means for a user to upload an image, means for receiving and temporarily storing the image, means for validating the format and size of the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, and means for providing the rough estimate to the user.

[0855] This ensures that the format and size of images uploaded by users are checked correctly, enabling the extraction of feature data and the calculation of rough estimates quickly and accurately using appropriate image data. It also makes it possible to efficiently request accurate estimates from vendors, improving the accuracy and efficiency of the entire system.

[0856] "User" means an individual or company that uses the system to upload images or request quotes.

[0857] A "server" is a computer system that receives, temporarily stores, analyzes, and calculates and provides estimates for image data sent by users.

[0858] "Terminal" means the device (e.g., computer, smartphone) used by a User to access the System and upload Images.

[0859] "Image data" is digital data that includes image information of the product or part that is the subject of the quotation.

[0860] A "validation check" is a process that verifies that the format and size of the received image data are appropriate.

[0861] An "artificial intelligence model" is a machine learning algorithm that analyzes image data and extracts feature data such as pattern, size, and shape.

[0862] "Feature data" refers to data that includes information such as the pattern, size, and shape of a product or part extracted through image analysis.

[0863] The "cost calculation engine" is a software module that calculates a rough estimate based on characteristic data, taking into account factors such as material costs, processing costs, and labor hours.

[0864] A "rough estimate" is a preliminary calculation result of the manufacturing cost of a product or part calculated based on the extracted feature data.

[0865] "Contractor" is the company or individual who confirms and provides the final production cost and delivery date.

[0866] An "accurate estimate" is an estimate that includes the final production cost and delivery date after confirmation from the contractor.

[0867] "Past estimate information" is historical information about estimates made based on previously analyzed image data.

[0868] "Product handling data" is detailed data on products and parts that the system has analyzed and handled in the past.

[0869] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyze the images, generate an estimate, and, if necessary, request a more accurate estimate from a vendor.

[0870] The system consists of three main elements: users, terminals, and servers. Users access the system using terminals and upload images of the items they wish to quote. Terminals are devices that can connect to the Internet, such as PCs or smartphones. The server is a computer system that receives the uploaded image data, analyzes it, and provides quotes.

[0871] Users log in to the system and use the interface to upload image data for quotation. They click the "Upload Image" button on the interface, select the image file, and then click the "Upload" button to send the image to the server.

[0872] The device sends the image file selected by the user to the server, which temporarily stores the image data. At the same time, a validation check is performed to confirm the file format (e.g., JPEG, PNG) and size (e.g., up to 5MB). If an image file of an inappropriate format or size is uploaded, the server returns an error message to the user.

[0873] The server passes the temporarily stored image data to an artificial intelligence (AI) model. This AI model (e.g., ResNet or YOLO) uses an image processing algorithm to extract feature data such as the pattern, size, and shape of the product or part. The AI ​​model then structures the feature data and returns it to the server.

[0874] Next, the server launches a cost calculation engine based on the feature data obtained from the AI ​​model. The cost calculation engine calculates a rough estimate taking into account factors such as material costs, processing costs, and labor hours. Specifically, it retrieves the necessary information from the database and performs the appropriate calculations.

[0875] Once the rough estimate is calculated, the server sends the data to the terminal. The user can check the rough estimate data through the terminal. If the user is satisfied with the estimate, he / she clicks the "Request an accurate estimate" button, and the terminal sends the request to the server. The server then checks the details with the partner company and provides the final estimate information from the company to the user.

[0876] For example, if a user wants to get a quote for a new electronic part, they first log in to the system and upload an image of the part. The server receives the image, temporarily stores it, and validates it. Next, an AI model analyzes the image and extracts feature data. Based on this feature data, a cost calculation engine calculates material and processing costs and provides a rough estimate. If the user is satisfied with this rough estimate, they can request a more accurate quote, and the server will request detailed confirmation from the supplier. The final quote information is then provided to the user.

[0877] Examples of prompts include:

[0878] "I would like to get a quote for a new electronic component. Please analyze the image below and extract features. Identify the component's pattern, size, and shape from this image and provide a rough estimate based on that."

[0879] In this way, the present invention provides fast and accurate product manufacturing quotes and streamlines the manufacturing process.

[0880] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0881] Step 1:

[0882] The user logs in to the system and uploads an image of the item to be quoted.

[0883] Input: User login information and image file

[0884] Operation: The user enters their ID and password on the system login screen and moves to the upload screen. The user clicks the "Upload Image" button and selects the image file to be quoted. Then, they click the "Upload" button to send the image.

[0885] Output: The selected image file is sent from the device to the server.

[0886] Step 2:

[0887] The terminal transmits the image file selected by the user to the server.

[0888] Input: An image file selected by the user and saved on the device

[0889] Operation: When the device sends the image file selected by the user to the server, it attaches basic information such as the data format and file size. The server then obtains the metadata associated with the image data.

[0890] Output: The image files and their metadata are received and temporarily stored on the server.

[0891] Step 3:

[0892] The server performs a validation check on the received image data and temporarily stores it.

[0893] Input: Image file sent from the device

[0894] Operation: The server checks whether the image file format (e.g., JPEG, PNG) and size (e.g., maximum 5MB) are valid. If validation is successful, the image is saved in a temporary folder. On the other hand, if the image format or size is inappropriate, an error message is generated and sent to the terminal.

[0895] Output: Image files that pass validation are temporarily saved, and if validation fails, an error message is sent to the terminal.

[0896] Step 4:

[0897] The server passes image data that has been successfully validated to the artificial intelligence model.

[0898] Input: Image file that has been successfully validated

[0899] How it works: The server inputs the saved image files into an AI model (e.g., ResNet or YOLO). The AI ​​model uses machine learning algorithms to extract feature data such as patterns, size, and shape from the image data.

[0900] Output: The feature data extracted by the AI ​​model is returned to the server.

[0901] Step 5:

[0902] The server uses a cost calculation engine to calculate a rough estimate based on the feature data obtained from the AI ​​model.

[0903] Input: Feature data returned from the AI ​​model

[0904] Operation: The server runs a cost calculation engine based on the feature data. The cost calculation engine extracts necessary information such as material costs, processing costs, and labor hours from the database and uses this data to calculate a rough estimate.

[0905] Output: The calculated rough estimate data is saved on the server.

[0906] Step 6:

[0907] The server transmits the calculated rough estimate data to the terminal.

[0908] Input: Calculated rough estimate data

[0909] Operation: The server sends the rough estimate data to the terminal so that the user can check it. The user can check the estimate details and calculation results on the terminal.

[0910] Output: The estimated data is displayed on the terminal.

[0911] Step 7:

[0912] If the user is satisfied with the rough estimate, he or she requests a more accurate estimate.

[0913] Input: User requests accurate quote

[0914] How it works: When the user clicks the "Request an accurate quote" button, the request is sent from the device to the server. The server then requests detailed confirmation from partner vendors. Specifically, it sends the extracted feature data and the quotation conditions to the vendors.

[0915] Output: The server sends a request for an accurate quote to the vendor.

[0916] Step 8:

[0917] The server provides the user with the final quote information received from the vendor.

[0918] Input: Final quote information from vendor

[0919] How it works: The vendor sends information about the final production cost and delivery date to the server. The server temporarily stores this information and notifies the user via their device. The user then checks the final estimate on their device and decides whether to request production based on that information.

[0920] Output: The final quote information is displayed on the terminal and notified to the user.

[0921] (Application example 1)

[0922] 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."

[0923] In modern manufacturing, there is a need to quickly and accurately estimate the production costs of parts and products. However, traditional methods are time-consuming and labor-intensive. Furthermore, it is difficult to quickly calculate costs on-site, which hinders rapid decision-making. This hinders the efficiency of the production process and limits productivity improvements. Furthermore, the time required to confirm accurate estimates from contractors based on rough estimates is also required, so further efficiency improvements are required.

[0924] 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.

[0925] In this invention, the server includes a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and a means for taking images of parts or products using a smartphone and transmitting the images to the server. This enables rapid cost calculation on-site and improves the efficiency of the production process. Furthermore, requesting an accurate estimate from a contractor based on the rough estimate enables rapid decision-making and contributes to improved productivity.

[0926] "User" refers to a person who uses the system to upload images and request a quote.

[0927] "Image" refers to a data file that visually records the shape, size, and other characteristics of a part or product.

[0928] "Upload" refers to the act of a user sending image data they have to a server.

[0929] A "means" refers to a combination of hardware and software for achieving a specific function.

[0930] "Receiving" refers to the process in which the server captures image data sent by the user.

[0931] "Temporarily saving" refers to the operation of saving received image data for a certain period of time.

[0932] "Analysis" refers to the process by which the server uses an artificial intelligence model to extract feature data from image data.

[0933] "Feature data" refers to information such as pattern, size, and shape extracted from an image.

[0934] An "artificial intelligence model" refers to an algorithm that extracts feature data using technologies such as machine learning and deep learning.

[0935] "Rough estimate" refers to the result of calculating a rough production cost based on feature data.

[0936] A "cost calculation engine" refers to a system that calculates a rough estimate based on extracted feature data, taking into account material costs, processing costs, labor hours, etc.

[0937] "Means for providing" refers to the process of displaying or notifying the calculated rough estimate to the user.

[0938] "Smartphone" refers to a portable information terminal that has Internet connectivity and is capable of taking and sending images.

[0939] "Server" refers to a computer system that receives image data from users, analyzes it, and calculates and provides a rough estimate.

[0940] This invention provides a system that allows users to quickly obtain a rough estimate by sending images taken with their smartphone to a server, thereby significantly improving the efficiency of the quotation process for parts and products in the manufacturing industry.

[0941] In the basic system configuration, users use a smartphone application to take pictures of parts or products and upload them to a server. This application includes functions for uploading images, communicating with the server, and displaying quotation results.

[0942] The server receives images sent by users and temporarily stores them. The stored images are first subjected to a validation check, and any images that are deemed inappropriate are requested to be re-uploaded. Images that pass validation are then passed to an artificial intelligence model, which extracts feature data such as pattern, size, and shape. The artificial intelligence model used here uses image analysis technologies such as TensorFlow and OpenCV.

[0943] Once the feature data is extracted, a cost calculation engine uses it to calculate a rough estimate. The cost calculation engine takes into account factors such as material costs, processing costs, and labor hours to generate an estimate. This result is then sent back to the user's smartphone via the server and displayed.

[0944] Furthermore, if the user is satisfied with the rough estimate, they can request a more accurate estimate from the supplier. Based on the user's request, the server will confirm the details with the supplier and confirm the final production cost and delivery date. This allows the user to receive a confirmed estimate and request production based on it.

[0945] For example, when a worker wants to manufacture a new part, he or she takes a picture of the part with their smartphone and sends it through the application. Within seconds, a rough estimate is displayed. The user can then decide to start production based on this estimate. This process allows for fast and efficient calculation of production costs.

[0946] Example prompts for generative AI models

[0947] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0948] Image file: [uploaded image]

[0949] Parameters: size, shape, weight

[0950] Estimate requirements: material costs, processing costs, labor hours

[0951] The above is a mode for carrying out the invention, and the specific operating procedures can be modified in various ways, thereby enabling the invention to be adapted to different manufacturing environments without losing its essence.

[0952] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0953] Step 1:

[0954] The user takes a picture of a part or product using a smartphone. The captured image is saved in the smartphone's application. The input is image data obtained by the smartphone's camera, and the output is an image file temporarily saved within the application. Specifically, the user taps the camera button on the smartphone to take a picture.

[0955] Step 2:

[0956] The user operates the application to take a picture and upload it to the server. The input is the taken image file, and the output is the image data sent to the server. Specifically, the user taps the "Upload" button in the application to send the image to the server.

[0957] Step 3:

[0958] The server temporarily stores the images it receives. The input is the image data sent by the user, and the output is the image file stored in temporary storage on the server. Specifically, the server stores the image data in a specified folder and performs validation checks on the file format and size.

[0959] Step 4:

[0960] The server passes the temporarily stored images to an artificial intelligence model for image analysis. The input is the image data stored on the server, and the output is feature data such as pattern, size, and shape. Specifically, the server calls an AI model (such as TensorFlow or OpenCV), analyzes the image data, and extracts feature data.

[0961] Step 5:

[0962] The server launches a cost calculation engine based on the extracted feature data to calculate a rough estimate. The input is the feature data, and the output is the rough estimate data. Specifically, the server runs a cost calculation algorithm to evaluate material costs, processing costs, labor hours, etc. to generate an estimate.

[0963] Step 6:

[0964] The server sends the calculated rough estimate data to the user's smartphone. The input is the rough estimate data, and the output is the estimate information displayed on the user's smartphone. Specifically, the server generates an HTTP response and sends the estimate data to the user application.

[0965] Step 7:

[0966] If the user is satisfied with the rough estimate, the application requests confirmation of the exact estimate from the supplier. The input is a formal quote request based on the rough estimate, and the output is the final quote information returned by the supplier. Specifically, the user taps the "Request a formal quote" button in the application, and the entered data is sent to the supplier via the server.

[0967] Step 8:

[0968] The server provides the user with the final quote information received from the vendor. The input is the final quote data from the vendor, and the output is the final quote information displayed on the user's smartphone. Specifically, the server analyzes the data received from the vendor and sends it to the user application.

[0969] Example prompts for generative AI models

[0970] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[0971] Image file: [uploaded image]

[0972] Parameters: size, shape, weight

[0973] Estimate requirements: material costs, processing costs, labor hours

[0974] 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.

[0975] The present invention is a system that uses image data and emotion data to quickly provide rough estimates for products and parts, optimizing the user experience. The system allows users to upload images, analyzes the images to generate estimates, and, if necessary, requests accurate estimates from vendors, recognizing the user's emotions to optimize the response.

[0976] User-uploaded images

[0977] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required and presses the upload button.

[0978] Receiving and temporarily storing image data

[0979] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[0980] Image analysis

[0981] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[0982] Calculating a rough estimate

[0983] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[0984] Providing a rough estimate

[0985] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[0986] Request an accurate quote

[0987] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[0988] Providing a final quote

[0989] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[0990] Emotion recognition and optimization

[0991] The server is equipped with an emotion engine that recognizes the user's emotions using facial, voice, and text analysis. Based on the emotion data recognized by the emotion engine, the system provides countermeasures to optimize the user experience. For example, if the user shows a dissatisfied expression, the system will provide additional support and detailed explanations.

[0992] Specific examples

[0993] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[0994] Furthermore, if a user expresses doubt or anxiety while uploading an image, the emotion engine will recognize that emotion and the server will automatically provide the user with appropriate advice and support.

[0995] In this way, the present invention provides fast and accurate product production quotes throughout the system, optimizing the user experience.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required.

[0999] Step 2:

[1000] The user presses the upload button. The device sends the selected image file and the user's facial expression data (if using the camera) to the server.

[1001] Step 3:

[1002] The server temporarily stores the received image data and facial expression data.

[1003] Step 4:

[1004] The server performs a validation check on the image data, checking the file format and size to ensure it is in the correct format.

[1005] Step 5:

[1006] The server passes the temporarily stored image data to the artificial intelligence model.

[1007] Step 6:

[1008] The AI ​​model uses image processing algorithms to extract feature data such as pattern, size, shape, etc. The extracted feature data is structured and returned to the server.

[1009] Step 7:

[1010] The server inputs the feature data into the cost calculation engine.

[1011] Step 8:

[1012] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[1013] Step 9:

[1014] The server transmits the calculated rough estimate data to the terminal.

[1015] Step 10:

[1016] The terminal displays the estimated estimate data to the user.

[1017] Step 11:

[1018] If the user is satisfied with the rough estimate, he / she presses a button to request an accurate estimate, and the terminal sends data including a request for an accurate estimate to the server.

[1019] Step 12:

[1020] The server receives an accurate quotation request and makes an inquiry to partner companies.

[1021] Step 13:

[1022] The partner company checks the actual production conditions, costs, and delivery dates and sends them back to the server.

[1023] Step 14:

[1024] The server provides the user with the final quote information received from the vendor.

[1025] Step 15:

[1026] The terminal displays the final quote information to the user.

[1027] Step 16:

[1028] The emotion engine installed on the server analyzes the received user facial expression data, voice data, and text input data to recognize the user's emotions.

[1029] Step 17:

[1030] The server uses the emotion data generated by the emotion engine to determine countermeasures to optimize the user experience, for example, automatically providing additional support or detailed explanations when it recognizes a user's dissatisfaction.

[1031] Step 18:

[1032] The device will display solutions to the user, who can then seek additional support if needed.

[1033] The above is the specific flow of the process in the present invention. This system allows users to receive fast and accurate product manufacturing quotes, and provides an optimal user experience through emotion recognition.

[1034] Example 2

[1035] 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."

[1036] Conventional quotation systems require time-consuming image analysis, resulting in low accuracy of the estimates users receive. Furthermore, they lacked sufficient mechanisms for improving the user experience, leaving users feeling dissatisfied and anxious. Furthermore, they lacked the technology to recognize user emotions and automatically provide appropriate responses.

[1037] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to upload an image, means for receiving and temporarily saving the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, means for providing the rough estimate to the user, an emotion engine for recognizing emotion data by analyzing the user's facial expression or voice, and response means for providing a response based on the emotion data recognized by the emotion engine. This makes it possible to provide a quick and accurate estimate and provide optimal support according to the user's emotions.

[1038] "User" refers to a user who uses this system to upload images and receive estimates and support.

[1039] "Means for uploading images" refers to functionality including interfaces and programs that users use to send image files to the system.

[1040] The "means for receiving and temporarily storing" refers to a function used by the server to receive image data sent from the user and temporarily store it.

[1041] "Artificial intelligence model for analyzing images and extracting feature data such as pattern, size, and shape" refers to a model that includes algorithms and programs that analyze image data, identify the characteristics of the object, and digitize them.

[1042] "Cost calculation engine for calculating a rough estimate" refers to an algorithm or program for calculating a rough estimate based on extracted feature data, taking into account the necessary material costs, processing costs, labor hours, etc.

[1043] "Means for providing a quote to a user" refers to the functionality used to display or transmit the calculated rough quote to the user's terminal.

[1044] An "emotion engine" refers to an algorithm or program that analyzes a user's facial expressions, voice, text, etc. and recognizes their emotions.

[1045] "Response means" refers to a function for providing appropriate support and information to users based on the emotional data recognized by the emotion engine.

[1046] "Vendor" refers to an external service provider or manufacturer that works with the server to provide accurate quotes and production.

[1047] "Fine-tuning" refers to the process by which artificial intelligence models are optimized based on historical usage and product data.

[1048] The present invention is a system that uses image data and emotion data to provide rapid product or part quotes and optimize the user experience. The system is implemented in the following manner.

[1049] The overall system configuration involves users uploading images, which the server analyzes to generate quotes, and the system also recognizes the user's emotions and optimizes responses.

[1050] Required Hardware and Software

[1051] The system uses a common web browser, server, artificial intelligence model, and emotion engine. Specifically, it uses the following hardware and software:

[1052] User device: A computer, smartphone, tablet, etc. that runs a web browser

[1053] Server: Physical server or cloud service for data processing and storage

[1054] Artificial intelligence models: Deep learning frameworks such as TensorFlow

[1055] Emotion engine: AWS Amazon Rekognition and Emotion API

[1056] System Program Processing

[1057] The system performs a process that includes the following major steps:

[1058] 1. User image upload:

[1059] A user logs into the system through a web browser and uploads an image of the product or part for which they want to receive a quote. The user presses the upload button and selects the image file.

[1060] 2. Receiving and temporarily storing image data:

[1061] The device sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check.

[1062] 3. Image Analysis:

[1063] The server analyzes the image using an artificial intelligence model such as TensorFlow to extract feature data such as pattern, size, and shape, and the analysis results are returned to the server as structured data.

[1064] 4. Calculating a rough estimate:

[1065] The server then uses the extracted feature data to launch an in-house cost calculation engine to calculate a rough estimate, taking into account factors such as the cost of materials, processing costs, and labor hours required.

[1066] 5. Providing a rough estimate:

[1067] The server transmits the calculated rough estimate to the user's terminal, where the user can view the estimate.

[1068] 6. Request an accurate quote:

[1069] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then confirms the details with the partner company and confirms the final production cost and delivery date.

[1070] 7. Providing a final quote:

[1071] The server sends the final quotation information received from the supplier to the user's terminal, where the user can confirm the final quotation and request production.

[1072] 8. Emotion recognition and optimization:

[1073] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. Based on the emotional data recognized by the emotion engine, the server automatically provides appropriate support and information.

[1074] Specific examples

[1075] For example, if a user wants to get a quote for a new electronic component, the system operates as follows:

[1076] 1. The user selects an image file of an electronic component (JPEG format, size 1.5MB) and presses the upload button.

[1077] 2. The device sends the selected image to the server as an HTTP POST request.

[1078] 3. The server receives the image, checks the format and size, and temporarily stores it.

[1079] 4. The server uses a TensorFlow model to analyze patterns, size, and shape from the image.

[1080] 5. Based on the analysis results, the cost calculation engine calculates material and processing costs.

[1081] 6. The server sends a rough estimate to the device, where the user can confirm it.

[1082] 7. The user presses the "Request an accurate quote" button.

[1083] 8. The server requests detailed estimates from the vendors and obtains the final estimate information.

[1084] 9. The server provides the final quote to the user.

[1085] 10. If the user shows signs of anxiety, the emotion engine will recognize this and display additional support information.

[1086] Prompt Sentence Examples

[1087] "Upload images of your new electronic components and begin the process of receiving a detailed quote."

[1088] In this way, the present invention aims to provide fast and accurate product production quotes and enhance the user experience.

[1089] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1090] Step 1: User uploads an image

[1091] The user logs in to the system and accesses the image upload screen. The user selects the image file to be quoted and presses the upload button. At this time, the image selected by the user is sent via a browser form. The input is the image file selected by the user, and the output is the image data sent to the server.

[1092] Step 2: Receiving and temporarily saving image data

[1093] The terminal sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check. Specifically, it verifies that the image format (e.g., JPEG, PNG) and size (e.g., 2MB or less) are appropriate. The input is the image data included in the HTTP POST request, and the output is the validated image data.

[1094] Step 3: Image analysis

[1095] The server passes the temporarily stored image data to an artificial intelligence model (e.g., TensorFlow). The model uses an image processing algorithm to extract feature data such as pattern, size, and shape. For example, it uses the model.predict(image data) method. The input is the validated image data, and the output is a structured list of feature data.

[1096] Step 4: Calculate a rough estimate

[1097] The server uses the extracted feature data to launch a cost calculation engine. This engine calculates a rough estimate by taking into account the cost of required materials, processing costs, labor hours, etc. For example, it calculates the cost by calling a function called calculate_cost(feature data). The input is a structured list of feature data, and the output is a numerical estimate.

[1098] Step 5: Provide a rough estimate

[1099] The server sends the calculated rough estimate data to the terminal. This communication is implemented as an HTTP response and displayed in the user's browser. The input is the numerical data of the rough estimate, and the output is the estimate information displayed in the browser.

[1100] Step 6: Request an accurate quote

[1101] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate. The device sends this request as an HTTP POST request to the server. The server receives this request, checks the details with the partner vendor, and confirms the final production cost and delivery date. The input is the user's request data, and the output is the final estimate information from the vendor.

[1102] Step 7: Providing a final quote

[1103] The server provides the final quote information received from the supplier to the user. This communication is also implemented as an HTTP response. The input is the final quote information, and the output is the final quote information displayed in the browser.

[1104] Step 8: Emotion recognition and optimization

[1105] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. When the emotion engine recognizes an emotion, the system provides appropriate support and information corresponding to that emotion. For example, if the user shows an anxious expression, the system provides additional support information. The input is the user's facial expression and voice data, and the output is information on countermeasures.

[1106] (Application example 2)

[1107] 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."

[1108] In modern manufacturing, fast and accurate product and component quotations are essential for efficient production management and cost reduction. However, existing systems do not consider user emotions during the quotation generation process using image data, resulting in a suboptimal user experience. Furthermore, more advanced analysis systems are needed to identify product deterioration and defects, as well as recognize the emotions of factory staff.

[1109] 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 a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and an emotion engine for acquiring emotion data and recognizing the user's emotion. This not only enables quick and accurate product estimates but also enables optimal responses that take user emotions into consideration. Furthermore, by checking products in the factory and monitoring staff emotions, the efficiency and quality of the entire manufacturing process can be improved.

[1110] "Means for users to upload images" means a function or interface that allows users to send image data to the system.

[1111] The "means for receiving and temporarily storing the image" refers to a module or device that has the function of temporarily storing image data sent from a user and further verifying the quality and format of the data.

[1112] "Artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape" refers to a software model that automatically analyzes and extracts features related to products and parts from image data using machine learning algorithms.

[1113] "Cost calculation engine that calculates a rough estimate based on the extracted feature data" refers to an algorithm and software engine that uses the extracted feature data to roughly calculate the manufacturing cost of a product.

[1114] The "means for providing the rough estimate to the user" refers to a function or interface for visually or audibly notifying the user of the calculated rough estimate information.

[1115] "Emotion engine for acquiring emotion data and recognizing a user's emotion" means an analytical algorithm and software engine for analyzing facial expressions, voice, and text data acquired from a user and identifying the user's emotional state.

[1116] This invention relates to a "robot assistant" system that checks products and calculates estimates in factories. The robot, equipped with smart glasses, mainly recognizes product images in real time, calculates estimates, and analyzes the emotions of factory staff to optimize work efficiency.

[1117] Hardware and software used

[1118] Hardware: Smart glasses, patrol robots

[1119] software:

[1120] Image analysis model (artificial intelligence model using TensorFlow / Keras)

[1121] Emotion recognition model (FER, MTCNN)

[1122] REST API (cost calculation engine)

[1123] System Flow

[1124] 1. Image upload and analysis:

[1125] The server receives the image data captured by the robot through the smart glasses and temporarily stores it.

[1126] This image data is then passed to an artificial intelligence model to extract feature data such as pattern, size, and shape.

[1127] 2. Acquiring and analyzing emotion data:

[1128] The server receives and temporarily stores facial images of factory staff taken with the smart glasses.

[1129] The emotional recognition model (FER) is used to analyze the emotional state of staff and generate the recognized emotions and their scores.

[1130] 3. Calculating a rough estimate:

[1131] The server sends the feature data obtained from the artificial intelligence model to the cost calculation engine.

[1132] The cost calculation engine calculates a rough estimate based on the acquired data, taking into account factors such as the cost of necessary materials, processing costs, and labor hours.

[1133] 4. Providing rough estimates and sentiment data:

[1134] The server transmits the calculated rough estimate data and the analyzed emotion data to the robot.

[1135] The robot provides this data to factory staff through display devices (display and audio output).

[1136] 5. Optimizing the user experience:

[1137] The server uses the emotion data to provide countermeasures to optimize the user experience, for example, providing additional support or detailed explanations if the user shows signs of dissatisfaction.

[1138] Specific examples

[1139] For example, a factory robot patrols an electronic parts production line, photographing any deterioration or defects in the product with smart glasses and analyzing the images. Based on the detection results, a cost calculation engine generates estimates and provides a list of defective products in real time. Furthermore, the system uses emotion analysis to observe the stress and fatigue of line workers, optimizing the speed of work and the timing of breaks.

[1140] Prompt Sentence Examples

[1141] "Please analyze this image (path_to_product_image.jpg), extract the product feature data, and get a rough estimate. Also, please analyze the emotion of the person in the image and provide the recognized emotion and its score."

[1142] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1143] Step 1:

[1144] The user takes an image using a means for uploading images, and the robot sends the image data of the product taken through the smart glasses to a server. The server temporarily stores the received image data. In this process, the smart glasses act as an input device, and the server acts as a data storage device that temporarily stores the image data.

[1145] Step 2:

[1146] The server performs a validation check on the saved image data. Here, it checks to make sure that the image data format (JPEG, PNG, etc.), resolution, and size are appropriate. Image data that passes the validation check is sent to the next analysis step. If validation fails, an error message is output.

[1147] Step 3:

[1148] The server sends the image data that has passed validation to an artificial intelligence model for image analysis. The image analysis model (a model using TensorFlow / Keras) extracts feature data such as pattern, size, and shape from the image data. This process takes the image data as input and outputs feature data. Specifically, a Convolutional Neural Network (CNN) is used to identify specific parts of the image and extract characteristics as numerical data.

[1149] Step 4:

[1150] The server uses the extracted feature data to send data to a cost calculation engine. The cost calculation engine calculates a rough estimate based on the feature data, taking into account factors such as material costs, processing costs, and labor hours. The input here is the feature data, and the output is a rough estimate. The data is sent to an external cost calculation service using a REST API, and the results are obtained.

[1151] Step 5:

[1152] The server sends the calculated rough estimate data to the robot, which then displays the rough estimate to the factory staff through smart glasses. This process uses the estimate data as input and outputs the results using a display and audio output.

[1153] Step 6:

[1154] The server receives and temporarily stores facial images of factory staff taken with smart glasses. The received image data is sent to the emotion recognition model (FER) for analysis. The emotion recognition model analyzes facial expressions from the images, recognizes the emotional state, and generates corresponding data. In this process, the facial expression image is input and the recognized emotional data is output.

[1155] Step 7:

[1156] The server optimizes the user experience based on the emotional data obtained from the emotion recognition model. If the emotional data indicates dissatisfaction or fatigue, the system generates countermeasures offering additional support or detailed explanations, which are then provided to the factory staff via the robot. Specifically, this could include displaying detailed operating instructions or playing a voice message encouraging the staff to take a break.

[1157] This series of processes enables quick and accurate product estimates and optimal responses that take user feelings into consideration.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] [Fourth embodiment]

[1162] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1163] 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.

[1164] 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).

[1165] 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.

[1166] 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.

[1167] 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).

[1168] 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. 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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."

[1175] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyzes the images, generates an estimate, and, if necessary, requests a more accurate estimate from a vendor.

[1176] User-uploaded images

[1177] After logging in to the system, the user uploads the image data for which they wish to make a quote. The user selects the image file from the upload screen and presses the upload button.

[1178] Receiving and temporarily storing image data

[1179] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[1180] Image analysis

[1181] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[1182] Calculating a rough estimate

[1183] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[1184] Providing a rough estimate

[1185] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[1186] Request an accurate quote

[1187] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[1188] Providing a final quote

[1189] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[1190] Specific examples

[1191] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[1192] In this way, the present invention provides a system that provides fast and accurate product manufacturing quotes, streamlining the manufacturing process.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] A user logs in to the system and accesses the image upload screen.

[1196] Step 2:

[1197] The user selects the image file to be quoted and presses the upload button.

[1198] Step 3:

[1199] The terminal transmits the selected image file to the server.

[1200] Step 4:

[1201] The server temporarily stores the received image data.

[1202] Step 5:

[1203] The server performs validation checks on the image data (checking file format and size).

[1204] Step 6:

[1205] The server passes the temporarily stored image data to the artificial intelligence model.

[1206] Step 7:

[1207] The artificial intelligence model uses image processing algorithms to extract feature data such as pattern, size, and shape.

[1208] Step 8:

[1209] The AI ​​model structures the extracted feature data and returns it to the server.

[1210] Step 9:

[1211] The server inputs the feature data into the cost calculation engine.

[1212] Step 10:

[1213] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[1214] Step 11:

[1215] The server transmits the calculated rough estimate data to the terminal.

[1216] Step 12:

[1217] The terminal displays a rough estimate to the user.

[1218] Step 13:

[1219] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate.

[1220] Step 14:

[1221] The terminal sends a precise quote request to the server.

[1222] Step 15:

[1223] The server receives an accurate quotation request and makes an inquiry to partner companies.

[1224] Step 16:

[1225] The partner company checks the actual production conditions, costs, and delivery dates and returns them to the server.

[1226] Step 17:

[1227] The server returns the final quote information received from the vendor to the user.

[1228] Step 18:

[1229] The terminal displays the final quote information to the user.

[1230] Example 1

[1231] 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."

[1232] Conventional rough estimate systems have an inefficient process for extracting feature data from images uploaded by users and providing accurate estimates based on that data. In particular, the lack of validation checks for image format and size often resulted in inappropriate images being processed, resulting in incorrect estimates. Another issue is the speed with which an accurate estimate can be requested from a contractor. There is a need to solve these problems and provide fast, accurate estimates.

[1233] 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.

[1234] In this invention, the server includes means for a user to upload an image, means for receiving and temporarily storing the image, means for validating the format and size of the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, and means for providing the rough estimate to the user.

[1235] This ensures that the format and size of images uploaded by users are checked correctly, enabling the extraction of feature data and the calculation of rough estimates quickly and accurately using appropriate image data. It also makes it possible to efficiently request accurate estimates from vendors, improving the accuracy and efficiency of the entire system.

[1236] "User" means an individual or company that uses the system to upload images or request quotes.

[1237] A "server" is a computer system that receives, temporarily stores, analyzes, and calculates and provides estimates for image data sent by users.

[1238] "Terminal" means the device (e.g., computer, smartphone) used by a User to access the System and upload Images.

[1239] "Image data" is digital data that includes image information of the product or part that is the subject of the quotation.

[1240] A "validation check" is a process that verifies that the format and size of the received image data are appropriate.

[1241] An "artificial intelligence model" is a machine learning algorithm that analyzes image data and extracts feature data such as pattern, size, and shape.

[1242] "Feature data" refers to data that includes information such as the pattern, size, and shape of a product or part extracted through image analysis.

[1243] The "cost calculation engine" is a software module that calculates a rough estimate based on characteristic data, taking into account factors such as material costs, processing costs, and labor hours.

[1244] A "rough estimate" is a preliminary calculation result of the manufacturing cost of a product or part calculated based on the extracted feature data.

[1245] "Contractor" is the company or individual who confirms and provides the final production cost and delivery date.

[1246] An "accurate estimate" is an estimate that includes the final production cost and delivery date after confirmation from the contractor.

[1247] "Past estimate information" is historical information about estimates made based on previously analyzed image data.

[1248] "Product handling data" is detailed data on products and parts that the system has analyzed and handled in the past.

[1249] The present invention is a system that uses image data to quickly provide a rough estimate for a product or part. The system allows users to upload images, analyze the images, generate an estimate, and, if necessary, request a more accurate estimate from a vendor.

[1250] The system consists of three main elements: users, terminals, and servers. Users access the system using terminals and upload images of the items they wish to quote. Terminals are devices that can connect to the Internet, such as PCs or smartphones. The server is a computer system that receives the uploaded image data, analyzes it, and provides quotes.

[1251] Users log in to the system and use the interface to upload image data for quotation. They click the "Upload Image" button on the interface, select the image file, and then click the "Upload" button to send the image to the server.

[1252] The device sends the image file selected by the user to the server, which temporarily stores the image data. At the same time, a validation check is performed to confirm the file format (e.g., JPEG, PNG) and size (e.g., up to 5MB). If an image file of an inappropriate format or size is uploaded, the server returns an error message to the user.

[1253] The server passes the temporarily stored image data to an artificial intelligence (AI) model. This AI model (e.g., ResNet or YOLO) uses an image processing algorithm to extract feature data such as the pattern, size, and shape of the product or part. The AI ​​model then structures the feature data and returns it to the server.

[1254] Next, the server launches a cost calculation engine based on the feature data obtained from the AI ​​model. The cost calculation engine calculates a rough estimate taking into account factors such as material costs, processing costs, and labor hours. Specifically, it retrieves the necessary information from the database and performs the appropriate calculations.

[1255] Once the rough estimate is calculated, the server sends the data to the terminal. The user can check the rough estimate data through the terminal. If the user is satisfied with the estimate, he / she clicks the "Request an accurate estimate" button, and the terminal sends the request to the server. The server then checks the details with the partner company and provides the final estimate information from the company to the user.

[1256] For example, if a user wants to get a quote for a new electronic part, they first log in to the system and upload an image of the part. The server receives the image, temporarily stores it, and validates it. Next, an AI model analyzes the image and extracts feature data. Based on this feature data, a cost calculation engine calculates material and processing costs and provides a rough estimate. If the user is satisfied with this rough estimate, they can request a more accurate quote, and the server will request detailed confirmation from the supplier. The final quote information is then provided to the user.

[1257] Examples of prompts include:

[1258] "I would like to get a quote for a new electronic component. Please analyze the image below and extract features. Identify the component's pattern, size, and shape from this image and provide a rough estimate based on that."

[1259] In this way, the present invention provides fast and accurate product manufacturing quotes and streamlines the manufacturing process.

[1260] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1261] Step 1:

[1262] The user logs in to the system and uploads an image of the item to be quoted.

[1263] Input: User login information and image file

[1264] Operation: The user enters their ID and password on the system login screen and moves to the upload screen. The user clicks the "Upload Image" button and selects the image file to be quoted. Then, they click the "Upload" button to send the image.

[1265] Output: The selected image file is sent from the device to the server.

[1266] Step 2:

[1267] The terminal transmits the image file selected by the user to the server.

[1268] Input: An image file selected by the user and saved on the device

[1269] Operation: When the device sends the image file selected by the user to the server, it attaches basic information such as the data format and file size. The server then obtains the metadata associated with the image data.

[1270] Output: The image files and their metadata are received and temporarily stored on the server.

[1271] Step 3:

[1272] The server performs a validation check on the received image data and temporarily stores it.

[1273] Input: Image file sent from the device

[1274] Operation: The server checks whether the image file format (e.g., JPEG, PNG) and size (e.g., maximum 5MB) are valid. If validation is successful, the image is saved in a temporary folder. On the other hand, if the image format or size is inappropriate, an error message is generated and sent to the terminal.

[1275] Output: Image files that pass validation are temporarily saved, and if validation fails, an error message is sent to the terminal.

[1276] Step 4:

[1277] The server passes image data that has been successfully validated to the artificial intelligence model.

[1278] Input: Image file that has been successfully validated

[1279] How it works: The server inputs the saved image files into an AI model (e.g., ResNet or YOLO). The AI ​​model uses machine learning algorithms to extract feature data such as patterns, size, and shape from the image data.

[1280] Output: The feature data extracted by the AI ​​model is returned to the server.

[1281] Step 5:

[1282] The server uses a cost calculation engine to calculate a rough estimate based on the feature data obtained from the AI ​​model.

[1283] Input: Feature data returned from the AI ​​model

[1284] Operation: The server runs a cost calculation engine based on the feature data. The cost calculation engine extracts necessary information such as material costs, processing costs, and labor hours from the database and uses this data to calculate a rough estimate.

[1285] Output: The calculated rough estimate data is saved on the server.

[1286] Step 6:

[1287] The server transmits the calculated rough estimate data to the terminal.

[1288] Input: Calculated rough estimate data

[1289] Operation: The server sends the rough estimate data to the terminal so that the user can check it. The user can check the estimate details and calculation results on the terminal.

[1290] Output: The estimated data is displayed on the terminal.

[1291] Step 7:

[1292] If the user is satisfied with the rough estimate, he or she requests a more accurate estimate.

[1293] Input: User requests accurate quote

[1294] How it works: When the user clicks the "Request an accurate quote" button, the request is sent from the device to the server. The server then requests detailed confirmation from partner vendors. Specifically, it sends the extracted feature data and the quotation conditions to the vendors.

[1295] Output: The server sends a request for an accurate quote to the vendor.

[1296] Step 8:

[1297] The server provides the user with the final quote information received from the vendor.

[1298] Input: Final quote information from vendor

[1299] How it works: The vendor sends information about the final production cost and delivery date to the server. The server temporarily stores this information and notifies the user via their device. The user then checks the final estimate on their device and decides whether to proceed with the production.

[1300] Output: The final quote information is displayed on the terminal and notified to the user.

[1301] (Application example 1)

[1302] 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."

[1303] In modern manufacturing, there is a need to quickly and accurately estimate the production costs of parts and products. However, traditional methods are time-consuming and labor-intensive. Furthermore, it is difficult to quickly calculate costs on-site, which hinders rapid decision-making. This hinders the efficiency of the production process and limits productivity improvements. Furthermore, the time required to confirm accurate estimates from contractors based on rough estimates is also required, so further efficiency improvements are required.

[1304] 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.

[1305] In this invention, the server includes a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and a means for taking images of parts or products using a smartphone and transmitting the images to the server. This enables rapid cost calculation on-site and improves the efficiency of the production process. Furthermore, requesting an accurate estimate from a contractor based on the rough estimate enables rapid decision-making and contributes to improved productivity.

[1306] "User" refers to a person who uses the system to upload images and request a quote.

[1307] "Image" refers to a data file that visually records the shape, size, and other characteristics of a part or product.

[1308] "Upload" refers to the act of a user sending image data they have to a server.

[1309] A "means" refers to a combination of hardware and software for achieving a specific function.

[1310] "Receiving" refers to the process in which the server captures image data sent by the user.

[1311] "Temporarily saving" refers to the operation of saving received image data for a certain period of time.

[1312] "Analysis" refers to the process by which the server uses an artificial intelligence model to extract feature data from image data.

[1313] "Feature data" refers to information such as pattern, size, and shape extracted from an image.

[1314] An "artificial intelligence model" refers to an algorithm that extracts feature data using technologies such as machine learning and deep learning.

[1315] "Rough estimate" refers to the result of calculating a rough production cost based on feature data.

[1316] A "cost calculation engine" refers to a system that calculates a rough estimate based on extracted feature data, taking into account material costs, processing costs, labor hours, etc.

[1317] "Means for providing" refers to the process of displaying or notifying the calculated rough estimate to the user.

[1318] "Smartphone" refers to a portable information terminal that has Internet connectivity and is capable of taking and sending images.

[1319] "Server" refers to a computer system that receives image data from users, analyzes it, and calculates and provides a rough estimate.

[1320] This invention provides a system that allows users to quickly obtain a rough estimate by sending images taken with their smartphone to a server, thereby significantly improving the efficiency of the quotation process for parts and products in the manufacturing industry.

[1321] In the basic system configuration, users use a smartphone application to take pictures of parts or products and upload them to a server. This application includes functions for uploading images, communicating with the server, and displaying quotation results.

[1322] The server receives images sent by users and temporarily stores them. The stored images are first subjected to a validation check, and any images that are deemed inappropriate are requested to be re-uploaded. Images that pass validation are then passed to an artificial intelligence model, which extracts feature data such as pattern, size, and shape. The artificial intelligence model used here uses image analysis technologies such as TensorFlow and OpenCV.

[1323] Once the feature data is extracted, a cost calculation engine uses it to calculate a rough estimate. The cost calculation engine takes into account factors such as material costs, processing costs, and labor hours to generate an estimate. This result is then sent back to the user's smartphone via the server and displayed.

[1324] Furthermore, if the user is satisfied with the rough estimate, they can request a more accurate estimate from the supplier. Based on the user's request, the server will confirm the details with the supplier and confirm the final production cost and delivery date. This allows the user to receive a confirmed estimate and request production based on it.

[1325] For example, when a worker wants to manufacture a new part, he or she takes a picture of the part with their smartphone and sends it through the application. Within seconds, a rough estimate is displayed. The user can then decide to start production based on this estimate. This process allows for fast and efficient calculation of production costs.

[1326] Example prompts for generative AI models

[1327] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[1328] Image file: [uploaded image]

[1329] Parameters: size, shape, weight

[1330] Estimate requirements: material costs, processing costs, labor hours

[1331] The above is a mode for carrying out the invention, and the specific operating procedures can be modified in various ways, thereby enabling the invention to be adapted to different manufacturing environments without losing its essence.

[1332] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1333] Step 1:

[1334] The user takes a picture of a part or product using a smartphone. The captured image is saved in the smartphone's application. The input is image data obtained by the smartphone's camera, and the output is an image file temporarily saved within the application. Specifically, the user taps the camera button on the smartphone to take a picture.

[1335] Step 2:

[1336] The user operates the application to take a picture and upload it to the server. The input is the taken image file, and the output is the image data sent to the server. Specifically, the user taps the "Upload" button in the application to send the image to the server.

[1337] Step 3:

[1338] The server temporarily stores the images it receives. The input is the image data sent by the user, and the output is the image file stored in temporary storage on the server. Specifically, the server stores the image data in a specified folder and performs validation checks on the file format and size.

[1339] Step 4:

[1340] The server passes the temporarily stored images to an artificial intelligence model for image analysis. The input is the image data stored on the server, and the output is feature data such as pattern, size, and shape. Specifically, the server calls an AI model (such as TensorFlow or OpenCV), analyzes the image data, and extracts feature data.

[1341] Step 5:

[1342] The server launches a cost calculation engine based on the extracted feature data to calculate a rough estimate. The input is the feature data, and the output is the rough estimate data. Specifically, the server runs a cost calculation algorithm to evaluate material costs, processing costs, labor hours, etc. to generate an estimate.

[1343] Step 6:

[1344] The server sends the calculated rough estimate data to the user's smartphone. The input is the rough estimate data, and the output is the estimate information displayed on the user's smartphone. Specifically, the server generates an HTTP response and sends the estimate data to the user application.

[1345] Step 7:

[1346] If the user is satisfied with the rough estimate, the application requests confirmation of the exact estimate from the supplier. The input is a formal quote request based on the rough estimate, and the output is the final quote information returned by the supplier. Specifically, the user taps the "Request a formal quote" button in the application, and the entered data is sent to the supplier via the server.

[1347] Step 8:

[1348] The server provides the user with the final quote information received from the vendor. The input is the final quote data from the vendor, and the output is the final quote information displayed on the user's smartphone. Specifically, the server analyzes the data received from the vendor and sends it to the user application.

[1349] Example prompts for generative AI models

[1350] To help us get you a quick quote on your parts, please analyze the image below and provide us with a rough estimate based on the cost of materials, machining, and labor hours required.

[1351] Image file: [uploaded image]

[1352] Parameters: size, shape, weight

[1353] Estimate requirements: material costs, processing costs, labor hours

[1354] 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.

[1355] The present invention is a system that uses image data and emotion data to quickly provide rough estimates for products and parts, optimizing the user experience. The system allows users to upload images, analyzes the images to generate estimates, and, if necessary, requests accurate estimates from vendors, recognizing the user's emotions to optimize the response.

[1356] User-uploaded images

[1357] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required and presses the upload button.

[1358] Receiving and temporarily storing image data

[1359] The terminal sends the image file selected by the user to the server. The server temporarily stores the received image data and performs a validation check. The validation check verifies that the image data format and size are appropriate.

[1360] Image analysis

[1361] The server passes the temporarily stored image data to an AI model, which uses image processing algorithms to extract feature data such as pattern, size, and shape. The extracted feature data is structured and returned to the server.

[1362] Calculating a rough estimate

[1363] The server uses the feature data from the AI ​​model to launch a cost calculation engine, which calculates a rough estimate by taking into account factors such as the cost of materials, processing costs, and labor hours required.

[1364] Providing a rough estimate

[1365] The server sends the calculated rough estimate data to the terminal, and the rough estimate is displayed to the user through the terminal.

[1366] Request an accurate quote

[1367] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then checks the details with affiliated vendors and confirms the final production cost and delivery date.

[1368] Providing a final quote

[1369] The server provides the user with the final quote information received from the supplier, and the user decides whether to order the product based on this information.

[1370] Emotion recognition and optimization

[1371] The server is equipped with an emotion engine that recognizes the user's emotions using facial, voice, and text analysis. Based on the emotion data recognized by the emotion engine, the system provides countermeasures to optimize the user experience. For example, if the user shows a dissatisfied expression, the system will provide additional support and detailed explanations.

[1372] Specific examples

[1373] For example, if a user wants to get a quote for a new electronic component, they first upload an image of the component. The server receives the image and uses an AI model to analyze its size and shape. Based on the analysis results, a cost calculation engine calculates material and processing costs and provides the user with a rough estimate. If the user is satisfied with this rough estimate and requests a formal quote, the server confirms with the supplier and provides the user with a final quote.

[1374] Furthermore, if a user expresses doubt or anxiety while uploading an image, the emotion engine will recognize that emotion and the server will automatically provide the user with appropriate advice and support.

[1375] In this way, the present invention provides fast and accurate product production quotes throughout the system, optimizing the user experience.

[1376] The processing flow will be explained below.

[1377] Step 1:

[1378] The user logs in to the system and accesses the image upload screen. The user selects the image file for which a quote is required.

[1379] Step 2:

[1380] The user presses the upload button. The device sends the selected image file and the user's facial expression data (if using the camera) to the server.

[1381] Step 3:

[1382] The server temporarily stores the received image data and facial expression data.

[1383] Step 4:

[1384] The server performs a validation check on the image data, checking the file format and size to ensure it is in the correct format.

[1385] Step 5:

[1386] The server passes the temporarily stored image data to the artificial intelligence model.

[1387] Step 6:

[1388] The AI ​​model uses image processing algorithms to extract feature data such as pattern, size, shape, etc. The extracted feature data is structured and returned to the server.

[1389] Step 7:

[1390] The server inputs the feature data into the cost calculation engine.

[1391] Step 8:

[1392] The cost calculation engine calculates a rough estimate based on the required material costs, processing costs, and labor hours.

[1393] Step 9:

[1394] The server transmits the calculated rough estimate data to the terminal.

[1395] Step 10:

[1396] The terminal displays the estimated estimate data to the user.

[1397] Step 11:

[1398] If the user is satisfied with the rough estimate, he / she presses a button to request an accurate estimate, and the terminal sends data including a request for an accurate estimate to the server.

[1399] Step 12:

[1400] The server receives an accurate quotation request and makes an inquiry to partner companies.

[1401] Step 13:

[1402] The partner company checks the actual production conditions, costs, and delivery dates and sends them back to the server.

[1403] Step 14:

[1404] The server provides the user with the final quote information received from the vendor.

[1405] Step 15:

[1406] The terminal displays the final quote information to the user.

[1407] Step 16:

[1408] The emotion engine installed on the server analyzes the received user facial expression data, voice data, and text input data to recognize the user's emotions.

[1409] Step 17:

[1410] The server uses the emotion data generated by the emotion engine to determine countermeasures to optimize the user experience, for example, automatically providing additional support or detailed explanations when it recognizes a user's dissatisfaction.

[1411] Step 18:

[1412] The device will display solutions to the user, who can then seek additional support if needed.

[1413] The above is the specific flow of the process in the present invention. This system allows users to receive fast and accurate product manufacturing quotes, and provides an optimal user experience through emotion recognition.

[1414] Example 2

[1415] 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."

[1416] Conventional quotation systems require time-consuming image analysis, resulting in low accuracy of the estimates users receive. Furthermore, they lacked sufficient mechanisms for improving the user experience, leaving users feeling dissatisfied and anxious. Furthermore, they lacked the technology to recognize user emotions and automatically provide appropriate responses.

[1417] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to upload an image, means for receiving and temporarily saving the image, an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, means for providing the rough estimate to the user, an emotion engine for recognizing emotion data by analyzing the user's facial expression or voice, and response means for providing a response based on the emotion data recognized by the emotion engine. This makes it possible to provide a quick and accurate estimate and provide optimal support according to the user's emotions.

[1418] "User" refers to a user who uses this system to upload images and receive estimates and support.

[1419] "Means for uploading images" refers to functionality including interfaces and programs that users use to send image files to the system.

[1420] The "means for receiving and temporarily storing" refers to a function used by the server to receive image data sent from the user and temporarily store it.

[1421] "Artificial intelligence model for analyzing images and extracting feature data such as pattern, size, and shape" refers to a model that includes algorithms and programs that analyze image data, identify the characteristics of the object, and digitize them.

[1422] "Cost calculation engine for calculating a rough estimate" refers to an algorithm or program for calculating a rough estimate based on extracted feature data, taking into account the necessary material costs, processing costs, labor hours, etc.

[1423] "Means for providing a quote to a user" refers to the functionality used to display or transmit the calculated rough quote to the user's terminal.

[1424] An "emotion engine" refers to an algorithm or program that analyzes a user's facial expressions, voice, text, etc. and recognizes their emotions.

[1425] "Response means" refers to a function for providing appropriate support and information to users based on the emotional data recognized by the emotion engine.

[1426] "Vendor" refers to an external service provider or manufacturer that works with the server to provide accurate quotes and production.

[1427] "Fine-tuning" refers to the process by which artificial intelligence models are optimized based on historical usage and product data.

[1428] The present invention is a system that uses image data and emotion data to provide rapid product or part quotes and optimize the user experience. The system is implemented in the following manner.

[1429] The overall system configuration involves users uploading images, which the server analyzes to generate quotes, and the system also recognizes the user's emotions and optimizes responses.

[1430] Required Hardware and Software

[1431] The system uses a common web browser, server, artificial intelligence model, and emotion engine. Specifically, it uses the following hardware and software:

[1432] User device: A computer, smartphone, tablet, etc. that runs a web browser

[1433] Server: Physical server or cloud service for data processing and storage

[1434] Artificial intelligence models: Deep learning frameworks such as TensorFlow

[1435] Emotion engine: AWS Amazon Rekognition and Emotion API

[1436] System Program Processing

[1437] The system performs a process that includes the following major steps:

[1438] 1. User image upload:

[1439] A user logs into the system through a web browser and uploads an image of the product or part for which they want to receive a quote. The user presses the upload button and selects the image file.

[1440] 2. Receiving and temporarily storing image data:

[1441] The device sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check.

[1442] 3. Image Analysis:

[1443] The server analyzes the image using an artificial intelligence model such as TensorFlow to extract feature data such as pattern, size, and shape, and the analysis results are returned to the server as structured data.

[1444] 4. Calculating a rough estimate:

[1445] The server then uses the extracted feature data to launch an in-house cost calculation engine to calculate a rough estimate, taking into account factors such as the cost of materials, processing costs, and labor hours required.

[1446] 5. Providing a rough estimate:

[1447] The server transmits the calculated rough estimate to the user's terminal, where the user can view the estimate.

[1448] 6. Request an accurate quote:

[1449] If the user is satisfied with the rough estimate, they can request a more accurate estimate. The terminal sends the user's request to the server, which then confirms the details with the partner company and confirms the final production cost and delivery date.

[1450] 7. Providing a final quote:

[1451] The server sends the final quotation information received from the supplier to the user's terminal, where the user can confirm the final quotation and request production.

[1452] 8. Emotion recognition and optimization:

[1453] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. Based on the emotional data recognized by the emotion engine, the server automatically provides appropriate support and information.

[1454] Specific examples

[1455] For example, if a user wants to get a quote for a new electronic component, the system operates as follows:

[1456] 1. The user selects an image file of an electronic component (JPEG format, size 1.5MB) and presses the upload button.

[1457] 2. The device sends the selected image to the server as an HTTP POST request.

[1458] 3. The server receives the image, checks the format and size, and temporarily stores it.

[1459] 4. The server uses a TensorFlow model to analyze patterns, size, and shape from the image.

[1460] 5. Based on the analysis results, the cost calculation engine calculates material and processing costs.

[1461] 6. The server sends a rough estimate to the device, where the user can confirm it.

[1462] 7. The user presses the "Request an accurate quote" button.

[1463] 8. The server requests detailed estimates from the vendors and obtains the final estimate information.

[1464] 9. The server provides the final quote to the user.

[1465] 10. If the user shows signs of anxiety, the emotion engine will recognize this and display additional support information.

[1466] Prompt Sentence Examples

[1467] "Upload images of your new electronic components and begin the process of receiving a detailed quote."

[1468] In this way, the present invention aims to provide fast and accurate product production quotes and enhance the user experience.

[1469] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1470] Step 1: User uploads an image

[1471] The user logs in to the system and accesses the image upload screen. The user selects the image file to be quoted and presses the upload button. At this time, the image selected by the user is sent via a browser form. The input is the image file selected by the user, and the output is the image data sent to the server.

[1472] Step 2: Receiving and temporarily saving image data

[1473] The terminal sends the image file selected by the user to the server using an HTTP POST request. The server temporarily stores the received image data and performs a validation check. Specifically, it verifies that the image format (e.g., JPEG, PNG) and size (e.g., 2MB or less) are appropriate. The input is the image data included in the HTTP POST request, and the output is the validated image data.

[1474] Step 3: Image analysis

[1475] The server passes the temporarily stored image data to an artificial intelligence model (e.g., TensorFlow). The model uses an image processing algorithm to extract feature data such as pattern, size, and shape. For example, it uses the model.predict(image data) method. The input is the validated image data, and the output is a structured list of feature data.

[1476] Step 4: Calculate a rough estimate

[1477] The server uses the extracted feature data to launch a cost calculation engine. This engine calculates a rough estimate by taking into account the cost of required materials, processing costs, labor hours, etc. For example, it calculates the cost by calling a function called calculate_cost(feature data). The input is a structured list of feature data, and the output is a numerical estimate.

[1478] Step 5: Provide a rough estimate

[1479] The server sends the calculated rough estimate data to the terminal. This communication is implemented as an HTTP response and displayed in the user's browser. The input is the numerical data of the rough estimate, and the output is the estimate information displayed in the browser.

[1480] Step 6: Request an accurate quote

[1481] If the user is satisfied with the rough estimate, he or she presses a button to request an accurate estimate. The device sends this request as an HTTP POST request to the server. The server receives this request, checks the details with the partner vendor, and confirms the final production cost and delivery date. The input is the user's request data, and the output is the final estimate information from the vendor.

[1482] Step 7: Providing a final quote

[1483] The server provides the final quote information received from the supplier to the user. This communication is also implemented as an HTTP response. The input is the final quote information, and the output is the final quote information displayed in the browser.

[1484] Step 8: Emotion recognition and optimization

[1485] The server is equipped with an emotion engine that analyzes the user's facial expressions, voice, and text to recognize emotional data. When the emotion engine recognizes an emotion, the system provides appropriate support and information corresponding to that emotion. For example, if the user shows an anxious expression, the system provides additional support information. The input is the user's facial expression and voice data, and the output is information on countermeasures.

[1486] (Application example 2)

[1487] 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."

[1488] In modern manufacturing, fast and accurate product and component quotations are essential for efficient production management and cost reduction. However, existing systems do not consider user emotions during the quotation generation process using image data, resulting in a suboptimal user experience. Furthermore, more advanced analysis systems are needed to identify product deterioration and defects, as well as recognize the emotions of factory staff.

[1489] 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 a means for users to upload images, a means for receiving and temporarily saving the images, an artificial intelligence model for analyzing the images and extracting feature data such as pattern, size, and shape, a cost calculation engine for calculating a rough estimate based on the extracted feature data, a means for providing the rough estimate to the user, and an emotion engine for acquiring emotion data and recognizing the user's emotion. This not only enables quick and accurate product estimates but also enables optimal responses that take user emotions into consideration. Furthermore, by checking products in the factory and monitoring staff emotions, the efficiency and quality of the entire manufacturing process can be improved.

[1490] "Means for users to upload images" means a function or interface that allows users to send image data to the system.

[1491] The "means for receiving and temporarily storing the image" refers to a module or device that has the function of temporarily storing image data sent from a user and further verifying the quality and format of the data.

[1492] "Artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape" refers to a software model that automatically analyzes and extracts features related to products and parts from image data using machine learning algorithms.

[1493] "Cost calculation engine that calculates a rough estimate based on the extracted feature data" refers to an algorithm and software engine that uses the extracted feature data to roughly calculate the manufacturing cost of a product.

[1494] The "means for providing the rough estimate to the user" refers to a function or interface for visually or audibly notifying the user of the calculated rough estimate information.

[1495] "Emotion engine for acquiring emotion data and recognizing a user's emotion" means an analytical algorithm and software engine for analyzing facial expressions, voice, and text data acquired from a user and identifying the user's emotional state.

[1496] This invention relates to a "robot assistant" system that checks products and calculates estimates in factories. The robot, equipped with smart glasses, mainly recognizes product images in real time, calculates estimates, and analyzes the emotions of factory staff to optimize work efficiency.

[1497] Hardware and software used

[1498] Hardware: Smart glasses, patrol robots

[1499] software:

[1500] Image analysis model (artificial intelligence model using TensorFlow / Keras)

[1501] Emotion recognition model (FER, MTCNN)

[1502] REST API (cost calculation engine)

[1503] System Flow

[1504] 1. Image upload and analysis:

[1505] The server receives the image data captured by the robot through the smart glasses and temporarily stores it.

[1506] This image data is then passed to an artificial intelligence model to extract feature data such as pattern, size, and shape.

[1507] 2. Acquiring and analyzing emotion data:

[1508] The server receives and temporarily stores facial images of factory staff taken with the smart glasses.

[1509] The emotional recognition model (FER) is used to analyze the emotional state of staff and generate the recognized emotions and their scores.

[1510] 3. Calculating a rough estimate:

[1511] The server sends the feature data obtained from the artificial intelligence model to the cost calculation engine.

[1512] The cost calculation engine calculates a rough estimate based on the acquired data, taking into account factors such as the cost of necessary materials, processing costs, and labor hours.

[1513] 4. Providing rough estimates and sentiment data:

[1514] The server transmits the calculated rough estimate data and the analyzed emotion data to the robot.

[1515] The robot provides this data to factory staff through display devices (display and audio output).

[1516] 5. Optimizing the user experience:

[1517] The server uses the emotion data to provide countermeasures to optimize the user experience, for example, providing additional support or detailed explanations if the user shows signs of dissatisfaction.

[1518] Specific examples

[1519] For example, a factory robot patrols an electronic parts production line, photographing any deterioration or defects in the product with smart glasses and analyzing the images. Based on the detection results, a cost calculation engine generates estimates and provides a list of defective products in real time. Furthermore, the system uses emotion analysis to observe the stress and fatigue of line workers, optimizing the speed of work and the timing of breaks.

[1520] Prompt Sentence Examples

[1521] "Please analyze this image (path_to_product_image.jpg), extract the product feature data, and get a rough estimate. Also, please analyze the emotion of the person in the image and provide the recognized emotion and its score."

[1522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1523] Step 1:

[1524] The user takes an image using a means for uploading images, and the robot sends the image data of the product taken through the smart glasses to a server. The server temporarily stores the received image data. In this process, the smart glasses act as an input device, and the server acts as a data storage device that temporarily stores the image data.

[1525] Step 2:

[1526] The server performs a validation check on the saved image data. Here, it checks to make sure that the image data format (JPEG, PNG, etc.), resolution, and size are appropriate. Image data that passes the validation check is sent to the next analysis step. If validation fails, an error message is output.

[1527] Step 3:

[1528] The server sends the image data that has passed validation to an artificial intelligence model for image analysis. The image analysis model (a model using TensorFlow / Keras) extracts feature data such as pattern, size, and shape from the image data. This process takes the image data as input and outputs feature data. Specifically, a Convolutional Neural Network (CNN) is used to identify specific parts of the image and extract characteristics as numerical data.

[1529] Step 4:

[1530] The server uses the extracted feature data to send data to a cost calculation engine. The cost calculation engine calculates a rough estimate based on the feature data, taking into account factors such as material costs, processing costs, and labor hours. The input here is the feature data, and the output is a rough estimate. The data is sent to an external cost calculation service using a REST API, and the results are obtained.

[1531] Step 5:

[1532] The server sends the calculated rough estimate data to the robot, which then displays the rough estimate to the factory staff through smart glasses. This process uses the estimate data as input and outputs the results using a display and audio output.

[1533] Step 6:

[1534] The server receives and temporarily stores facial images of factory staff taken with smart glasses. The received image data is sent to the emotion recognition model (FER) for analysis. The emotion recognition model analyzes facial expressions from the images, recognizes the emotional state, and generates corresponding data. In this process, the facial expression image is input and the recognized emotional data is output.

[1535] Step 7:

[1536] The server optimizes the user experience based on the emotional data obtained from the emotion recognition model. If the emotional data indicates dissatisfaction or fatigue, the system generates countermeasures offering additional support or detailed explanations, which are then provided to the factory staff via the robot. Specifically, this could include displaying detailed operating instructions or playing a voice message encouraging the staff to take a break.

[1537] This series of processes enables quick and accurate product estimates and optimal responses that take user feelings into consideration.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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).

[1545] 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.

[1546] 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."

[1547] 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.

[1548] 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).

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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, in order to avoid confusion and to 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.

[1558] 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.

[1559] The following is further disclosed regarding the above embodiment.

[1560] (Claim 1)

[1561] means for a user to upload an image;

[1562] means for receiving and temporarily storing the image;

[1563] an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape;

[1564] a cost calculation engine that calculates a rough estimate based on the extracted feature data;

[1565] means for providing said rough estimate to a user;

[1566] A system including:

[1567] (Claim 2)

[1568] 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

[1569] (Claim 3)

[1570] 2. The system of claim 1, wherein the artificial intelligence model is fine-tuned based on historical quote information and product line data.

[1571] "Example 1"

[1572] (Claim 1)

[1573] means for a user to upload an image;

[1574] means for receiving and temporarily storing the image;

[1575] means for validating the format and size of the image;

[1576] an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape;

[1577] a cost calculation engine that calculates a rough estimate based on the extracted feature data;

[1578] means for providing said rough estimate to a user;

[1579] A system including:

[1580] (Claim 2)

[1581] 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

[1582] (Claim 3)

[1583] 2. The system according to claim 1, wherein the artificial intelligence model is adaptively adjusted based on past quote information and product data.

[1584] "Application Example 1"

[1585] (Claim 1)

[1586] means for a user to upload an image;

[1587] means for receiving and temporarily storing the image;

[1588] an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape;

[1589] a cost calculation engine that calculates a rough estimate based on the extracted feature data;

[1590] means for providing said rough estimate to a user;

[1591] A means for taking an image of a part or product using a smartphone and transmitting the image to a server;

[1592] A system including:

[1593] (Claim 2)

[1594] 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

[1595] (Claim 3)

[1596] 2. The system of claim 1, wherein the artificial intelligence model is fine-tuned based on historical quote information and product line data.

[1597] "Example 2: Combining Emotion Engines"

[1598] (Claim 1)

[1599] means for a user to upload an image;

[1600] means for receiving and temporarily storing the image;

[1601] an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape;

[1602] a cost calculation engine that calculates a rough estimate based on the extracted feature data;

[1603] means for providing said rough estimate to a user;

[1604] an emotion engine that analyzes a user's facial expression or voice to recognize emotion data;

[1605] a response means for providing a response based on the emotion data recognized by the emotion engine;

[1606] A system including:

[1607] (Claim 2)

[1608] 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

[1609] (Claim 3)

[1610] 10. The system of claim 1, wherein the artificial intelligence model is fine-tuned based on historical usage data and product line data.

[1611] "Application example 2 when combining emotion engines"

[1612] (Claim 1)

[1613] means for a user to upload an image;

[1614] means for receiving and temporarily storing the image;

[1615] an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape;

[1616] a cost calculation engine that calculates a rough estimate based on the extracted feature data;

[1617] means for providing said rough estimate to a user;

[1618] an emotion engine for acquiring emotion data and recognizing the user's emotion;

[1619] A system including:

[1620] (Claim 2)

[1621] 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

[1622] (Claim 3)

[1623] 2. The system of claim 1, wherein the artificial intelligence model is fine-tuned based on historical quote information and product line data. [Explanation of symbols]

[1624] 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. means for a user to upload an image; means for receiving and temporarily storing the image; an artificial intelligence model for analyzing the image and extracting feature data such as pattern, size, and shape; a cost calculation engine that calculates a rough estimate based on the extracted feature data; means for providing said rough estimate to a user; A system including:

2. 2. The system according to claim 1, further comprising means for requesting confirmation of an accurate estimate from the contractor based on the rough estimate.

3. 2. The system of claim 1, wherein the artificial intelligence model is fine-tuned based on historical quote information and product line data.

Images