System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an image of a room captured by a user with a terminal; means for analyzing the received image to extract features of a household item; means for recognizing a type of the household item based on the extracted features; means for estimating a size and a weight of the recognized household item; means for receiving information on a moving time and a moving destination input by the user; means for calculating a moving cost based on the received information; and means for presenting the calculated moving cost 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] Currently, moving cost estimates are often opaque, forcing consumers to accept the price quoted by moving companies. This makes it difficult to receive services at a fair price, leading to anxiety about the lack of transparency and high fees. Furthermore, obtaining an estimate takes a lot of time and effort, placing a heavy burden on consumers. The goal is to solve these problems by making moving estimates transparent and providing them simply and quickly. [Means for solving the problem]

[0005] The present invention provides a system including means for receiving images of a room taken by a user with a terminal, means for analyzing the received images to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination input by the user, means for calculating moving costs based on the received information, and means for presenting the calculated moving costs to the user. This allows the user to easily and quickly receive a moving estimate, and improves the transparency of the estimate.

[0006] "User" refers to a consumer who uses the System to request a moving quote.

[0007] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that can take images and send input information.

[0008] "Image" refers to photo data of a room taken by a user on a terminal.

[0009] "Means for receiving" refers to the technical means for transmitting images and information from a terminal to a server and receiving them.

[0010] "Means for analysing images" refers to technical means for processing the received image data to extract features of the household item.

[0011] "Extraction means" refers to the technical means for extracting characteristic information of a particular household item from the analyzed image data.

[0012] "Household goods" refers to items such as furniture and home appliances in a room.

[0013] "Means for recognition" refers to a technical means for identifying the type of household item based on the extracted feature information.

[0014] "Size" refers to the physical dimensions of the item (width, height, depth).

[0015] "Weight" refers to the mass of the household goods.

[0016] "Estimating means" refers to technical means for calculating or estimating the size or weight of household goods.

[0017] "Moving date" refers to the date the user plans to move.

[0018] "Moving destination" refers to the new location to which the user plans to move from their current residence.

[0019] "Means for calculating" refers to the technical means for calculating the moving costs based on the information received.

[0020] "Presentation means" refers to the technical means for displaying the calculated moving costs to the user in an easily viewable format. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is a system in which a user takes a photo of a room using a device such as a smartphone, and an AI automatically generates a moving estimate based on the photo. Specific embodiments of the system are described below.

[0043] User operations

[0044] First, the user takes a photo of the room they are moving into with their smartphone. Then, they launch a dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[0045] Processing on the server

[0046] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[0047] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[0048] Estimating the size and weight of your belongings

[0049] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0050] Estimate calculation

[0051] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[0052] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0053] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0054] Distance-based surcharge: Charges are added based on the distance traveled.

[0055] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0056] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0057] Displaying the estimate results

[0058] Once the calculation is complete, the server sends the results to the user's device, where the estimate details and breakdown are displayed on the user's smartphone via a user interface, allowing the user to see a transparent estimate of moving costs.

[0059] Specific examples

[0060] For example, consider the case where a user moves from an apartment in the city to a house in the suburbs in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[0061] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user takes a photo of the room with their smartphone.

[0065] Step 2:

[0066] The user launches the dedicated application and selects the photos they have taken.

[0067] Step 3:

[0068] The user taps the upload button in the application to send the photo data to the server.

[0069] Step 4:

[0070] The server passes the photo data received from the user to the image analysis module.

[0071] Step 5:

[0072] The image analysis module (server) analyzes the received image data and extracts the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[0073] Step 6:

[0074] The server passes the extracted features to the object recognition module.

[0075] Step 7:

[0076] The object recognition module (server) analyzes the features and recognizes the type of household item. In this step, a pre-trained object recognition model is used to identify sofas, beds, tables, etc. as examples.

[0077] Step 8:

[0078] The server inputs the recognized household items into the household item size and weight determination module.

[0079] Step 9:

[0080] The household item size and weight determination module (server) estimates the size of the object using known references in the image (e.g., the height of a door) and also references reference data provided by the user in advance.

[0081] Step 10:

[0082] Based on the size information of the household items, the server refers to a database and estimates the general weight. For example, the weight of a sofa estimated based on its size is set to 70 kg.

[0083] Step 11:

[0084] Within the application, users enter their moving date, new address, and any special requirements.

[0085] Step 12:

[0086] The terminal transmits the input information to the server.

[0087] Step 13:

[0088] The server passes the input information to the estimate calculation module.

[0089] Step 14:

[0090] The estimate calculation module (server) calculates the moving costs. The calculation includes the following factors:

[0091] Basic freight charge

[0092] Additional charges based on the weight of your belongings

[0093] Distance-based surcharge

[0094] Price fluctuations depending on the season

[0095] Additional charges based on special requirements

[0096] Step 15:

[0097] The server passes the calculated estimate to the user interface.

[0098] Step 16:

[0099] The terminal displays the estimate results received from the server.

[0100] Step 17:

[0101] The user interface (terminal) presents the user with quote details and breakdowns, such as basic freight charges, object weight charges, distance charges, time charges, and special request charges.

[0102] Step 18:

[0103] The user checks the estimate and makes further adjustments if necessary.

[0104] Example 1

[0105] 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."

[0106] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and prone to data errors due to subjective judgment. Furthermore, the transparency of estimates was not ensured, and there were often large discrepancies between the estimated cost and the actual moving costs. Furthermore, it was difficult to properly reflect special requirements and seasonal price fluctuations, which caused inconvenience to users.

[0107] 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.

[0108] In this invention, the server includes means for receiving images of a space taken by a user using an information processing device, means for analyzing the received images to extract features of objects, means for recognizing the type of object based on the extracted features, means for estimating the size and weight of the recognized object, means for receiving information on time and target entered by the user, means for calculating costs based on the received information, and means for presenting the calculated costs to the user. This allows users to quickly obtain accurate moving estimates simply by taking and submitting photos of their rooms. Furthermore, highly transparent estimates are provided based on user-entered information and automated analysis results, reducing discrepancies with actual moving costs. Furthermore, special requirements and seasonal price fluctuations are accurately reflected, providing greater convenience for users.

[0109] "User" refers to an individual or corporation that uses the system to request a moving estimate.

[0110] "Information processing device" refers to devices such as smartphones, tablets, and personal computers, and is equipment used to take images, input information, and transmit data.

[0111] "Images of the space" refers to photographs or video data showing the room to be moved and the situation within the room.

[0112] "Server" refers to a remote computer system that processes received images and data and performs recognition, estimation, and calculations.

[0113] "Features of an object" refers to attribute information such as the shape, color, and size of the furniture in the room to be moved.

[0114] "Type of object" refers to a category such as furniture or home appliance that the server identifies by analyzing the characteristics of the object.

[0115] "Size" refers to the dimensional information (e.g., width, height, depth) of the recognized object.

[0116] "Weight" refers to the mass information of an object estimated by the server.

[0117] "Time" refers to the specific date, time, or season when the user plans to move.

[0118] "Target information" refers to additional data that the user provides to the server, such as a new address or special requirements.

[0119] "Cost" refers to the total cost of the move, including the base fee, additional charges based on weight, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements.

[0120] "Presenting" refers to displaying or transmitting the cost calculated by the server to the user's information processing device.

[0121] The present invention is a system that allows a user to take an image of a space to be moved using an information processing device, and automatically calculates a moving estimate based on the image. Specific embodiments of the system are described below.

[0122] User operations

[0123] First, the user takes a photo of the room they are moving into using an information processing device such as a smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[0124] Processing on the server

[0125] The server passes the image data received from the user to the analysis module. This analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm using deep learning to identify the contours of objects and extract the features of each object. Expressive deep learning frameworks such as TensorFlow and PyTorch are used.

[0126] Recognition and classification of household items

[0127] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item (e.g., common household objects such as sofas, tables, beds, refrigerators, etc.).

[0128] Estimating the size and weight of your belongings

[0129] The server uses a size estimation algorithm to estimate the size of each recognized household item. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0130] Estimate calculation

[0131] The server then launches an estimate calculation module based on the collected information to calculate the moving costs, which includes the following factors:

[0132] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0133] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0134] Distance-based surcharge: Charges are added based on the distance traveled.

[0135] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0136] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0137] Displaying the estimate results

[0138] Once the server generates the calculation results, they are sent to the user's information processing device. The estimate details and breakdown are displayed on the user's smartphone via the user interface of a dedicated application. This allows the user to see a transparent estimate of moving costs.

[0139] Specific examples

[0140] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates their size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[0141] Prompt Sentence Examples

[0142] "I took photos of the apartment I'm moving into. Please explain the system I use to automatically calculate a moving estimate based on the photos. Please also include details about the specific steps and technology used."

[0143] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] The user takes an image of the space to be moved into using an information processing device and launches a dedicated application. The user selects the image and taps the upload button. This sends the image data to the server. The input is the image data taken by the user, and the output is the image data sent to the server.

[0147] Step 2:

[0148] The server receives the image data sent by the user. The server receives the data securely using the HTTPS protocol and stores the received image data in a database. The input is the image data sent by the user, and the output is the image data stored in the database.

[0149] Step 3:

[0150] The server passes the received image data to the image analysis module. This module analyzes the image using a segmentation algorithm based on deep learning, identifies the contours of objects, and extracts their features. For example, TensorFlow is used. The input is image data read from the database, and the output is the extracted object feature data.

[0151] Step 4:

[0152] The server receives feature data from the image analysis module and passes it to the object recognition module, which uses these features to identify the type of household item. For example, it uses a machine learning model to recognize sofas, tables, beds, etc. The input is the feature data, and the output is the type data of the identified object.

[0153] Step 5:

[0154] The server runs a size estimation algorithm on the recognized object, calculating its size relative to known objects in the photo and using reference data provided by the user. Based on this, the server references a database to estimate the object's weight. The input is object type data and reference data, and the output is estimated size and weight data.

[0155] Step 6:

[0156] The server launches a quote calculation module based on all collected information. The quote calculation includes basic shipping charges, surcharges based on the weight of the belongings, surcharges based on distance, time-of-year variances, and surcharges based on special requirements. The inputs are the size and weight data of all objects in the room, the time of the move, the distance, and any special requirements, and the output is the total estimated cost.

[0157] Step 7:

[0158] The server sends the calculation results to the user's information processing device. The details and breakdown of the estimate are displayed on the user's smartphone via the user interface of a dedicated application. The input is the total estimated cost data, and the output is the estimate results displayed on the user's device.

[0159] The above are the specific processing steps of the program of this system.

[0160] (Application example 1)

[0161] 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."

[0162] Conventional moving quotation systems required users to manually input the type, size, and weight of household goods, which was time-consuming and labor-intensive. In addition, inventory management and item placement optimization at logistics centers were also done manually, resulting in inefficiency. There was a need to solve these problems and provide an automated, efficient quotation and inventory management system.

[0163] 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.

[0164] In this invention, the server includes means for receiving an image of a location taken by a user with a terminal, means for analyzing the received image to extract features of an item, means for recognizing the type of item based on the extracted features, means for estimating the size and weight of the recognized item, means for receiving information on the moving time and moving destination input by the user, means for calculating moving costs based on the received information, means for presenting the calculated moving costs to the user, means for automatically generating an inventory list based on the analyzed item information, and means for providing suggestions for optimizing inventory allocation based on the analyzed item information, thereby enabling the rapid provision of moving estimates and efficient inventory management at logistics centers.

[0165] A "user" is someone who uses the system to input information and receive results.

[0166] A "terminal" is a device used by a user, and is an apparatus that has functions such as taking photographs and transmitting data.

[0167] "Place images" are photographic data of a specific location or space taken by a user with a terminal.

[0168] A "server" is a computer system that analyzes received data and returns the results of its calculations to the user.

[0169] "Features of an item" are attributes for identifying an item, such as the shape, color, size, and weight of the item.

[0170] "Type of item" is the category to which the item belongs, such as table, chair, sofa, etc.

[0171] "Size" refers to the dimensions of an item, such as length, width, and height.

[0172] "Weight" is a quantity that represents the weight of an item.

[0173] "Moving date" is the date and time when the user desires to move the item.

[0174] "Destination" is the address or location of the destination to which the user wants to move the item.

[0175] "Information" is a general term for data entered by the user and data obtained by the server through analysis.

[0176] "Transportation costs" are the costs incurred to transport an item to a specific location.

[0177] An "inventory list" is a list of items managed as inventory that is automatically generated based on analyzed item information.

[0178] "Location optimization" refers to proposals and plans for efficiently locating inventory and goods.

[0179] The present invention is a system that automates and streamlines inventory management and item movement cost estimation at logistics centers. The system starts when a user takes a photo of the inventory in the logistics center using a device such as a smartphone.

[0180] Hardware and Software Configuration

[0181] User device: A device with a camera and internet connection, such as a smartphone or tablet, is used. The user uses this device to take pictures of the location and uploads them to the server via the application.

[0182] Server: A computer system with a powerful processor and GPU for deep learning, where deep learning models are run using Python and TensorFlow.

[0183] AI model: A deep learning model for recognizing the type, size, and weight of an item, specifically using object detection and segmentation algorithms.

[0184] Database: Stores data on common sizes and weights of items and references them to support estimation results.

[0185] Processing flow

[0186] 1. Take and upload an image

[0187] Users take photos of inventory in the logistics center with their smartphones and upload the images to the server via a dedicated application.

[0188] 2. Image analysis and object recognition

[0189] The server receives the uploaded image data and passes it to an AI model for analysis, which identifies the outline of the objects and extracts and recognizes the features of each object.

[0190] 3. Size and weight estimation

[0191] For each recognized item, the server uses a size estimation algorithm to estimate the size and weight of each item, using known objects in the photo and reference data previously provided by the user.

[0192] 4. Automatically generate inventory lists

[0193] Based on the analyzed product information, the server automatically generates an inventory list, which includes information such as product type, size, and weight.

[0194] 5. Calculating travel expenses

[0195] Based on the travel time and destination information entered by the user, the server calculates the travel cost, which includes a base fee, weight-based surcharges, distance charges, seasonally-dependent charges, and surcharges for special requirements.

[0196] 6. Inventory placement optimization

[0197] Based on the analyzed item information, the server provides suggestions for optimizing inventory allocation, thereby improving the efficiency of item allocation within the distribution center.

[0198] 7. Presenting the results to the user

[0199] The server sends the calculated travel costs and inventory placement optimization proposals to the user's device, where the user can check them.

[0200] Examples and prompts

[0201] For example, a user can take a photo of items on shelves in a logistics center and send it to a server via a dedicated application. The server analyzes the photo and identifies the type and weight of each item. Based on the results, it calculates transportation costs and makes suggestions for optimizing inventory placement. The user can then check this information to achieve efficient inventory management.

[0202] Example prompt sentence:

[0203] "We take photos of the warehouse interior and use an app to streamline inventory management. AI analyzes the type, size, and weight of items, automatically generates an inventory list, and suggests optimal placement."

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] Users take photos of inventory in the logistics center and upload them to the server via a dedicated application.

[0207] Input: Image data taken with a smartphone

[0208] Output: Image data sent to the server

[0209] Step 2:

[0210] The server passes the received image data to the AI ​​model for analysis.

[0211] Input: Image data sent to the server

[0212] Output: Item feature data

[0213] Specific operation: Image data is input into a deep learning segmentation algorithm to extract the object's contours and features.

[0214] Step 3:

[0215] The server uses the extracted feature data to recognize the type of item.

[0216] Input: Item feature data

[0217] Output: Item type data

[0218] Specific operation: Analyzes feature data using a deep learning model to identify the type of item.

[0219] Step 4:

[0220] The server estimates the size and weight of the recognized item.

[0221] Input: Item type data

[0222] Output: Item size and weight data

[0223] Specific Behavior: Estimate the general size and weight of an item by referencing known objects or reference data.

[0224] Step 5:

[0225] The server automatically generates an inventory list based on the analyzed item information.

[0226] Input: Item size and weight data

[0227] Output: Inventory list data

[0228] Specific operation: Collects item information and automatically creates an inventory list.

[0229] Step 6:

[0230] The server receives information about the travel time and destination entered by the user.

[0231] Input: Information from the user about the time and destination of the trip

[0232] Output: Travel time and destination data

[0233] Specific operation: Information on travel time and destination entered by the user via the application is stored in a database.

[0234] Step 7:

[0235] The server calculates the travel cost based on the received information.

[0236] Input: Product information, time of movement and destination data

[0237] Output: Travel cost data

[0238] Specific operation: Calculates base charges, weight-based surcharges, distance charges, seasonally variable charges, and special requirement surcharges.

[0239] Step 8:

[0240] The server provides suggestions for optimizing inventory placement based on the analyzed product information.

[0241] Input: Product information, inventory list data

[0242] Output: Optimized inventory placement proposal

[0243] Specific operation: Based on the type and weight of the item, an efficient placement simulation is performed and suggestions are generated.

[0244] Step 9:

[0245] The server transmits the calculated travel costs and inventory placement optimization proposals to the user's terminal and presents the results to the user.

[0246] Input: Travel cost data, optimized inventory placement proposal

[0247] Output: Display data of travel cost details and placement proposals

[0248] Specific operation: Display details of travel costs and optimization suggestions to the user through the user interface.

[0249] 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.

[0250] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. In addition, by combining it with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service.

[0251] User operations

[0252] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch the dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[0253] Processing on the server

[0254] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[0255] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[0256] Estimating the size and weight of your belongings

[0257] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0258] Estimate calculation

[0259] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[0260] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0261] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0262] Distance-based surcharge: Charges are added based on the distance traveled.

[0263] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0264] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0265] Implementing the Emotion Engine

[0266] The present invention also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). When the user uploads photos or checks the estimate results, the emotion engine collects data from the device's microphone and camera.

[0267] Emotion-based interface adjustment

[0268] The emotion engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotions. For example, if the user is feeling doubtful or dissatisfied, additional explanations can be displayed. Conversely, if the user is satisfied, only a concise message can be displayed. Furthermore, if the user shows strong anxiety or dissatisfaction, the emotion engine can temporarily halt the estimation process and display a message urging reconfirmation.

[0269] Displaying the estimate results

[0270] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion engine also provides appropriate support based on the user's emotions.

[0271] Specific examples

[0272] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[0273] The present invention allows users to easily and quickly obtain moving estimates, ensuring transparency in fees and providing support that responds to the user's emotions, thereby aiming to make moving preparations go more smoothly.

[0274] The processing flow will be explained below.

[0275] Step 1:

[0276] The user takes a photo of the room with their smartphone.

[0277] Step 2:

[0278] The user launches the dedicated application and selects the photos they have taken.

[0279] Step 3:

[0280] The user taps the upload button in the application to send the photo data to the server.

[0281] Step 4:

[0282] The server passes the photo data received from the user to the image analysis module.

[0283] Step 5:

[0284] The image analysis module (server) analyzes the received image data to extract the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[0285] Step 6:

[0286] The server passes the extracted features to the object recognition module.

[0287] Step 7:

[0288] The object recognition module (server) analyzes the features and recognizes the type of household item, using a pre-trained object recognition model to identify sofas, beds, tables, etc.

[0289] Step 8:

[0290] The server inputs the recognized household items into a size and weight determination module.

[0291] Step 9:

[0292] The size and weight determination module (server) estimates the size of an object using known references in the image (e.g., the height of a door) and also references reference data previously provided by the user.

[0293] Step 10:

[0294] Based on the size information of the household item, the server refers to a database and estimates the general weight. For example, the estimated weight of a sofa based on its size is 70 kg.

[0295] Step 11:

[0296] Within the application, users enter their moving date, new address, and any special requirements.

[0297] Step 12:

[0298] The terminal transmits the input information to the server.

[0299] Step 13:

[0300] The server passes the input information to the estimate calculation module.

[0301] Step 14:

[0302] The quote calculation module (server) calculates the moving costs, including the following factors: basic freight charges, surcharges based on the weight of the belongings, surcharges based on distance, seasonal variations in charges, and surcharges based on special requirements.

[0303] Step 15:

[0304] The server passes the calculated estimate to the user interface.

[0305] Step 16:

[0306] The terminal displays the estimate results received from the server to the user.

[0307] Step 17:

[0308] The monitoring module (terminal) transmits the user's voice data and facial expression data to the emotion engine.

[0309] Step 18:

[0310] The emotion engine (server) analyzes the user's voice data and facial expression data to recognize the user's emotions.

[0311] Step 19:

[0312] The emotion engine adjusts the user interface display and messages based on the recognized emotion, for example, displaying additional explanations if the user shows a surprised expression.

[0313] Step 20:

[0314] The user interface (terminal) presents the adjusted display content and messages to the user.

[0315] Step 21:

[0316] The user checks the estimate results and the displayed messages and makes additional adjustments if necessary.

[0317] Example 2

[0318] 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."

[0319] Conventional moving estimate systems require users to manually input information about their belongings, moving dates, and destinations, which can be time-consuming and can result in inaccurate estimates. Furthermore, the user interface is often unintuitive and does not take into account the user's feelings or satisfaction, which can often cause frustration for users. This can lead to problems such as difficulty in understanding or agreeing with the estimate results.

[0320] 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 receiving an image of a room taken by a user with a terminal, means for analyzing the received image to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for analyzing the user's emotions using an emotion recognition engine, and means for dynamically adjusting the user interface based on the analyzed emotions. This allows the user to obtain an accurate and detailed estimate without any hassle, and the provision of an interface that corresponds to the user's emotions enables a more user-friendly experience.

[0321] A "user" is someone who uses the system to take photos of their room and request a moving estimate.

[0322] A "terminal" is a mobile information device such as a smartphone or tablet used by a user.

[0323] A "server" is a central computer system that receives, analyzes, and processes image data sent by users.

[0324] An "image analysis module" is a software or hardware component that processes received image data and extracts features of household items.

[0325] "Feature extraction" is the process of analyzing image data such as contours, shape, size, and color to extract important attributes.

[0326] An "object recognition module" is a software or hardware component that has the functionality to identify the type of household item based on extracted features.

[0327] "Size estimation" is an algorithm that determines the size of an item based on a known standard (e.g., door height).

[0328] "Weight estimation" is the process of calculating the weight of household goods, and is estimated based on past database information and size information.

[0329] The "moving cost calculation means" is a component that has a function of automatically calculating moving costs including basic transportation charges, additional charges, distance charges, seasonally variable charges, and special requirement charges.

[0330] An "emotion recognition engine" is a software or hardware component that analyzes a user's voice data and facial expression data to recognize emotions.

[0331] "User interface adaptation" is the process of dynamically changing display content and messages based on perceived user emotions.

[0332] "Deep learning" is a technology that uses multi-layered neural networks to analyze data and discover patterns and relationships.

[0333] A "segmentation algorithm" is an algorithm for dividing an image into multiple segments (regions) and identifying the contours of objects.

[0334] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. This invention also incorporates an emotion engine that recognizes the user's emotions, providing a more user-friendly interface and service.

[0335] Hardware and Software

[0336] Hardware

[0337] Smartphones and tablets (devices)

[0338] Server (Central Computer System)

[0339] Camera (built into the device)

[0340] Microphone (built into the device)

[0341] software

[0342] Dedicated application

[0343] Image Analysis Module

[0344] Deep learning models (e.g. TensorFlow, PyTorch)

[0345] Emotion recognition engine (e.g., OpenCV, AWS Rekognition)

[0346] Specific details of processing

[0347] User operations

[0348] The user activates the smartphone camera and takes a photo of the room to be moved. Then, they launch the dedicated application, select the photo, tap the upload button, and send the image data to the server. The user then enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[0349] Processing on the server

[0350] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data using a deep learning-based segmentation algorithm to extract the features of the household items present in the room. The extracted features are then passed to the object recognition module, which identifies the type of each item. For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[0351] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door), and also references a database to estimate the typical weight of each household item.

[0352] Based on the collected information, the server uses an estimate calculation module to calculate the moving costs, which include the following factors:

[0353] Basic freight charge: Rate based on distance traveled and basic service

[0354] Weight-based surcharge: A surcharge based on the total weight of your belongings.

[0355] Distance-based surcharge: Charges are added based on the distance traveled

[0356] Seasonal price fluctuations: Prices vary depending on peak and off-peak seasons.

[0357] Extra charges based on special requirements: Extra charges based on special requests entered by the user (e.g. piano transport fees)

[0358] Furthermore, an emotion recognition engine is used to analyze the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). The emotion recognition engine collects data from the device's microphone and camera when the user uploads photos or checks the estimate results.

[0359] Emotion-based interface adjustment

[0360] The emotion recognition engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion. For example, if the user is dissatisfied or uncertain, the system can alleviate the user's anxiety by providing additional explanations or payment options in installments. Conversely, if the user is satisfied, the system can display only a concise message.

[0361] Displaying the estimate results

[0362] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion recognition engine provides appropriate support based on the user's emotions.

[0363] Specific examples

[0364] For example, consider a case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion recognition engine detects this and alleviates the user's anxiety by offering additional explanations and the option to pay in installments.

[0365] Prompt Sentence Examples

[0366] "Describe a system that takes a photo of a room and automatically calculates an estimate for moving, taking into account the time of the move, the destination, and any special requirements. Also include a requirement to recognize the user's emotions and display an appropriate interface."

[0367] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0368] Step 1:

[0369] A user takes a photo of a room using a smartphone. The user activates the smartphone camera and takes a photo that shows the entire room. At this time, the user should be conscious of taking a photo that clearly shows the furniture.

[0370] Step 2:

[0371] The user launches the dedicated application, selects the photo they have taken, and taps the upload button. This sends the image data to the server. The input is the photo data taken by the user, and the output is the image data transferred to the server.

[0372] Step 3:

[0373] The server receives the photo data sent by the user. The server first checks the format and content of the sent data and prepares to pass it to the appropriate image analysis module. The input is the image data sent by the user, and the output is the image data passed to the image analysis module.

[0374] Step 4:

[0375] The server passes the received image data to the image analysis module, which then analyzes the image using a segmentation algorithm based on deep learning. Specifically, it uses TensorFlow and PyTorch to extract the contours and features of household items in the image. The input is the image data, and the output is the extracted feature data.

[0376] Step 5:

[0377] The server receives the feature data extracted from the image analysis module and passes it to the object recognition module. The object recognition module identifies the type of household item based on this feature data. For example, it recognizes sofas, tables, beds, refrigerators, etc. The input is the feature data, and the output is the recognized type data of the household item.

[0378] Step 6:

[0379] Based on the item type data received from the object recognition module, the server uses a size estimation algorithm to estimate the size of each item. This estimation uses known objects in the photo (e.g., the height of a door) as a reference. The input is the item type data, and the output is the estimated size data.

[0380] Step 7:

[0381] The server uses the estimated size data to estimate the general weight of each household item by referencing a database, such as a furniture catalog database or historical data. The input is size data, and the output is estimated weight data.

[0382] Step 8:

[0383] The server receives information about the moving date and destination entered by the user. The user enters this information through a dedicated application. The input is the moving date and destination information, and the output is this information stored on the server.

[0384] Step 9:

[0385] The server uses the estimate calculation module to calculate the moving costs based on the collected information (type of household goods, size, weight, moving time, and moving destination). The calculation includes basic shipping charges, additional charges based on the weight of household goods, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements. The input is all the collected data, and the output is the calculated moving costs.

[0386] Step 10:

[0387] The server sends the calculated moving costs to the user's device. The user can check the details and breakdown of the estimated costs through a dedicated application. The input is the calculated moving cost data, and the output is the estimated results displayed on the user's device.

[0388] Step 11:

[0389] At the same time, the server uses an emotion recognition engine to analyze the user's emotional data. It analyzes the voice data and facial expression data collected from the device's microphone and camera to recognize the user's emotions. The input is the emotional data collected from the device, and the output is the recognized emotional information.

[0390] Step 12:

[0391] Based on the emotions recognized by the emotion recognition engine, the server dynamically adjusts the content and messages displayed in the user interface. For example, if the user feels surprised or anxious, additional explanations or support messages are displayed. The input is the recognized emotional information, and the output is the adjusted user interface.

[0392] Step 13:

[0393] The user checks the quotation results through the application and takes necessary actions (for example, accepting the quotation or requesting additional information). The system executes the next action according to the user's actions. The input is the user's actions, and the output is the system's response to them.

[0394] (Application example 2)

[0395] 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."

[0396] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and laborious. Furthermore, if the estimate results are difficult for users to understand, they may not be able to provide sufficient support. This can cause stress for users when planning a move. Furthermore, the hassle of recognizing products and obtaining information when shopping face-to-face can also detract from the shopping experience.

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

[0398] In this invention, the server includes means for receiving images of a room taken by a user with a terminal, means for analyzing the received images to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for recognizing the user's emotions by analyzing voice and facial expressions, and means for dynamically adjusting the user interface based on the recognized emotions. This enables users to obtain accurate estimates without hassle and receive appropriate support in real time, thereby improving the quality of their shopping experience.

[0399] "Images of a room taken by a user using a terminal" refers to image data of a room taken by a user using a device such as a smartphone or tablet.

[0400] "Means for receiving" refers to the function by which a server or cloud system receives data sent from a user.

[0401] "Means for analyzing and extracting the characteristics of household items" refers to a method that uses image analysis technology to identify characteristics such as the shape, color, and arrangement of furniture and household items from images of a room.

[0402] "Means for recognizing the type of household goods" refers to technology that identifies the type of specific furniture or home appliances, such as sofas or tables, based on extracted features.

[0403] "Size and weight estimation means" refers to an algorithm that calculates the size and weight of a recognized household item.

[0404] The "means for receiving information about the moving date and new address" refers to a function for collecting information such as the moving date and new address provided by the user.

[0405] "Means for calculating moving costs" refers to a calculation function that calculates the total cost of moving based on the collected information.

[0406] The "means for presenting the calculated moving costs to the user" refers to an interface that displays the estimated amount calculated by the server to the user.

[0407] "Means for recognizing a user's emotions by analyzing voice and facial expressions" refers to technology that uses the device's camera and microphone to analyze emotions from the user's voice and facial expressions.

[0408] "Means for dynamically adjusting the user interface based on recognized emotions" refers to a function that changes the displayed messages and layout depending on the user's emotional state.

[0409] "Means for recognizing products and visually presenting their location and information to the user" refers to technology that uses smart glasses or cameras to identify products in a store and display details of them to the user in real time.

[0410] "Means of providing additional recommended information and details to users based on product recognition information and user sentiment" refers to a function that provides detailed information about products that interest users and suggests related products.

[0411] This invention is a system that allows a user to take pictures of a room using a device such as a smartphone or tablet, and automatically provides a moving estimate based on those pictures. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service. Below, specific embodiments of the invention are described.

[0412] System configuration

[0413] The system consists of the following main components:

[0414] 1. Terminal

[0415] It is used by users to take and upload photos of their rooms, and can be a smartphone or tablet.

[0416] It has a built-in camera and microphone for emotion recognition.

[0417] 2. Server

[0418] Receives and analyzes photo data.

[0419] It is equipped with an image analysis module that uses deep learning.

[0420] It is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions and voice data.

[0421] Calculate the moving costs and present the results to the user.

[0422] Implementation Procedure

[0423] 1. User operations

[0424] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (e.g., transporting a piano) through the application.

[0425] 2. Processing on the server

[0426] The server passes the photo data received from the user to the image analysis module, which uses a deep learning-based segmentation algorithm to extract the characteristics of the household items in the room.Then, based on the extracted features, it identifies the type of household item.For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[0427] 3. Estimate the size and weight of your belongings

[0428] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door) as well as reference data provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0429] 4. Estimate calculation

[0430] The server uses the collected information to calculate the cost of the move, including the basic freight charge, additional charges based on the weight of the belongings, additional charges based on distance, seasonal variations, and additional charges based on special requirements.

[0431] 5. Implementing the Emotion Engine

[0432] When the user reviews the photos and quotes, the server uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize emotions. Based on the recognized emotions, the server dynamically adjusts the interface and displays additional explanations and payment options as needed.

[0433] Specific examples

[0434] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[0435] Prompt Sentence Examples

[0436] Input to the product recognition model: We train the model using a large number of images of shelves and products, with the following prompt: 'Identify and output the name, price, and details of the product in this image.'

[0437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0438] Step 1:

[0439] The user takes a photo of the room with their smartphone, launches the dedicated application, selects the photo, and taps the upload button.

[0440] Input: A photo of a room taken with a smartphone.

[0441] Output: Image data sent to the server.

[0442] Specific operation: The user operates the application to select a photo and taps the upload button, which sends the image data to the server.

[0443] Step 2:

[0444] The server acquires the photo data received from the user and passes it to the image analysis module.

[0445] Input: Room image data sent by the user.

[0446] Output: Data input to the image analysis module.

[0447] Specific operation: The server stores the received photo data in memory and passes it to the image analysis module.

[0448] Step 3:

[0449] The image analysis module on the server uses deep learning to analyze the images and extract the characteristics of the household items in the room.

[0450] Input: Image data of the room input to the image analysis module.

[0451] Output: Extracted feature data of household items (e.g., furniture shape and layout).

[0452] How it works: The deep learning model uses a segmentation algorithm to identify furniture and appliances in the image and generate feature data.

[0453] Step 4:

[0454] Based on the extracted feature data, the server identifies the type of household item.

[0455] Input: Household property characteristics data.

[0456] Output: Identified household item type data (e.g. sofa, table, bed).

[0457] Specific operation: By referring to the feature data, the deep learning object recognition algorithm identifies the type of household item.

[0458] Step 5:

[0459] The server runs an algorithm to estimate the size and weight of recognized household items.

[0460] Input: Household item type data.

[0461] Output: Estimated household item size and weight data.

[0462] What it does: Using known objects (e.g., door height) or user-provided reference data, the size estimation algorithm calculates the size and weight of household items.

[0463] Step 6:

[0464] The user enters the moving date, new address, and any special requirements through a dedicated application, and then sends the data to the server.

[0465] Input: User-entered moving information, including when and where to move, and any special requirements.

[0466] Output: The moving information data sent to the server.

[0467] Specific operation: The user enters moving information into the application form and taps the submit button, which sends the data to the server.

[0468] Step 7:

[0469] The server calculates the moving expenses based on the received moving information data and the estimated size and weight data of the household goods.

[0470] Input: Moving information data, size and weight data of household goods.

[0471] Output: Calculated moving cost data.

[0472] Specific operation: The server calculates the basic transportation fee, additional fees based on the weight of the belongings, additional fees based on the distance, seasonal variations in fees, and additional fees based on special requirements, and then calculates the final moving cost.

[0473] Step 8:

[0474] When a user uploads a photo or checks the estimate results, the server uses the device's camera and microphone to collect the user's voice and facial expressions, which are then analyzed by the emotion engine.

[0475] Input: User voice and facial expression data collected by the device's camera and microphone.

[0476] Output: Recognized user emotional state data.

[0477] Specific operation: The emotion engine analyzes the tone of the voice data and facial expression data to classify the user's emotions.

[0478] Step 9:

[0479] The server dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion, providing additional explanations and payment instalment options as needed.

[0480] Input: Recognized emotional state data.

[0481] Output: Dynamically adjusted interface display and messages.

[0482] Specific behavior: If the user expresses surprise or dissatisfaction, an interface is generated that displays additional explanations and options.

[0483] Step 10:

[0484] The final calculated moving cost, along with the details and breakdown of the estimate, are displayed on the user's smartphone via a user interface tailored by the emotion engine's results.

[0485] Input: Calculated moving cost data, dynamically adjusted interface data.

[0486] Output: Quote details and breakdown displayed on the user's smartphone.

[0487] Specific operation: The server sends the calculation results and adjusted interface data to the user terminal and displays them for the user to check.

[0488] The above are the specific processing steps of the program for the system that realizes the application example.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] [Second embodiment]

[0493] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0494] 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.

[0495] 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).

[0496] 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.

[0497] 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.

[0498] 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).

[0499] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0504] 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."

[0505] The present invention is a system in which a user takes a photo of a room using a device such as a smartphone, and an AI automatically generates a moving estimate based on the photo. Specific embodiments of the system are described below.

[0506] User operations

[0507] First, the user takes a photo of the room they are moving into with their smartphone. Then, they launch a dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[0508] Processing on the server

[0509] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[0510] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[0511] Estimating the size and weight of your belongings

[0512] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0513] Estimate calculation

[0514] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[0515] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0516] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0517] Distance-based surcharge: Charges are added based on the distance traveled.

[0518] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0519] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0520] Displaying the estimate results

[0521] Once the calculation is complete, the server sends the results to the user's device, where the estimate details and breakdown are displayed on the user's smartphone via a user interface, allowing the user to see a transparent estimate of moving costs.

[0522] Specific examples

[0523] For example, consider the case where a user moves from an apartment in the city to a house in the suburbs in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[0524] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] The user takes a photo of the room with their smartphone.

[0528] Step 2:

[0529] The user launches the dedicated application and selects the photos they have taken.

[0530] Step 3:

[0531] The user taps the upload button in the application to send the photo data to the server.

[0532] Step 4:

[0533] The server passes the photo data received from the user to the image analysis module.

[0534] Step 5:

[0535] The image analysis module (server) analyzes the received image data and extracts the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[0536] Step 6:

[0537] The server passes the extracted features to the object recognition module.

[0538] Step 7:

[0539] The object recognition module (server) analyzes the features and recognizes the type of household item. In this step, a pre-trained object recognition model is used to identify sofas, beds, tables, etc. as examples.

[0540] Step 8:

[0541] The server inputs the recognized household items into the household item size and weight determination module.

[0542] Step 9:

[0543] The household item size and weight determination module (server) estimates the size of the object using known references in the image (e.g., the height of a door) and also references reference data provided by the user in advance.

[0544] Step 10:

[0545] Based on the size information of the household items, the server refers to a database and estimates the general weight. For example, the weight of a sofa estimated based on its size is set to 70 kg.

[0546] Step 11:

[0547] Within the application, users enter their moving date, new address, and any special requirements.

[0548] Step 12:

[0549] The terminal transmits the input information to the server.

[0550] Step 13:

[0551] The server passes the input information to the estimate calculation module.

[0552] Step 14:

[0553] The estimate calculation module (server) calculates the moving costs. The calculation includes the following factors:

[0554] Basic freight charge

[0555] Additional charges based on the weight of your belongings

[0556] Distance-based surcharge

[0557] Price fluctuations depending on the season

[0558] Additional charges based on special requirements

[0559] Step 15:

[0560] The server passes the calculated estimate to the user interface.

[0561] Step 16:

[0562] The terminal displays the estimate results received from the server.

[0563] Step 17:

[0564] The user interface (terminal) presents the user with quote details and breakdowns, such as basic freight charges, object weight charges, distance charges, time charges, and special request charges.

[0565] Step 18:

[0566] The user checks the estimate and makes further adjustments if necessary.

[0567] Example 1

[0568] 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."

[0569] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and prone to data errors due to subjective judgment. Furthermore, the transparency of estimates was not ensured, and there were often large discrepancies between the estimated cost and the actual moving costs. Furthermore, it was difficult to properly reflect special requirements and seasonal price fluctuations, which caused inconvenience to users.

[0570] 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.

[0571] In this invention, the server includes means for receiving images of a space taken by a user using an information processing device, means for analyzing the received images to extract features of objects, means for recognizing the type of object based on the extracted features, means for estimating the size and weight of the recognized object, means for receiving information on time and target entered by the user, means for calculating costs based on the received information, and means for presenting the calculated costs to the user. This allows users to quickly obtain accurate moving estimates simply by taking and submitting photos of their rooms. Furthermore, highly transparent estimates are provided based on user-entered information and automated analysis results, reducing discrepancies with actual moving costs. Furthermore, special requirements and seasonal price fluctuations are accurately reflected, providing greater convenience for users.

[0572] "User" refers to an individual or corporation that uses the system to request a moving estimate.

[0573] "Information processing device" refers to devices such as smartphones, tablets, and personal computers, and is equipment used to take images, input information, and transmit data.

[0574] "Images of the space" refers to photographs or video data showing the room to be moved and the situation within the room.

[0575] "Server" refers to a remote computer system that processes received images and data and performs recognition, estimation, and calculations.

[0576] "Features of an object" refers to attribute information such as the shape, color, and size of the furniture in the room to be moved.

[0577] "Type of object" refers to a category such as furniture or home appliance that the server identifies by analyzing the characteristics of the object.

[0578] "Size" refers to the dimensional information (e.g., width, height, depth) of the recognized object.

[0579] "Weight" refers to the mass information of an object estimated by the server.

[0580] "Time" refers to the specific date, time, or season when the user plans to move.

[0581] "Target information" refers to additional data that the user provides to the server, such as a new address or special requirements.

[0582] "Cost" refers to the total cost of the move, including the base fee, additional charges based on weight, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements.

[0583] "Presenting" refers to displaying or transmitting the cost calculated by the server to the user's information processing device.

[0584] The present invention is a system that allows a user to take an image of a space to be moved using an information processing device, and automatically calculates a moving estimate based on the image. Specific embodiments of the system are described below.

[0585] User operations

[0586] First, the user takes a photo of the room they are moving into using an information processing device such as a smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[0587] Processing on the server

[0588] The server passes the image data received from the user to the analysis module. This analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm using deep learning to identify the contours of objects and extract the features of each object. Expressive deep learning frameworks such as TensorFlow and PyTorch are used.

[0589] Recognition and classification of household items

[0590] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item (e.g., common household objects such as sofas, tables, beds, refrigerators, etc.).

[0591] Estimating the size and weight of your belongings

[0592] The server uses a size estimation algorithm to estimate the size of each recognized household item. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0593] Estimate calculation

[0594] The server then launches an estimate calculation module based on the collected information to calculate the moving costs, which includes the following factors:

[0595] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0596] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0597] Distance-based surcharge: Charges are added based on the distance traveled.

[0598] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0599] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0600] Displaying the estimate results

[0601] Once the server generates the calculation results, they are sent to the user's information processing device. The estimate details and breakdown are displayed on the user's smartphone via the user interface of a dedicated application. This allows the user to see a transparent estimate of moving costs.

[0602] Specific examples

[0603] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates their size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[0604] Prompt Sentence Examples

[0605] "I took photos of the apartment I'm moving into. Please explain the system I use to automatically calculate a moving estimate based on the photos. Please also include details about the specific steps and technology used."

[0606] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Step 1:

[0609] The user takes an image of the space to be moved into using an information processing device and launches a dedicated application. The user selects the image and taps the upload button. This sends the image data to the server. The input is the image data taken by the user, and the output is the image data sent to the server.

[0610] Step 2:

[0611] The server receives the image data sent by the user. The server receives the data securely using the HTTPS protocol and stores the received image data in a database. The input is the image data sent by the user, and the output is the image data stored in the database.

[0612] Step 3:

[0613] The server passes the received image data to the image analysis module. This module analyzes the image using a segmentation algorithm based on deep learning, identifies the contours of objects, and extracts their features. For example, TensorFlow is used. The input is image data read from the database, and the output is the extracted object feature data.

[0614] Step 4:

[0615] The server receives feature data from the image analysis module and passes it to the object recognition module, which uses these features to identify the type of household item. For example, it uses a machine learning model to recognize sofas, tables, beds, etc. The input is the feature data, and the output is the type data of the identified object.

[0616] Step 5:

[0617] The server runs a size estimation algorithm on the recognized object, calculating its size relative to known objects in the photo and using reference data provided by the user. Based on this, the server references a database to estimate the object's weight. The input is object type data and reference data, and the output is estimated size and weight data.

[0618] Step 6:

[0619] The server launches a quote calculation module based on all collected information. The quote calculation includes basic shipping charges, surcharges based on the weight of the belongings, surcharges based on distance, time-of-year variances, and surcharges based on special requirements. The inputs are the size and weight data of all objects in the room, the time of the move, the distance, and any special requirements, and the output is the total estimated cost.

[0620] Step 7:

[0621] The server sends the calculation results to the user's information processing device. The details and breakdown of the estimate are displayed on the user's smartphone via the user interface of a dedicated application. The input is the total estimated cost data, and the output is the estimate results displayed on the user's device.

[0622] The above are the specific processing steps of the program of this system.

[0623] (Application example 1)

[0624] 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."

[0625] Conventional moving quotation systems required users to manually input the type, size, and weight of household goods, which was time-consuming and labor-intensive. In addition, inventory management and item placement optimization at logistics centers were also done manually, resulting in inefficiency. There was a need to solve these problems and provide an automated, efficient quotation and inventory management system.

[0626] 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.

[0627] In this invention, the server includes means for receiving an image of a location taken by a user with a terminal, means for analyzing the received image to extract features of an item, means for recognizing the type of item based on the extracted features, means for estimating the size and weight of the recognized item, means for receiving information on the moving time and moving destination input by the user, means for calculating moving costs based on the received information, means for presenting the calculated moving costs to the user, means for automatically generating an inventory list based on the analyzed item information, and means for providing suggestions for optimizing inventory allocation based on the analyzed item information, thereby enabling the rapid provision of moving estimates and efficient inventory management at logistics centers.

[0628] A "user" is someone who uses the system to input information and receive results.

[0629] A "terminal" is a device used by a user, and is an apparatus that has functions such as taking photographs and transmitting data.

[0630] "Place images" are photographic data of a specific location or space taken by a user with a terminal.

[0631] A "server" is a computer system that analyzes received data and returns the results of its calculations to the user.

[0632] "Features of an item" are attributes for identifying an item, such as the shape, color, size, and weight of the item.

[0633] "Type of item" is the category to which the item belongs, such as table, chair, sofa, etc.

[0634] "Size" refers to the dimensions of an item, such as length, width, and height.

[0635] "Weight" is a quantity that represents the weight of an item.

[0636] "Moving date" is the date and time when the user desires to move the item.

[0637] "Destination" is the address or location of the destination to which the user wants to move the item.

[0638] "Information" is a general term for data entered by the user and data obtained by the server through analysis.

[0639] "Transportation costs" are the costs incurred to transport an item to a specific location.

[0640] An "inventory list" is a list of items managed as inventory that is automatically generated based on analyzed item information.

[0641] "Location optimization" refers to proposals and plans for efficiently locating inventory and goods.

[0642] The present invention is a system that automates and streamlines inventory management and item movement cost estimation at logistics centers. The system starts when a user takes a photo of the inventory in the logistics center using a device such as a smartphone.

[0643] Hardware and Software Configuration

[0644] User device: A device with a camera and internet connection, such as a smartphone or tablet, is used. The user uses this device to take pictures of the location and uploads them to the server via the application.

[0645] Server: A computer system with a powerful processor and GPU for deep learning, where deep learning models are run using Python and TensorFlow.

[0646] AI model: A deep learning model for recognizing the type, size, and weight of an item, specifically using object detection and segmentation algorithms.

[0647] Database: Stores data on common sizes and weights of items and references them to support estimation results.

[0648] Processing flow

[0649] 1. Take and upload an image

[0650] Users take photos of inventory in the logistics center with their smartphones and upload the images to the server via a dedicated application.

[0651] 2. Image analysis and object recognition

[0652] The server receives the uploaded image data and passes it to an AI model for analysis, which identifies the outline of the objects and extracts and recognizes the features of each object.

[0653] 3. Size and weight estimation

[0654] For each recognized item, the server uses a size estimation algorithm to estimate the size and weight of each item, using known objects in the photo and reference data previously provided by the user.

[0655] 4. Automatically generate inventory lists

[0656] Based on the analyzed product information, the server automatically generates an inventory list, which includes information such as product type, size, and weight.

[0657] 5. Calculating travel expenses

[0658] Based on the travel time and destination information entered by the user, the server calculates the travel cost, which includes a base fee, weight-based surcharges, distance charges, seasonally-dependent charges, and surcharges for special requirements.

[0659] 6. Inventory placement optimization

[0660] Based on the analyzed item information, the server provides suggestions for optimizing inventory allocation, thereby improving the efficiency of item allocation within the distribution center.

[0661] 7. Presenting the results to the user

[0662] The server sends the calculated travel costs and inventory placement optimization proposals to the user's device, where the user can check them.

[0663] Examples and prompts

[0664] For example, a user can take a photo of items on shelves in a logistics center and send it to a server via a dedicated application. The server analyzes the photo and identifies the type and weight of each item. Based on the results, it calculates transportation costs and makes suggestions for optimizing inventory placement. The user can then check this information to achieve efficient inventory management.

[0665] Example prompt sentence:

[0666] "We take photos of the warehouse interior and use an app to streamline inventory management. AI analyzes the type, size, and weight of items, automatically generates an inventory list, and suggests optimal placement."

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] Users take photos of inventory in the logistics center and upload them to the server via a dedicated application.

[0670] Input: Image data taken with a smartphone

[0671] Output: Image data sent to the server

[0672] Step 2:

[0673] The server passes the received image data to the AI ​​model for analysis.

[0674] Input: Image data sent to the server

[0675] Output: Item feature data

[0676] Specific operation: Image data is input into a deep learning segmentation algorithm to extract the object's contours and features.

[0677] Step 3:

[0678] The server uses the extracted feature data to recognize the type of item.

[0679] Input: Item feature data

[0680] Output: Item type data

[0681] Specific operation: Analyzes feature data using a deep learning model to identify the type of item.

[0682] Step 4:

[0683] The server estimates the size and weight of the recognized item.

[0684] Input: Item type data

[0685] Output: Item size and weight data

[0686] Specific Behavior: Estimate the general size and weight of an item by referencing known objects or reference data.

[0687] Step 5:

[0688] The server automatically generates an inventory list based on the analyzed item information.

[0689] Input: Item size and weight data

[0690] Output: Inventory list data

[0691] Specific operation: Collects item information and automatically creates an inventory list.

[0692] Step 6:

[0693] The server receives information about the travel time and destination entered by the user.

[0694] Input: Information from the user about the time and destination of the trip

[0695] Output: Travel time and destination data

[0696] Specific operation: Information on travel time and destination entered by the user via the application is stored in a database.

[0697] Step 7:

[0698] The server calculates the travel cost based on the received information.

[0699] Input: Product information, time of movement and destination data

[0700] Output: Travel cost data

[0701] Specific operation: Calculates base charges, weight-based surcharges, distance charges, seasonally variable charges, and special requirement surcharges.

[0702] Step 8:

[0703] The server provides suggestions for optimizing inventory placement based on the analyzed product information.

[0704] Input: Product information, inventory list data

[0705] Output: Optimized inventory placement proposal

[0706] Specific operation: Based on the type and weight of the item, an efficient placement simulation is performed and suggestions are generated.

[0707] Step 9:

[0708] The server transmits the calculated travel costs and inventory placement optimization proposals to the user's terminal and presents the results to the user.

[0709] Input: Travel cost data, optimized inventory placement proposal

[0710] Output: Display data of travel cost details and placement proposals

[0711] Specific operation: Display details of travel costs and optimization suggestions to the user through the user interface.

[0712] 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.

[0713] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. In addition, by combining it with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service.

[0714] User operations

[0715] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch the dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[0716] Processing on the server

[0717] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[0718] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[0719] Estimating the size and weight of your belongings

[0720] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0721] Estimate calculation

[0722] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[0723] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0724] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0725] Distance-based surcharge: Charges are added based on the distance traveled.

[0726] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0727] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0728] Implementing the Emotion Engine

[0729] The present invention also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). When the user uploads photos or checks the estimate results, the emotion engine collects data from the device's microphone and camera.

[0730] Emotion-based interface adjustment

[0731] The emotion engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotions. For example, if the user is feeling doubtful or dissatisfied, additional explanations can be displayed. Conversely, if the user is satisfied, only a concise message can be displayed. Furthermore, if the user shows strong anxiety or dissatisfaction, the emotion engine can temporarily halt the estimation process and display a message urging reconfirmation.

[0732] Displaying the estimate results

[0733] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion engine also provides appropriate support based on the user's emotions.

[0734] Specific examples

[0735] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[0736] The present invention allows users to easily and quickly obtain moving estimates, ensuring transparency in fees and providing support that responds to the user's emotions, thereby aiming to make moving preparations go more smoothly.

[0737] The processing flow will be explained below.

[0738] Step 1:

[0739] The user takes a photo of the room with their smartphone.

[0740] Step 2:

[0741] The user launches the dedicated application and selects the photos they have taken.

[0742] Step 3:

[0743] The user taps the upload button in the application to send the photo data to the server.

[0744] Step 4:

[0745] The server passes the photo data received from the user to the image analysis module.

[0746] Step 5:

[0747] The image analysis module (server) analyzes the received image data to extract the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[0748] Step 6:

[0749] The server passes the extracted features to the object recognition module.

[0750] Step 7:

[0751] The object recognition module (server) analyzes the features and recognizes the type of household item, using a pre-trained object recognition model to identify sofas, beds, tables, etc.

[0752] Step 8:

[0753] The server inputs the recognized household items into a size and weight determination module.

[0754] Step 9:

[0755] The size and weight determination module (server) estimates the size of an object using known references in the image (e.g., the height of a door) and also references reference data previously provided by the user.

[0756] Step 10:

[0757] Based on the size information of the household item, the server refers to a database and estimates the general weight. For example, the estimated weight of a sofa based on its size is 70 kg.

[0758] Step 11:

[0759] Within the application, users enter their moving date, new address, and any special requirements.

[0760] Step 12:

[0761] The terminal transmits the input information to the server.

[0762] Step 13:

[0763] The server passes the input information to the estimate calculation module.

[0764] Step 14:

[0765] The quote calculation module (server) calculates the moving costs, including the following factors: basic freight charges, surcharges based on the weight of the belongings, surcharges based on distance, seasonal variations in charges, and surcharges based on special requirements.

[0766] Step 15:

[0767] The server passes the calculated estimate to the user interface.

[0768] Step 16:

[0769] The terminal displays the estimate results received from the server to the user.

[0770] Step 17:

[0771] The monitoring module (terminal) transmits the user's voice data and facial expression data to the emotion engine.

[0772] Step 18:

[0773] The emotion engine (server) analyzes the user's voice data and facial expression data to recognize the user's emotions.

[0774] Step 19:

[0775] The emotion engine adjusts the user interface display and messages based on the recognized emotion, for example, displaying additional explanations if the user shows a surprised expression.

[0776] Step 20:

[0777] The user interface (terminal) presents the adjusted display content and messages to the user.

[0778] Step 21:

[0779] The user checks the estimate results and the displayed messages and makes additional adjustments if necessary.

[0780] Example 2

[0781] 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."

[0782] Conventional moving estimate systems require users to manually input information about their belongings, moving dates, and destinations, which can be time-consuming and can result in inaccurate estimates. Furthermore, the user interface is often unintuitive and does not take into account the user's feelings or satisfaction, which can often cause frustration for users. This can lead to problems such as difficulty in understanding or agreeing with the estimate results.

[0783] 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 receiving an image of a room taken by a user with a terminal, means for analyzing the received image to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for analyzing the user's emotions using an emotion recognition engine, and means for dynamically adjusting the user interface based on the analyzed emotions. This allows the user to obtain an accurate and detailed estimate without any hassle, and the provision of an interface that corresponds to the user's emotions enables a more user-friendly experience.

[0784] A "user" is someone who uses the system to take photos of their room and request a moving estimate.

[0785] A "terminal" is a mobile information device such as a smartphone or tablet used by a user.

[0786] A "server" is a central computer system that receives, analyzes, and processes image data sent by users.

[0787] An "image analysis module" is a software or hardware component that processes received image data and extracts features of household items.

[0788] "Feature extraction" is the process of analyzing image data such as contours, shape, size, and color to extract important attributes.

[0789] An "object recognition module" is a software or hardware component that has the functionality to identify the type of household item based on extracted features.

[0790] "Size estimation" is an algorithm that determines the size of an item based on a known standard (e.g., door height).

[0791] "Weight estimation" is the process of calculating the weight of household goods, and is estimated based on past database information and size information.

[0792] The "moving cost calculation means" is a component that has a function of automatically calculating moving costs including basic transportation charges, additional charges, distance charges, seasonally variable charges, and special requirement charges.

[0793] An "emotion recognition engine" is a software or hardware component that analyzes a user's voice data and facial expression data to recognize emotions.

[0794] "User interface adaptation" is the process of dynamically changing display content and messages based on perceived user emotions.

[0795] "Deep learning" is a technology that uses multi-layered neural networks to analyze data and discover patterns and relationships.

[0796] A "segmentation algorithm" is an algorithm for dividing an image into multiple segments (regions) and identifying the contours of objects.

[0797] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. This invention also incorporates an emotion engine that recognizes the user's emotions, providing a more user-friendly interface and service.

[0798] Hardware and Software

[0799] Hardware

[0800] Smartphones and tablets (devices)

[0801] Server (Central Computer System)

[0802] Camera (built into the device)

[0803] Microphone (built into the device)

[0804] software

[0805] Dedicated application

[0806] Image Analysis Module

[0807] Deep learning models (e.g. TensorFlow, PyTorch)

[0808] Emotion recognition engine (e.g., OpenCV, AWS Rekognition)

[0809] Specific details of processing

[0810] User operations

[0811] The user activates the smartphone camera and takes a photo of the room to be moved. Then, they launch the dedicated application, select the photo, tap the upload button, and send the image data to the server. The user then enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[0812] Processing on the server

[0813] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data using a deep learning-based segmentation algorithm to extract the features of the household items present in the room. The extracted features are then passed to the object recognition module, which identifies the type of each item. For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[0814] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door), and also references a database to estimate the typical weight of each household item.

[0815] Based on the collected information, the server uses an estimate calculation module to calculate the moving costs, which include the following factors:

[0816] Basic freight charge: Rate based on distance traveled and basic service

[0817] Weight-based surcharge: A surcharge based on the total weight of your belongings.

[0818] Distance-based surcharge: Charges are added based on the distance traveled

[0819] Seasonal price fluctuations: Prices vary depending on peak and off-peak seasons.

[0820] Extra charges based on special requirements: Extra charges based on special requests entered by the user (e.g. piano transport fees)

[0821] Furthermore, an emotion recognition engine is used to analyze the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). The emotion recognition engine collects data from the device's microphone and camera when the user uploads photos or checks the estimate results.

[0822] Emotion-based interface adjustment

[0823] The emotion recognition engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion. For example, if the user is dissatisfied or uncertain, the system can alleviate the user's anxiety by providing additional explanations or payment options in installments. Conversely, if the user is satisfied, the system can display only a concise message.

[0824] Displaying the estimate results

[0825] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion recognition engine provides appropriate support based on the user's emotions.

[0826] Specific examples

[0827] For example, consider a case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion recognition engine detects this and alleviates the user's anxiety by offering additional explanations and the option to pay in installments.

[0828] Prompt Sentence Examples

[0829] "Describe a system that takes a photo of a room and automatically calculates an estimate for moving, taking into account the time of the move, the destination, and any special requirements. Also include a requirement to recognize the user's emotions and display an appropriate interface."

[0830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] A user takes a photo of a room using a smartphone. The user activates the smartphone camera and takes a photo that shows the entire room. At this time, the user should be conscious of taking a photo that clearly shows the furniture.

[0833] Step 2:

[0834] The user launches the dedicated application, selects the photo they have taken, and taps the upload button. This sends the image data to the server. The input is the photo data taken by the user, and the output is the image data transferred to the server.

[0835] Step 3:

[0836] The server receives the photo data sent by the user. The server first checks the format and content of the sent data and prepares to pass it to the appropriate image analysis module. The input is the image data sent by the user, and the output is the image data passed to the image analysis module.

[0837] Step 4:

[0838] The server passes the received image data to the image analysis module, which then analyzes the image using a segmentation algorithm based on deep learning. Specifically, it uses TensorFlow and PyTorch to extract the contours and features of household items in the image. The input is the image data, and the output is the extracted feature data.

[0839] Step 5:

[0840] The server receives the feature data extracted from the image analysis module and passes it to the object recognition module. The object recognition module identifies the type of household item based on this feature data. For example, it recognizes sofas, tables, beds, refrigerators, etc. The input is the feature data, and the output is the recognized type data of the household item.

[0841] Step 6:

[0842] Based on the item type data received from the object recognition module, the server uses a size estimation algorithm to estimate the size of each item. This estimation uses known objects in the photo (e.g., the height of a door) as a reference. The input is the item type data, and the output is the estimated size data.

[0843] Step 7:

[0844] The server uses the estimated size data to estimate the general weight of each household item by referencing a database, such as a furniture catalog database or historical data. The input is size data, and the output is estimated weight data.

[0845] Step 8:

[0846] The server receives information about the moving date and destination entered by the user. The user enters this information through a dedicated application. The input is the moving date and destination information, and the output is this information stored on the server.

[0847] Step 9:

[0848] The server uses the estimate calculation module to calculate the moving costs based on the collected information (type of household goods, size, weight, moving time, and moving destination). The calculation includes basic shipping charges, additional charges based on the weight of household goods, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements. The input is all the collected data, and the output is the calculated moving costs.

[0849] Step 10:

[0850] The server sends the calculated moving costs to the user's device. The user can check the details and breakdown of the estimated costs through a dedicated application. The input is the calculated moving cost data, and the output is the estimated results displayed on the user's device.

[0851] Step 11:

[0852] At the same time, the server uses an emotion recognition engine to analyze the user's emotional data. It analyzes the voice data and facial expression data collected from the device's microphone and camera to recognize the user's emotions. The input is the emotional data collected from the device, and the output is the recognized emotional information.

[0853] Step 12:

[0854] Based on the emotions recognized by the emotion recognition engine, the server dynamically adjusts the content and messages displayed in the user interface. For example, if the user feels surprised or anxious, additional explanations or support messages are displayed. The input is the recognized emotional information, and the output is the adjusted user interface.

[0855] Step 13:

[0856] The user checks the quotation results through the application and takes necessary actions (for example, accepting the quotation or requesting additional information). The system executes the next action according to the user's actions. The input is the user's actions, and the output is the system's response to them.

[0857] (Application example 2)

[0858] 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."

[0859] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and laborious. Furthermore, if the estimate results are difficult for users to understand, they may not be able to provide sufficient support. This can cause stress for users when planning a move. Furthermore, the hassle of recognizing products and obtaining information when shopping face-to-face can also detract from the shopping experience.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0861] In this invention, the server includes means for receiving images of a room taken by a user with a terminal, means for analyzing the received images to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for recognizing the user's emotions by analyzing voice and facial expressions, and means for dynamically adjusting the user interface based on the recognized emotions. This enables users to obtain accurate estimates without hassle and receive appropriate support in real time, thereby improving the quality of their shopping experience.

[0862] "Images of a room taken by a user using a terminal" refers to image data of a room taken by a user using a device such as a smartphone or tablet.

[0863] "Means for receiving" refers to the function by which a server or cloud system receives data sent from a user.

[0864] "Means for analyzing and extracting the characteristics of household items" refers to a method that uses image analysis technology to identify characteristics such as the shape, color, and arrangement of furniture and household items from images of a room.

[0865] "Means for recognizing the type of household goods" refers to technology that identifies the type of specific furniture or home appliances, such as sofas or tables, based on extracted features.

[0866] "Size and weight estimation means" refers to an algorithm that calculates the size and weight of a recognized household item.

[0867] The "means for receiving information about the moving date and new address" refers to a function for collecting information such as the moving date and new address provided by the user.

[0868] "Means for calculating moving costs" refers to a calculation function that calculates the total cost of moving based on the collected information.

[0869] The "means for presenting the calculated moving costs to the user" refers to an interface that displays the estimated amount calculated by the server to the user.

[0870] "Means for recognizing a user's emotions by analyzing voice and facial expressions" refers to technology that uses the device's camera and microphone to analyze emotions from the user's voice and facial expressions.

[0871] "Means for dynamically adjusting the user interface based on recognized emotions" refers to a function that changes the displayed messages and layout depending on the user's emotional state.

[0872] "Means for recognizing products and visually presenting their location and information to the user" refers to technology that uses smart glasses or cameras to identify products in a store and display details of them to the user in real time.

[0873] "Means of providing additional recommended information and details to users based on product recognition information and user sentiment" refers to a function that provides detailed information about products that interest users and suggests related products.

[0874] This invention is a system that allows a user to take pictures of a room using a device such as a smartphone or tablet, and automatically provides a moving estimate based on those pictures. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service. Below, specific embodiments of the invention are described.

[0875] System configuration

[0876] The system consists of the following main components:

[0877] 1. Terminal

[0878] It is used by users to take and upload photos of their rooms, and can be a smartphone or tablet.

[0879] It has a built-in camera and microphone for emotion recognition.

[0880] 2. Server

[0881] Receives and analyzes photo data.

[0882] It is equipped with an image analysis module that uses deep learning.

[0883] It is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions and voice data.

[0884] Calculate the moving costs and present the results to the user.

[0885] Implementation Procedure

[0886] 1. User operations

[0887] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (e.g., transporting a piano) through the application.

[0888] 2. Processing on the server

[0889] The server passes the photo data received from the user to the image analysis module, which uses a deep learning-based segmentation algorithm to extract the characteristics of the household items in the room.Then, based on the extracted features, it identifies the type of household item.For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[0890] 3. Estimate the size and weight of your belongings

[0891] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door) as well as reference data provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0892] 4. Estimate calculation

[0893] The server uses the collected information to calculate the cost of the move, including the basic freight charge, additional charges based on the weight of the belongings, additional charges based on distance, seasonal variations, and additional charges based on special requirements.

[0894] 5. Implementing the Emotion Engine

[0895] When the user reviews the photos and quotes, the server uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize emotions. Based on the recognized emotions, the server dynamically adjusts the interface and displays additional explanations and payment options as needed.

[0896] Specific examples

[0897] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[0898] Prompt Sentence Examples

[0899] Input to the product recognition model: We train the model using a large number of images of shelves and products, with the following prompt: 'Identify and output the name, price, and details of the product in this image.'

[0900] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0901] Step 1:

[0902] The user takes a photo of the room with their smartphone, launches the dedicated application, selects the photo, and taps the upload button.

[0903] Input: A photo of a room taken with a smartphone.

[0904] Output: Image data sent to the server.

[0905] Specific operation: The user operates the application to select a photo and taps the upload button, which sends the image data to the server.

[0906] Step 2:

[0907] The server acquires the photo data received from the user and passes it to the image analysis module.

[0908] Input: Room image data sent by the user.

[0909] Output: Data input to the image analysis module.

[0910] Specific operation: The server stores the received photo data in memory and passes it to the image analysis module.

[0911] Step 3:

[0912] The image analysis module on the server uses deep learning to analyze the images and extract the characteristics of the household items in the room.

[0913] Input: Image data of the room input to the image analysis module.

[0914] Output: Extracted feature data of household items (e.g., furniture shape and layout).

[0915] How it works: The deep learning model uses a segmentation algorithm to identify furniture and appliances in the image and generate feature data.

[0916] Step 4:

[0917] Based on the extracted feature data, the server identifies the type of household item.

[0918] Input: Household property characteristics data.

[0919] Output: Identified household item type data (e.g. sofa, table, bed).

[0920] Specific operation: By referring to the feature data, the deep learning object recognition algorithm identifies the type of household item.

[0921] Step 5:

[0922] The server runs an algorithm to estimate the size and weight of recognized household items.

[0923] Input: Household item type data.

[0924] Output: Estimated household item size and weight data.

[0925] What it does: Using known objects (e.g., door height) or user-provided reference data, the size estimation algorithm calculates the size and weight of household items.

[0926] Step 6:

[0927] The user enters the moving date, new address, and any special requirements through a dedicated application, and then sends the data to the server.

[0928] Input: User-entered moving information, including when and where to move, and any special requirements.

[0929] Output: The moving information data sent to the server.

[0930] Specific operation: The user enters moving information into the application form and taps the submit button, which sends the data to the server.

[0931] Step 7:

[0932] The server calculates the moving expenses based on the received moving information data and the estimated size and weight data of the household goods.

[0933] Input: Moving information data, size and weight data of household goods.

[0934] Output: Calculated moving cost data.

[0935] Specific operation: The server calculates the basic transportation fee, additional fees based on the weight of the belongings, additional fees based on the distance, seasonal variations in fees, and additional fees based on special requirements, and then calculates the final moving cost.

[0936] Step 8:

[0937] When a user uploads a photo or checks the estimate results, the server uses the device's camera and microphone to collect the user's voice and facial expressions, which are then analyzed by the emotion engine.

[0938] Input: User voice and facial expression data collected by the device's camera and microphone.

[0939] Output: Recognized user emotional state data.

[0940] Specific operation: The emotion engine analyzes the tone of the voice data and facial expression data to classify the user's emotions.

[0941] Step 9:

[0942] The server dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion, providing additional explanations and payment instalment options as needed.

[0943] Input: Recognized emotional state data.

[0944] Output: Dynamically adjusted interface display and messages.

[0945] Specific behavior: If the user expresses surprise or dissatisfaction, an interface is generated that displays additional explanations and options.

[0946] Step 10:

[0947] The final calculated moving cost, along with the details and breakdown of the estimate, are displayed on the user's smartphone via a user interface tailored by the emotion engine's results.

[0948] Input: Calculated moving cost data, dynamically adjusted interface data.

[0949] Output: Quote details and breakdown displayed on the user's smartphone.

[0950] Specific operation: The server sends the calculation results and adjusted interface data to the user terminal and displays them for the user to check.

[0951] The above are the specific processing steps of the program for the system that realizes the application example.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Third embodiment]

[0956] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0957] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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."

[0968] The present invention is a system in which a user takes a photo of a room using a device such as a smartphone, and an AI automatically generates a moving estimate based on the photo. Specific embodiments of the system are described below.

[0969] User operations

[0970] First, the user takes a photo of the room they are moving into with their smartphone. Then, they launch a dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[0971] Processing on the server

[0972] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[0973] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[0974] Estimating the size and weight of your belongings

[0975] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[0976] Estimate calculation

[0977] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[0978] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[0979] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[0980] Distance-based surcharge: Charges are added based on the distance traveled.

[0981] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[0982] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[0983] Displaying the estimate results

[0984] Once the calculation is complete, the server sends the results to the user's device, where the estimate details and breakdown are displayed on the user's smartphone via a user interface, allowing the user to see a transparent estimate of moving costs.

[0985] Specific examples

[0986] For example, consider the case where a user moves from an apartment in the city to a house in the suburbs in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[0987] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[0988] The processing flow will be explained below.

[0989] Step 1:

[0990] The user takes a photo of the room with their smartphone.

[0991] Step 2:

[0992] The user launches the dedicated application and selects the photos they have taken.

[0993] Step 3:

[0994] The user taps the upload button in the application to send the photo data to the server.

[0995] Step 4:

[0996] The server passes the photo data received from the user to the image analysis module.

[0997] Step 5:

[0998] The image analysis module (server) analyzes the received image data and extracts the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[0999] Step 6:

[1000] The server passes the extracted features to the object recognition module.

[1001] Step 7:

[1002] The object recognition module (server) analyzes the features and recognizes the type of household item. In this step, a pre-trained object recognition model is used to identify sofas, beds, tables, etc. as examples.

[1003] Step 8:

[1004] The server inputs the recognized household items into the household item size and weight determination module.

[1005] Step 9:

[1006] The household item size and weight determination module (server) estimates the size of the object using known references in the image (e.g., the height of a door) and also references reference data provided by the user in advance.

[1007] Step 10:

[1008] Based on the size information of the household items, the server refers to a database and estimates the general weight. For example, the weight of a sofa estimated based on its size is set to 70 kg.

[1009] Step 11:

[1010] Within the application, users enter their moving date, new address, and any special requirements.

[1011] Step 12:

[1012] The terminal transmits the input information to the server.

[1013] Step 13:

[1014] The server passes the input information to the estimate calculation module.

[1015] Step 14:

[1016] The estimate calculation module (server) calculates the moving costs. The calculation includes the following factors:

[1017] Basic freight charge

[1018] Additional charges based on the weight of your belongings

[1019] Distance-based surcharge

[1020] Price fluctuations depending on the season

[1021] Additional charges based on special requirements

[1022] Step 15:

[1023] The server passes the calculated estimate to the user interface.

[1024] Step 16:

[1025] The terminal displays the estimate results received from the server.

[1026] Step 17:

[1027] The user interface (terminal) presents the user with quote details and breakdowns, such as basic freight charges, object weight charges, distance charges, time charges, and special request charges.

[1028] Step 18:

[1029] The user checks the estimate and makes further adjustments if necessary.

[1030] Example 1

[1031] 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."

[1032] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and prone to data errors due to subjective judgment. Furthermore, the transparency of estimates was not ensured, and there were often large discrepancies between the estimated cost and the actual moving costs. Furthermore, it was difficult to properly reflect special requirements and seasonal price fluctuations, which caused inconvenience to users.

[1033] 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.

[1034] In this invention, the server includes means for receiving images of a space taken by a user using an information processing device, means for analyzing the received images to extract features of objects, means for recognizing the type of object based on the extracted features, means for estimating the size and weight of the recognized object, means for receiving information on time and target entered by the user, means for calculating costs based on the received information, and means for presenting the calculated costs to the user. This allows users to quickly obtain accurate moving estimates simply by taking and submitting photos of their rooms. Furthermore, highly transparent estimates are provided based on user-entered information and automated analysis results, reducing discrepancies with actual moving costs. Furthermore, special requirements and seasonal price fluctuations are accurately reflected, providing greater convenience for users.

[1035] "User" refers to an individual or corporation that uses the system to request a moving estimate.

[1036] "Information processing device" refers to devices such as smartphones, tablets, and personal computers, and is equipment used to take images, input information, and transmit data.

[1037] "Images of the space" refers to photographs or video data showing the room to be moved and the situation within the room.

[1038] "Server" refers to a remote computer system that processes received images and data and performs recognition, estimation, and calculations.

[1039] "Features of an object" refers to attribute information such as the shape, color, and size of the furniture in the room to be moved.

[1040] "Type of object" refers to a category such as furniture or home appliance that the server identifies by analyzing the characteristics of the object.

[1041] "Size" refers to the dimensional information (e.g., width, height, depth) of the recognized object.

[1042] "Weight" refers to the mass information of an object estimated by the server.

[1043] "Time" refers to the specific date, time, or season when the user plans to move.

[1044] "Target information" refers to additional data that the user provides to the server, such as a new address or special requirements.

[1045] "Cost" refers to the total cost of the move, including the base fee, additional charges based on weight, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements.

[1046] "Presenting" refers to displaying or transmitting the cost calculated by the server to the user's information processing device.

[1047] The present invention is a system that allows a user to take an image of a space to be moved using an information processing device, and automatically calculates a moving estimate based on the image. Specific embodiments of the system are described below.

[1048] User operations

[1049] First, the user takes a photo of the room they are moving into using an information processing device such as a smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[1050] Processing on the server

[1051] The server passes the image data received from the user to the analysis module. This analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm using deep learning to identify the contours of objects and extract the features of each object. Expressive deep learning frameworks such as TensorFlow and PyTorch are used.

[1052] Recognition and classification of household items

[1053] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item (e.g., common household objects such as sofas, tables, beds, refrigerators, etc.).

[1054] Estimating the size and weight of your belongings

[1055] The server uses a size estimation algorithm to estimate the size of each recognized household item. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1056] Estimate calculation

[1057] The server then launches an estimate calculation module based on the collected information to calculate the moving costs, which includes the following factors:

[1058] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[1059] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[1060] Distance-based surcharge: Charges are added based on the distance traveled.

[1061] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[1062] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[1063] Displaying the estimate results

[1064] Once the server generates the calculation results, they are sent to the user's information processing device. The estimate details and breakdown are displayed on the user's smartphone via the user interface of a dedicated application. This allows the user to see a transparent estimate of moving costs.

[1065] Specific examples

[1066] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates their size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[1067] Prompt Sentence Examples

[1068] "I took photos of the apartment I'm moving into. Please explain the system I use to automatically calculate a moving estimate based on the photos. Please also include details about the specific steps and technology used."

[1069] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[1070] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1071] Step 1:

[1072] The user takes an image of the space to be moved into using an information processing device and launches a dedicated application. The user selects the image and taps the upload button. This sends the image data to the server. The input is the image data taken by the user, and the output is the image data sent to the server.

[1073] Step 2:

[1074] The server receives the image data sent by the user. The server receives the data securely using the HTTPS protocol and stores the received image data in a database. The input is the image data sent by the user, and the output is the image data stored in the database.

[1075] Step 3:

[1076] The server passes the received image data to the image analysis module. This module analyzes the image using a segmentation algorithm based on deep learning, identifies the contours of objects, and extracts their features. For example, TensorFlow is used. The input is image data read from the database, and the output is the extracted object feature data.

[1077] Step 4:

[1078] The server receives feature data from the image analysis module and passes it to the object recognition module, which uses these features to identify the type of household item. For example, it uses a machine learning model to recognize sofas, tables, beds, etc. The input is the feature data, and the output is the type data of the identified object.

[1079] Step 5:

[1080] The server runs a size estimation algorithm on the recognized object, calculating its size relative to known objects in the photo and using reference data provided by the user. Based on this, the server references a database to estimate the object's weight. The input is object type data and reference data, and the output is estimated size and weight data.

[1081] Step 6:

[1082] The server launches a quote calculation module based on all collected information. The quote calculation includes basic shipping charges, surcharges based on the weight of the belongings, surcharges based on distance, time-of-year variances, and surcharges based on special requirements. The inputs are the size and weight data of all objects in the room, the time of the move, the distance, and any special requirements, and the output is the total estimated cost.

[1083] Step 7:

[1084] The server sends the calculation results to the user's information processing device. The details and breakdown of the estimate are displayed on the user's smartphone via the user interface of a dedicated application. The input is the total estimated cost data, and the output is the estimate results displayed on the user's device.

[1085] The above are the specific processing steps of the program of this system.

[1086] (Application example 1)

[1087] 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."

[1088] Conventional moving quotation systems required users to manually input the type, size, and weight of household goods, which was time-consuming and labor-intensive. In addition, inventory management and item placement optimization at logistics centers were also done manually, resulting in inefficiency. There was a need to solve these problems and provide an automated, efficient quotation and inventory management system.

[1089] 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.

[1090] In this invention, the server includes means for receiving an image of a location taken by a user with a terminal, means for analyzing the received image to extract features of an item, means for recognizing the type of item based on the extracted features, means for estimating the size and weight of the recognized item, means for receiving information on the moving time and moving destination input by the user, means for calculating moving costs based on the received information, means for presenting the calculated moving costs to the user, means for automatically generating an inventory list based on the analyzed item information, and means for providing suggestions for optimizing inventory allocation based on the analyzed item information, thereby enabling the rapid provision of moving estimates and efficient inventory management at logistics centers.

[1091] A "user" is someone who uses the system to input information and receive results.

[1092] A "terminal" is a device used by a user, and is an apparatus that has functions such as taking photographs and transmitting data.

[1093] "Place images" are photographic data of a specific location or space taken by a user with a terminal.

[1094] A "server" is a computer system that analyzes received data and returns the results of its calculations to the user.

[1095] "Features of an item" are attributes for identifying an item, such as the shape, color, size, and weight of the item.

[1096] "Type of item" is the category to which the item belongs, such as table, chair, sofa, etc.

[1097] "Size" refers to the dimensions of an item, such as length, width, and height.

[1098] "Weight" is a quantity that represents the weight of an item.

[1099] "Moving date" is the date and time when the user desires to move the item.

[1100] "Destination" is the address or location of the destination to which the user wants to move the item.

[1101] "Information" is a general term for data entered by the user and data obtained by the server through analysis.

[1102] "Transportation costs" are the costs incurred to transport an item to a specific location.

[1103] An "inventory list" is a list of items managed as inventory that is automatically generated based on analyzed item information.

[1104] "Location optimization" refers to proposals and plans for efficiently locating inventory and goods.

[1105] The present invention is a system that automates and streamlines inventory management and item movement cost estimation at logistics centers. The system starts when a user takes a photo of the inventory in the logistics center using a device such as a smartphone.

[1106] Hardware and Software Configuration

[1107] User device: A device with a camera and internet connection, such as a smartphone or tablet, is used. The user uses this device to take pictures of the location and uploads them to the server via the application.

[1108] Server: A computer system with a powerful processor and GPU for deep learning, where deep learning models are run using Python and TensorFlow.

[1109] AI model: A deep learning model for recognizing the type, size, and weight of an item, specifically using object detection and segmentation algorithms.

[1110] Database: Stores data on common sizes and weights of items and references them to support estimation results.

[1111] Processing flow

[1112] 1. Take and upload an image

[1113] Users take photos of inventory in the logistics center with their smartphones and upload the images to the server via a dedicated application.

[1114] 2. Image analysis and object recognition

[1115] The server receives the uploaded image data and passes it to an AI model for analysis, which identifies the outline of the objects and extracts and recognizes the features of each object.

[1116] 3. Size and weight estimation

[1117] For each recognized item, the server uses a size estimation algorithm to estimate the size and weight of each item, using known objects in the photo and reference data previously provided by the user.

[1118] 4. Automatically generate inventory lists

[1119] Based on the analyzed product information, the server automatically generates an inventory list, which includes information such as product type, size, and weight.

[1120] 5. Calculating travel expenses

[1121] Based on the travel time and destination information entered by the user, the server calculates the travel cost, which includes a base fee, weight-based surcharges, distance charges, seasonally-dependent charges, and surcharges for special requirements.

[1122] 6. Inventory placement optimization

[1123] Based on the analyzed item information, the server provides suggestions for optimizing inventory allocation, thereby improving the efficiency of item allocation within the distribution center.

[1124] 7. Presenting the results to the user

[1125] The server sends the calculated travel costs and inventory placement optimization proposals to the user's device, where the user can check them.

[1126] Examples and prompts

[1127] For example, a user can take a photo of items on shelves in a logistics center and send it to a server via a dedicated application. The server analyzes the photo and identifies the type and weight of each item. Based on the results, it calculates transportation costs and makes suggestions for optimizing inventory placement. The user can then check this information to achieve efficient inventory management.

[1128] Example prompt sentence:

[1129] "We take photos of the warehouse interior and use an app to streamline inventory management. AI analyzes the type, size, and weight of items, automatically generates an inventory list, and suggests optimal placement."

[1130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1131] Step 1:

[1132] Users take photos of inventory in the logistics center and upload them to the server via a dedicated application.

[1133] Input: Image data taken with a smartphone

[1134] Output: Image data sent to the server

[1135] Step 2:

[1136] The server passes the received image data to the AI ​​model for analysis.

[1137] Input: Image data sent to the server

[1138] Output: Item feature data

[1139] Specific operation: Image data is input into a deep learning segmentation algorithm to extract the object's contours and features.

[1140] Step 3:

[1141] The server uses the extracted feature data to recognize the type of item.

[1142] Input: Item feature data

[1143] Output: Item type data

[1144] Specific operation: Analyzes feature data using a deep learning model to identify the type of item.

[1145] Step 4:

[1146] The server estimates the size and weight of the recognized item.

[1147] Input: Item type data

[1148] Output: Item size and weight data

[1149] Specific Behavior: Estimate the general size and weight of an item by referencing known objects or reference data.

[1150] Step 5:

[1151] The server automatically generates an inventory list based on the analyzed item information.

[1152] Input: Item size and weight data

[1153] Output: Inventory list data

[1154] Specific operation: Collects item information and automatically creates an inventory list.

[1155] Step 6:

[1156] The server receives information about the travel time and destination entered by the user.

[1157] Input: Information from the user about the time and destination of the trip

[1158] Output: Travel time and destination data

[1159] Specific operation: Information on travel time and destination entered by the user via the application is stored in a database.

[1160] Step 7:

[1161] The server calculates the travel cost based on the received information.

[1162] Input: Product information, time of movement and destination data

[1163] Output: Travel cost data

[1164] Specific operation: Calculates base charges, weight-based surcharges, distance charges, seasonally variable charges, and special requirement surcharges.

[1165] Step 8:

[1166] The server provides suggestions for optimizing inventory placement based on the analyzed product information.

[1167] Input: Product information, inventory list data

[1168] Output: Optimized inventory placement proposal

[1169] Specific operation: Based on the type and weight of the item, an efficient placement simulation is performed and suggestions are generated.

[1170] Step 9:

[1171] The server transmits the calculated travel costs and inventory placement optimization proposals to the user's terminal and presents the results to the user.

[1172] Input: Travel cost data, optimized inventory placement proposal

[1173] Output: Display data of travel cost details and placement proposals

[1174] Specific operation: Display details of travel costs and optimization suggestions to the user through the user interface.

[1175] 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.

[1176] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. In addition, by combining it with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service.

[1177] User operations

[1178] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch the dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[1179] Processing on the server

[1180] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[1181] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[1182] Estimating the size and weight of your belongings

[1183] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1184] Estimate calculation

[1185] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[1186] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[1187] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[1188] Distance-based surcharge: Charges are added based on the distance traveled.

[1189] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[1190] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[1191] Implementing the Emotion Engine

[1192] The present invention also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). When the user uploads photos or checks the estimate results, the emotion engine collects data from the device's microphone and camera.

[1193] Emotion-based interface adjustment

[1194] The emotion engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotions. For example, if the user is feeling doubtful or dissatisfied, additional explanations can be displayed. Conversely, if the user is satisfied, only a concise message can be displayed. Furthermore, if the user shows strong anxiety or dissatisfaction, the emotion engine can temporarily halt the estimation process and display a message urging reconfirmation.

[1195] Displaying the estimate results

[1196] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion engine also provides appropriate support based on the user's emotions.

[1197] Specific examples

[1198] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[1199] The present invention allows users to easily and quickly obtain moving estimates, ensuring transparency in fees and providing support that responds to the user's emotions, thereby aiming to make moving preparations go more smoothly.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The user takes a photo of the room with their smartphone.

[1203] Step 2:

[1204] The user launches the dedicated application and selects the photos they have taken.

[1205] Step 3:

[1206] The user taps the upload button in the application to send the photo data to the server.

[1207] Step 4:

[1208] The server passes the photo data received from the user to the image analysis module.

[1209] Step 5:

[1210] The image analysis module (server) analyzes the received image data to extract the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[1211] Step 6:

[1212] The server passes the extracted features to the object recognition module.

[1213] Step 7:

[1214] The object recognition module (server) analyzes the features and recognizes the type of household item, using a pre-trained object recognition model to identify sofas, beds, tables, etc.

[1215] Step 8:

[1216] The server inputs the recognized household items into a size and weight determination module.

[1217] Step 9:

[1218] The size and weight determination module (server) estimates the size of an object using known references in the image (e.g., the height of a door) and also references reference data previously provided by the user.

[1219] Step 10:

[1220] Based on the size information of the household item, the server refers to a database and estimates the general weight. For example, the estimated weight of a sofa based on its size is 70 kg.

[1221] Step 11:

[1222] Within the application, users enter their moving date, new address, and any special requirements.

[1223] Step 12:

[1224] The terminal transmits the input information to the server.

[1225] Step 13:

[1226] The server passes the input information to the estimate calculation module.

[1227] Step 14:

[1228] The quote calculation module (server) calculates the moving costs, including the following factors: basic freight charges, surcharges based on the weight of the belongings, surcharges based on distance, seasonal variations in charges, and surcharges based on special requirements.

[1229] Step 15:

[1230] The server passes the calculated estimate to the user interface.

[1231] Step 16:

[1232] The terminal displays the estimate results received from the server to the user.

[1233] Step 17:

[1234] The monitoring module (terminal) transmits the user's voice data and facial expression data to the emotion engine.

[1235] Step 18:

[1236] The emotion engine (server) analyzes the user's voice data and facial expression data to recognize the user's emotions.

[1237] Step 19:

[1238] The emotion engine adjusts the user interface display and messages based on the recognized emotion, for example, displaying additional explanations if the user shows a surprised expression.

[1239] Step 20:

[1240] The user interface (terminal) presents the adjusted display content and messages to the user.

[1241] Step 21:

[1242] The user checks the estimate results and the displayed messages and makes additional adjustments if necessary.

[1243] Example 2

[1244] 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."

[1245] Conventional moving estimate systems require users to manually input information about their belongings, moving dates, and destinations, which can be time-consuming and can result in inaccurate estimates. Furthermore, the user interface is often unintuitive and does not take into account the user's feelings or satisfaction, which can often cause frustration for users. This can lead to problems such as difficulty in understanding or agreeing with the estimate results.

[1246] 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 receiving an image of a room taken by a user with a terminal, means for analyzing the received image to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for analyzing the user's emotions using an emotion recognition engine, and means for dynamically adjusting the user interface based on the analyzed emotions. This allows the user to obtain an accurate and detailed estimate without any hassle, and the provision of an interface that corresponds to the user's emotions enables a more user-friendly experience.

[1247] A "user" is someone who uses the system to take photos of their room and request a moving estimate.

[1248] A "terminal" is a mobile information device such as a smartphone or tablet used by a user.

[1249] A "server" is a central computer system that receives, analyzes, and processes image data sent by users.

[1250] An "image analysis module" is a software or hardware component that processes received image data and extracts features of household items.

[1251] "Feature extraction" is the process of analyzing image data such as contours, shape, size, and color to extract important attributes.

[1252] An "object recognition module" is a software or hardware component that has the functionality to identify the type of household item based on extracted features.

[1253] "Size estimation" is an algorithm that determines the size of an item based on a known standard (e.g., door height).

[1254] "Weight estimation" is the process of calculating the weight of household goods, and is estimated based on past database information and size information.

[1255] The "moving cost calculation means" is a component that has a function of automatically calculating moving costs including basic transportation charges, additional charges, distance charges, seasonally variable charges, and special requirement charges.

[1256] An "emotion recognition engine" is a software or hardware component that analyzes a user's voice data and facial expression data to recognize emotions.

[1257] "User interface adaptation" is the process of dynamically changing display content and messages based on perceived user emotions.

[1258] "Deep learning" is a technology that uses multi-layered neural networks to analyze data and discover patterns and relationships.

[1259] A "segmentation algorithm" is an algorithm for dividing an image into multiple segments (regions) and identifying the contours of objects.

[1260] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. This invention also incorporates an emotion engine that recognizes the user's emotions, providing a more user-friendly interface and service.

[1261] Hardware and Software

[1262] Hardware

[1263] Smartphones and tablets (devices)

[1264] Server (Central Computer System)

[1265] Camera (built into the device)

[1266] Microphone (built into the device)

[1267] software

[1268] Dedicated application

[1269] Image Analysis Module

[1270] Deep learning models (e.g. TensorFlow, PyTorch)

[1271] Emotion recognition engine (e.g., OpenCV, AWS Rekognition)

[1272] Specific details of processing

[1273] User operations

[1274] The user activates the smartphone camera and takes a photo of the room to be moved. Then, they launch the dedicated application, select the photo, tap the upload button, and send the image data to the server. The user then enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[1275] Processing on the server

[1276] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data using a deep learning-based segmentation algorithm to extract the features of the household items present in the room. The extracted features are then passed to the object recognition module, which identifies the type of each item. For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[1277] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door), and also references a database to estimate the typical weight of each household item.

[1278] Based on the collected information, the server uses an estimate calculation module to calculate the moving costs, which include the following factors:

[1279] Basic freight charge: Rate based on distance traveled and basic service

[1280] Weight-based surcharge: A surcharge based on the total weight of your belongings.

[1281] Distance-based surcharge: Charges are added based on the distance traveled

[1282] Seasonal price fluctuations: Prices vary depending on peak and off-peak seasons.

[1283] Extra charges based on special requirements: Extra charges based on special requests entered by the user (e.g. piano transport fees)

[1284] Furthermore, an emotion recognition engine is used to analyze the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). The emotion recognition engine collects data from the device's microphone and camera when the user uploads photos or checks the estimate results.

[1285] Emotion-based interface adjustment

[1286] The emotion recognition engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion. For example, if the user is dissatisfied or uncertain, the system can alleviate the user's anxiety by providing additional explanations or payment options in installments. Conversely, if the user is satisfied, the system can display only a concise message.

[1287] Displaying the estimate results

[1288] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion recognition engine provides appropriate support based on the user's emotions.

[1289] Specific examples

[1290] For example, consider a case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion recognition engine detects this and alleviates the user's anxiety by offering additional explanations and the option to pay in installments.

[1291] Prompt Sentence Examples

[1292] "Describe a system that takes a photo of a room and automatically calculates an estimate for moving, taking into account the time of the move, the destination, and any special requirements. Also include a requirement to recognize the user's emotions and display an appropriate interface."

[1293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1294] Step 1:

[1295] A user takes a photo of a room using a smartphone. The user activates the smartphone camera and takes a photo that shows the entire room. At this time, the user should be conscious of taking a photo that clearly shows the furniture.

[1296] Step 2:

[1297] The user launches the dedicated application, selects the photo they have taken, and taps the upload button. This sends the image data to the server. The input is the photo data taken by the user, and the output is the image data transferred to the server.

[1298] Step 3:

[1299] The server receives the photo data sent by the user. The server first checks the format and content of the sent data and prepares to pass it to the appropriate image analysis module. The input is the image data sent by the user, and the output is the image data passed to the image analysis module.

[1300] Step 4:

[1301] The server passes the received image data to the image analysis module, which then analyzes the image using a segmentation algorithm based on deep learning. Specifically, it uses TensorFlow and PyTorch to extract the contours and features of household items in the image. The input is the image data, and the output is the extracted feature data.

[1302] Step 5:

[1303] The server receives the feature data extracted from the image analysis module and passes it to the object recognition module. The object recognition module identifies the type of household item based on this feature data. For example, it recognizes sofas, tables, beds, refrigerators, etc. The input is the feature data, and the output is the recognized type data of the household item.

[1304] Step 6:

[1305] Based on the item type data received from the object recognition module, the server uses a size estimation algorithm to estimate the size of each item. This estimation uses known objects in the photo (e.g., the height of a door) as a reference. The input is the item type data, and the output is the estimated size data.

[1306] Step 7:

[1307] The server uses the estimated size data to estimate the general weight of each household item by referencing a database, such as a furniture catalog database or historical data. The input is size data, and the output is estimated weight data.

[1308] Step 8:

[1309] The server receives information about the moving date and destination entered by the user. The user enters this information through a dedicated application. The input is the moving date and destination information, and the output is this information stored on the server.

[1310] Step 9:

[1311] The server uses the estimate calculation module to calculate the moving costs based on the collected information (type of household goods, size, weight, moving time, and moving destination). The calculation includes basic shipping charges, additional charges based on the weight of household goods, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements. The input is all the collected data, and the output is the calculated moving costs.

[1312] Step 10:

[1313] The server sends the calculated moving costs to the user's device. The user can check the details and breakdown of the estimated costs through a dedicated application. The input is the calculated moving cost data, and the output is the estimated results displayed on the user's device.

[1314] Step 11:

[1315] At the same time, the server uses an emotion recognition engine to analyze the user's emotional data. It analyzes the voice data and facial expression data collected from the device's microphone and camera to recognize the user's emotions. The input is the emotional data collected from the device, and the output is the recognized emotional information.

[1316] Step 12:

[1317] Based on the emotions recognized by the emotion recognition engine, the server dynamically adjusts the content and messages displayed in the user interface. For example, if the user feels surprised or anxious, additional explanations or support messages are displayed. The input is the recognized emotional information, and the output is the adjusted user interface.

[1318] Step 13:

[1319] The user checks the quotation results through the application and takes necessary actions (for example, accepting the quotation or requesting additional information). The system executes the next action according to the user's actions. The input is the user's actions, and the output is the system's response to them.

[1320] (Application example 2)

[1321] 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."

[1322] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and laborious. Furthermore, if the estimate results are difficult for users to understand, they may not be able to provide sufficient support. This can cause stress for users when planning a move. Furthermore, the hassle of recognizing products and obtaining information when shopping face-to-face can also detract from the shopping experience.

[1323] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1324] In this invention, the server includes means for receiving images of a room taken by a user with a terminal, means for analyzing the received images to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for recognizing the user's emotions by analyzing voice and facial expressions, and means for dynamically adjusting the user interface based on the recognized emotions. This enables users to obtain accurate estimates without hassle and receive appropriate support in real time, thereby improving the quality of their shopping experience.

[1325] "Images of a room taken by a user using a terminal" refers to image data of a room taken by a user using a device such as a smartphone or tablet.

[1326] "Means for receiving" refers to the function by which a server or cloud system receives data sent from a user.

[1327] "Means for analyzing and extracting the characteristics of household items" refers to a method that uses image analysis technology to identify characteristics such as the shape, color, and arrangement of furniture and household items from images of a room.

[1328] "Means for recognizing the type of household goods" refers to technology that identifies the type of specific furniture or home appliances, such as sofas or tables, based on extracted features.

[1329] "Size and weight estimation means" refers to an algorithm that calculates the size and weight of a recognized household item.

[1330] The "means for receiving information about the moving date and new address" refers to a function for collecting information such as the moving date and new address provided by the user.

[1331] "Means for calculating moving costs" refers to a calculation function that calculates the total cost of moving based on the collected information.

[1332] The "means for presenting the calculated moving costs to the user" refers to an interface that displays the estimated amount calculated by the server to the user.

[1333] "Means for recognizing a user's emotions by analyzing voice and facial expressions" refers to technology that uses the device's camera and microphone to analyze emotions from the user's voice and facial expressions.

[1334] "Means for dynamically adjusting the user interface based on recognized emotions" refers to a function that changes the displayed messages and layout depending on the user's emotional state.

[1335] "Means for recognizing products and visually presenting their location and information to the user" refers to technology that uses smart glasses or cameras to identify products in a store and display details of them to the user in real time.

[1336] "Means of providing additional recommended information and details to users based on product recognition information and user sentiment" refers to a function that provides detailed information about products that interest users and suggests related products.

[1337] This invention is a system that allows a user to take pictures of a room using a device such as a smartphone or tablet, and automatically provides a moving estimate based on those pictures. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service. Below, specific embodiments of the invention are described.

[1338] System configuration

[1339] The system consists of the following main components:

[1340] 1. Terminal

[1341] It is used by users to take and upload photos of their rooms, and can be a smartphone or tablet.

[1342] It has a built-in camera and microphone for emotion recognition.

[1343] 2. Server

[1344] Receives and analyzes photo data.

[1345] It is equipped with an image analysis module that uses deep learning.

[1346] It is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions and voice data.

[1347] Calculate the moving costs and present the results to the user.

[1348] Implementation Procedure

[1349] 1. User operations

[1350] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (e.g., transporting a piano) through the application.

[1351] 2. Processing on the server

[1352] The server passes the photo data received from the user to the image analysis module, which uses a deep learning-based segmentation algorithm to extract the characteristics of the household items in the room.Then, based on the extracted features, it identifies the type of household item.For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[1353] 3. Estimate the size and weight of your belongings

[1354] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door) as well as reference data provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1355] 4. Estimate calculation

[1356] The server uses the collected information to calculate the cost of the move, including the basic freight charge, additional charges based on the weight of the belongings, additional charges based on distance, seasonal variations, and additional charges based on special requirements.

[1357] 5. Implementing the Emotion Engine

[1358] When the user reviews the photos and quotes, the server uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize emotions. Based on the recognized emotions, the server dynamically adjusts the interface and displays additional explanations and payment options as needed.

[1359] Specific examples

[1360] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[1361] Prompt Sentence Examples

[1362] Input to the product recognition model: We train the model using a large number of images of shelves and products, with the following prompt: 'Identify and output the name, price, and details of the product in this image.'

[1363] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1364] Step 1:

[1365] The user takes a photo of the room with their smartphone, launches the dedicated application, selects the photo, and taps the upload button.

[1366] Input: A photo of a room taken with a smartphone.

[1367] Output: Image data sent to the server.

[1368] Specific operation: The user operates the application to select a photo and taps the upload button, which sends the image data to the server.

[1369] Step 2:

[1370] The server acquires the photo data received from the user and passes it to the image analysis module.

[1371] Input: Room image data sent by the user.

[1372] Output: Data input to the image analysis module.

[1373] Specific operation: The server stores the received photo data in memory and passes it to the image analysis module.

[1374] Step 3:

[1375] The image analysis module on the server uses deep learning to analyze the images and extract the characteristics of the household items in the room.

[1376] Input: Image data of the room input to the image analysis module.

[1377] Output: Extracted feature data of household items (e.g., furniture shape and layout).

[1378] How it works: The deep learning model uses a segmentation algorithm to identify furniture and appliances in the image and generate feature data.

[1379] Step 4:

[1380] Based on the extracted feature data, the server identifies the type of household item.

[1381] Input: Household property characteristics data.

[1382] Output: Identified household item type data (e.g. sofa, table, bed).

[1383] Specific operation: By referring to the feature data, the deep learning object recognition algorithm identifies the type of household item.

[1384] Step 5:

[1385] The server runs an algorithm to estimate the size and weight of recognized household items.

[1386] Input: Household item type data.

[1387] Output: Estimated household item size and weight data.

[1388] What it does: Using known objects (e.g., door height) or user-provided reference data, the size estimation algorithm calculates the size and weight of household items.

[1389] Step 6:

[1390] The user enters the moving date, new address, and any special requirements through a dedicated application, and then sends the data to the server.

[1391] Input: User-entered moving information, including when and where to move, and any special requirements.

[1392] Output: The moving information data sent to the server.

[1393] Specific operation: The user enters moving information into the application form and taps the submit button, which sends the data to the server.

[1394] Step 7:

[1395] The server calculates the moving expenses based on the received moving information data and the estimated size and weight data of the household goods.

[1396] Input: Moving information data, size and weight data of household goods.

[1397] Output: Calculated moving cost data.

[1398] Specific operation: The server calculates the basic transportation fee, additional fees based on the weight of the belongings, additional fees based on the distance, seasonal variations in fees, and additional fees based on special requirements, and then calculates the final moving cost.

[1399] Step 8:

[1400] When a user uploads a photo or checks the estimate results, the server uses the device's camera and microphone to collect the user's voice and facial expressions, which are then analyzed by the emotion engine.

[1401] Input: User voice and facial expression data collected by the device's camera and microphone.

[1402] Output: Recognized user emotional state data.

[1403] Specific operation: The emotion engine analyzes the tone of the voice data and facial expression data to classify the user's emotions.

[1404] Step 9:

[1405] The server dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion, providing additional explanations and payment instalment options as needed.

[1406] Input: Recognized emotional state data.

[1407] Output: Dynamically adjusted interface display and messages.

[1408] Specific behavior: If the user expresses surprise or dissatisfaction, an interface is generated that displays additional explanations and options.

[1409] Step 10:

[1410] The final calculated moving cost, along with the details and breakdown of the estimate, are displayed on the user's smartphone via a user interface tailored by the emotion engine's results.

[1411] Input: Calculated moving cost data, dynamically adjusted interface data.

[1412] Output: Quote details and breakdown displayed on the user's smartphone.

[1413] Specific operation: The server sends the calculation results and adjusted interface data to the user terminal and displays them for the user to check.

[1414] The above are the specific processing steps of the program for the system that realizes the application example.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] [Fourth embodiment]

[1419] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1420] 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.

[1421] 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).

[1422] 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.

[1423] 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.

[1424] 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).

[1425] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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."

[1432] The present invention is a system in which a user takes a photo of a room using a device such as a smartphone, and an AI automatically generates a moving estimate based on the photo. Specific embodiments of the system are described below.

[1433] User operations

[1434] First, the user takes a photo of the room they are moving into with their smartphone. Then, they launch a dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[1435] Processing on the server

[1436] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[1437] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[1438] Estimating the size and weight of your belongings

[1439] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1440] Estimate calculation

[1441] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[1442] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[1443] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[1444] Distance-based surcharge: Charges are added based on the distance traveled.

[1445] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[1446] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[1447] Displaying the estimate results

[1448] Once the calculation is complete, the server sends the results to the user's device, where the estimate details and breakdown are displayed on the user's smartphone via a user interface, allowing the user to see a transparent estimate of moving costs.

[1449] Specific examples

[1450] For example, consider the case where a user moves from an apartment in the city to a house in the suburbs in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[1451] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[1452] The processing flow will be explained below.

[1453] Step 1:

[1454] The user takes a photo of the room with their smartphone.

[1455] Step 2:

[1456] The user launches the dedicated application and selects the photos they have taken.

[1457] Step 3:

[1458] The user taps the upload button in the application to send the photo data to the server.

[1459] Step 4:

[1460] The server passes the photo data received from the user to the image analysis module.

[1461] Step 5:

[1462] The image analysis module (server) analyzes the received image data and extracts the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[1463] Step 6:

[1464] The server passes the extracted features to the object recognition module.

[1465] Step 7:

[1466] The object recognition module (server) analyzes the features and recognizes the type of household item. In this step, a pre-trained object recognition model is used to identify sofas, beds, tables, etc. as examples.

[1467] Step 8:

[1468] The server inputs the recognized household items into the household item size and weight determination module.

[1469] Step 9:

[1470] The household item size and weight determination module (server) estimates the size of the object using known references in the image (e.g., the height of a door) and also references reference data provided by the user in advance.

[1471] Step 10:

[1472] Based on the size information of the household items, the server refers to a database and estimates the general weight. For example, the weight of a sofa estimated based on its size is set to 70 kg.

[1473] Step 11:

[1474] Within the application, users enter their moving date, new address, and any special requirements.

[1475] Step 12:

[1476] The terminal transmits the input information to the server.

[1477] Step 13:

[1478] The server passes the input information to the estimate calculation module.

[1479] Step 14:

[1480] The estimate calculation module (server) calculates the moving costs. The calculation includes the following factors:

[1481] Basic freight charge

[1482] Additional charges based on the weight of your belongings

[1483] Distance-based surcharge

[1484] Price fluctuations depending on the season

[1485] Additional charges based on special requirements

[1486] Step 15:

[1487] The server passes the calculated estimate to the user interface.

[1488] Step 16:

[1489] The terminal displays the estimate results received from the server.

[1490] Step 17:

[1491] The user interface (terminal) presents the user with quote details and breakdowns, such as basic freight charges, object weight charges, distance charges, time charges, and special request charges.

[1492] Step 18:

[1493] The user checks the estimate and makes further adjustments if necessary.

[1494] Example 1

[1495] 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."

[1496] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and prone to data errors due to subjective judgment. Furthermore, the transparency of estimates was not ensured, and there were often large discrepancies between the estimated cost and the actual moving costs. Furthermore, it was difficult to properly reflect special requirements and seasonal price fluctuations, which caused inconvenience to users.

[1497] 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.

[1498] In this invention, the server includes means for receiving images of a space taken by a user using an information processing device, means for analyzing the received images to extract features of objects, means for recognizing the type of object based on the extracted features, means for estimating the size and weight of the recognized object, means for receiving information on time and target entered by the user, means for calculating costs based on the received information, and means for presenting the calculated costs to the user. This allows users to quickly obtain accurate moving estimates simply by taking and submitting photos of their rooms. Furthermore, highly transparent estimates are provided based on user-entered information and automated analysis results, reducing discrepancies with actual moving costs. Furthermore, special requirements and seasonal price fluctuations are accurately reflected, providing greater convenience for users.

[1499] "User" refers to an individual or corporation that uses the system to request a moving estimate.

[1500] "Information processing device" refers to devices such as smartphones, tablets, and personal computers, and is equipment used to take images, input information, and transmit data.

[1501] "Images of the space" refers to photographs or video data showing the room to be moved and the situation within the room.

[1502] "Server" refers to a remote computer system that processes received images and data and performs recognition, estimation, and calculations.

[1503] "Features of an object" refers to attribute information such as the shape, color, and size of the furniture in the room to be moved.

[1504] "Type of object" refers to a category such as furniture or home appliance that the server identifies by analyzing the characteristics of the object.

[1505] "Size" refers to the dimensional information (e.g., width, height, depth) of the recognized object.

[1506] "Weight" refers to the mass information of an object estimated by the server.

[1507] "Time" refers to the specific date, time, or season when the user plans to move.

[1508] "Target information" refers to additional data that the user provides to the server, such as a new address or special requirements.

[1509] "Cost" refers to the total cost of the move, including the base fee, additional charges based on weight, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements.

[1510] "Presenting" refers to displaying or transmitting the cost calculated by the server to the user's information processing device.

[1511] The present invention is a system that allows a user to take an image of a space to be moved using an information processing device, and automatically calculates a moving estimate based on the image. Specific embodiments of the system are described below.

[1512] User operations

[1513] First, the user takes a photo of the room they are moving into using an information processing device such as a smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[1514] Processing on the server

[1515] The server passes the image data received from the user to the analysis module. This analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm using deep learning to identify the contours of objects and extract the features of each object. Expressive deep learning frameworks such as TensorFlow and PyTorch are used.

[1516] Recognition and classification of household items

[1517] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item (e.g., common household objects such as sofas, tables, beds, refrigerators, etc.).

[1518] Estimating the size and weight of your belongings

[1519] The server uses a size estimation algorithm to estimate the size of each recognized household item. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1520] Estimate calculation

[1521] The server then launches an estimate calculation module based on the collected information to calculate the moving costs, which includes the following factors:

[1522] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[1523] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[1524] Distance-based surcharge: Charges are added based on the distance traveled.

[1525] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[1526] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[1527] Displaying the estimate results

[1528] Once the server generates the calculation results, they are sent to the user's information processing device. The estimate details and breakdown are displayed on the user's smartphone via the user interface of a dedicated application. This allows the user to see a transparent estimate of moving costs.

[1529] Specific examples

[1530] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates their size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate totaling 150,000 yen.

[1531] Prompt Sentence Examples

[1532] "I took photos of the apartment I'm moving into. Please explain the system I use to automatically calculate a moving estimate based on the photos. Please also include details about the specific steps and technology used."

[1533] The present invention aims to enable users to easily and quickly obtain moving estimates, ensure transparency in fees, and facilitate smooth preparations for moving.

[1534] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1535] Step 1:

[1536] The user takes an image of the space to be moved into using an information processing device and launches a dedicated application. The user selects the image and taps the upload button. This sends the image data to the server. The input is the image data taken by the user, and the output is the image data sent to the server.

[1537] Step 2:

[1538] The server receives the image data sent by the user. The server receives the data securely using the HTTPS protocol and stores the received image data in a database. The input is the image data sent by the user, and the output is the image data stored in the database.

[1539] Step 3:

[1540] The server passes the received image data to the image analysis module. This module analyzes the image using a segmentation algorithm based on deep learning, identifies the contours of objects, and extracts their features. For example, TensorFlow is used. The input is image data read from the database, and the output is the extracted object feature data.

[1541] Step 4:

[1542] The server receives feature data from the image analysis module and passes it to the object recognition module, which uses these features to identify the type of household item. For example, it uses a machine learning model to recognize sofas, tables, beds, etc. The input is the feature data, and the output is the type data of the identified object.

[1543] Step 5:

[1544] The server runs a size estimation algorithm on the recognized object, calculating its size relative to known objects in the photo and using reference data provided by the user. Based on this, the server references a database to estimate the object's weight. The input is object type data and reference data, and the output is estimated size and weight data.

[1545] Step 6:

[1546] The server launches a quote calculation module based on all collected information. The quote calculation includes basic shipping charges, surcharges based on the weight of the belongings, surcharges based on distance, time-of-year variances, and surcharges based on special requirements. The inputs are the size and weight data of all objects in the room, the time of the move, the distance, and any special requirements, and the output is the total estimated cost.

[1547] Step 7:

[1548] The server sends the calculation results to the user's information processing device. The details and breakdown of the estimate are displayed on the user's smartphone via the user interface of a dedicated application. The input is the total estimated cost data, and the output is the estimate results displayed on the user's device.

[1549] The above are the specific processing steps of the program of this system.

[1550] (Application example 1)

[1551] 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."

[1552] Conventional moving quotation systems required users to manually input the type, size, and weight of household goods, which was time-consuming and labor-intensive. In addition, inventory management and item placement optimization at logistics centers were also done manually, resulting in inefficiency. There was a need to solve these problems and provide an automated, efficient quotation and inventory management system.

[1553] 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.

[1554] In this invention, the server includes means for receiving an image of a location taken by a user with a terminal, means for analyzing the received image to extract features of an item, means for recognizing the type of item based on the extracted features, means for estimating the size and weight of the recognized item, means for receiving information on the moving time and moving destination input by the user, means for calculating moving costs based on the received information, means for presenting the calculated moving costs to the user, means for automatically generating an inventory list based on the analyzed item information, and means for providing suggestions for optimizing inventory allocation based on the analyzed item information, thereby enabling the rapid provision of moving estimates and efficient inventory management at logistics centers.

[1555] A "user" is someone who uses the system to input information and receive results.

[1556] A "terminal" is a device used by a user, and is an apparatus that has functions such as taking photographs and transmitting data.

[1557] "Place images" are photographic data of a specific location or space taken by a user with a terminal.

[1558] A "server" is a computer system that analyzes received data and returns the results of its calculations to the user.

[1559] "Features of an item" are attributes for identifying an item, such as the shape, color, size, and weight of the item.

[1560] "Type of item" is the category to which the item belongs, such as table, chair, sofa, etc.

[1561] "Size" refers to the dimensions of an item, such as length, width, and height.

[1562] "Weight" is a quantity that represents the weight of an item.

[1563] "Moving date" is the date and time when the user desires to move the item.

[1564] "Destination" is the address or location of the destination to which the user wants to move the item.

[1565] "Information" is a general term for data entered by the user and data obtained by the server through analysis.

[1566] "Transportation costs" are the costs incurred to transport an item to a specific location.

[1567] An "inventory list" is a list of items managed as inventory that is automatically generated based on analyzed item information.

[1568] "Location optimization" refers to proposals and plans for efficiently locating inventory and goods.

[1569] The present invention is a system that automates and streamlines inventory management and item movement cost estimation at logistics centers. The system starts when a user takes a photo of the inventory in the logistics center using a device such as a smartphone.

[1570] Hardware and Software Configuration

[1571] User device: A device with a camera and internet connection, such as a smartphone or tablet, is used. The user uses this device to take pictures of the location and uploads them to the server via the application.

[1572] Server: A computer system with a powerful processor and GPU for deep learning, where deep learning models are run using Python and TensorFlow.

[1573] AI model: A deep learning model for recognizing the type, size, and weight of an item, specifically using object detection and segmentation algorithms.

[1574] Database: Stores data on common sizes and weights of items and references them to support estimation results.

[1575] Processing flow

[1576] 1. Take and upload an image

[1577] Users take photos of inventory in the logistics center with their smartphones and upload the images to the server via a dedicated application.

[1578] 2. Image analysis and object recognition

[1579] The server receives the uploaded image data and passes it to an AI model for analysis, which identifies the outline of the objects and extracts and recognizes the features of each object.

[1580] 3. Size and weight estimation

[1581] For each recognized item, the server uses a size estimation algorithm to estimate the size and weight of each item, using known objects in the photo and reference data previously provided by the user.

[1582] 4. Automatically generate inventory lists

[1583] Based on the analyzed product information, the server automatically generates an inventory list, which includes information such as product type, size, and weight.

[1584] 5. Calculating travel expenses

[1585] Based on the travel time and destination information entered by the user, the server calculates the travel cost, which includes a base fee, weight-based surcharges, distance charges, seasonally-dependent charges, and surcharges for special requirements.

[1586] 6. Inventory placement optimization

[1587] Based on the analyzed item information, the server provides suggestions for optimizing inventory allocation, thereby improving the efficiency of item allocation within the distribution center.

[1588] 7. Presenting the results to the user

[1589] The server sends the calculated travel costs and inventory placement optimization proposals to the user's device, where the user can check them.

[1590] Examples and prompts

[1591] For example, a user can take a photo of items on shelves in a logistics center and send it to a server via a dedicated application. The server analyzes the photo and identifies the type and weight of each item. Based on the results, it calculates transportation costs and makes suggestions for optimizing inventory placement. The user can then check this information to achieve efficient inventory management.

[1592] Example prompt sentence:

[1593] "We take photos of the warehouse interior and use an app to streamline inventory management. AI analyzes the type, size, and weight of items, automatically generates an inventory list, and suggests optimal placement."

[1594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1595] Step 1:

[1596] Users take photos of inventory in the logistics center and upload them to the server via a dedicated application.

[1597] Input: Image data taken with a smartphone

[1598] Output: Image data sent to the server

[1599] Step 2:

[1600] The server passes the received image data to the AI ​​model for analysis.

[1601] Input: Image data sent to the server

[1602] Output: Item feature data

[1603] Specific operation: Image data is input into a deep learning segmentation algorithm to extract the object's contours and features.

[1604] Step 3:

[1605] The server uses the extracted feature data to recognize the type of item.

[1606] Input: Item feature data

[1607] Output: Item type data

[1608] Specific operation: Analyzes feature data using a deep learning model to identify the type of item.

[1609] Step 4:

[1610] The server estimates the size and weight of the recognized item.

[1611] Input: Item type data

[1612] Output: Item size and weight data

[1613] Specific Behavior: Estimate the general size and weight of an item by referencing known objects or reference data.

[1614] Step 5:

[1615] The server automatically generates an inventory list based on the analyzed item information.

[1616] Input: Item size and weight data

[1617] Output: Inventory list data

[1618] Specific operation: Collects item information and automatically creates an inventory list.

[1619] Step 6:

[1620] The server receives information about the travel time and destination entered by the user.

[1621] Input: Information from the user about the time and destination of the trip

[1622] Output: Travel time and destination data

[1623] Specific operation: Information on travel time and destination entered by the user via the application is stored in a database.

[1624] Step 7:

[1625] The server calculates the travel cost based on the received information.

[1626] Input: Product information, time of movement and destination data

[1627] Output: Travel cost data

[1628] Specific operation: Calculates base charges, weight-based surcharges, distance charges, seasonally variable charges, and special requirement surcharges.

[1629] Step 8:

[1630] The server provides suggestions for optimizing inventory placement based on the analyzed product information.

[1631] Input: Product information, inventory list data

[1632] Output: Optimized inventory placement proposal

[1633] Specific operation: Based on the type and weight of the item, an efficient placement simulation is performed and suggestions are generated.

[1634] Step 9:

[1635] The server transmits the calculated travel costs and inventory placement optimization proposals to the user's terminal and presents the results to the user.

[1636] Input: Travel cost data, optimized inventory placement proposal

[1637] Output: Display data of travel cost details and placement proposals

[1638] Specific operation: Display details of travel costs and optimization suggestions to the user through the user interface.

[1639] 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.

[1640] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. In addition, by combining it with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service.

[1641] User operations

[1642] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch the dedicated application, select the photo they took, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (such as transporting a piano) through the application.

[1643] Processing on the server

[1644] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data and extracts the characteristics of the household items in the room. Specifically, it uses a segmentation algorithm based on deep learning to identify the contours of objects and extract the characteristics of each household item.

[1645] The extracted features are then passed to an object recognition module, which uses these features to identify the type of household item, for example recognizing common household objects such as sofas, tables, beds, refrigerators, etc.

[1646] Estimating the size and weight of your belongings

[1647] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object. This estimation uses known objects in the photo as references (e.g., the height of a door) and also uses reference data previously provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1648] Estimate calculation

[1649] Based on the collected information, the quote calculation module will calculate the moving costs, which will include the following factors:

[1650] Basic Freight Charge: This is a charge based on distance traveled and basic services.

[1651] Weight-based surcharge: This is an additional charge based on the total weight of your belongings.

[1652] Distance-based surcharge: Charges are added based on the distance traveled.

[1653] Seasonal pricing: Seasonal pricing applies depending on peak and off-peak seasons.

[1654] Extra charges based on special requirements: Extra charges may apply based on special requests entered by the user (e.g., piano transport fees).

[1655] Implementing the Emotion Engine

[1656] The present invention also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). When the user uploads photos or checks the estimate results, the emotion engine collects data from the device's microphone and camera.

[1657] Emotion-based interface adjustment

[1658] The emotion engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotions. For example, if the user is feeling doubtful or dissatisfied, additional explanations can be displayed. Conversely, if the user is satisfied, only a concise message can be displayed. Furthermore, if the user shows strong anxiety or dissatisfaction, the emotion engine can temporarily halt the estimation process and display a message urging reconfirmation.

[1659] Displaying the estimate results

[1660] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion engine also provides appropriate support based on the user's emotions.

[1661] Specific examples

[1662] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[1663] The present invention allows users to easily and quickly obtain moving estimates, ensuring transparency in fees and providing support that responds to the user's emotions, thereby aiming to make moving preparations go more smoothly.

[1664] The processing flow will be explained below.

[1665] Step 1:

[1666] The user takes a photo of the room with their smartphone.

[1667] Step 2:

[1668] The user launches the dedicated application and selects the photos they have taken.

[1669] Step 3:

[1670] The user taps the upload button in the application to send the photo data to the server.

[1671] Step 4:

[1672] The server passes the photo data received from the user to the image analysis module.

[1673] Step 5:

[1674] The image analysis module (server) analyzes the received image data to extract the features of the household items. At this stage, a deep learning-based segmentation algorithm is used to identify the contours of the objects.

[1675] Step 6:

[1676] The server passes the extracted features to the object recognition module.

[1677] Step 7:

[1678] The object recognition module (server) analyzes the features and recognizes the type of household item, using a pre-trained object recognition model to identify sofas, beds, tables, etc.

[1679] Step 8:

[1680] The server inputs the recognized household items into a size and weight determination module.

[1681] Step 9:

[1682] The size and weight determination module (server) estimates the size of an object using known references in the image (e.g., the height of a door) and also references reference data previously provided by the user.

[1683] Step 10:

[1684] Based on the size information of the household item, the server refers to a database and estimates the general weight. For example, the estimated weight of a sofa based on its size is 70 kg.

[1685] Step 11:

[1686] Within the application, users enter their moving date, new address, and any special requirements.

[1687] Step 12:

[1688] The terminal transmits the input information to the server.

[1689] Step 13:

[1690] The server passes the input information to the estimate calculation module.

[1691] Step 14:

[1692] The quote calculation module (server) calculates the moving costs, including the following factors: basic freight charges, surcharges based on the weight of the belongings, surcharges based on distance, seasonal variations in charges, and surcharges based on special requirements.

[1693] Step 15:

[1694] The server passes the calculated estimate to the user interface.

[1695] Step 16:

[1696] The terminal displays the estimate results received from the server to the user.

[1697] Step 17:

[1698] The monitoring module (terminal) transmits the user's voice data and facial expression data to the emotion engine.

[1699] Step 18:

[1700] The emotion engine (server) analyzes the user's voice data and facial expression data to recognize the user's emotions.

[1701] Step 19:

[1702] The emotion engine adjusts the user interface display and messages based on the recognized emotion, for example, displaying additional explanations if the user shows a surprised expression.

[1703] Step 20:

[1704] The user interface (terminal) presents the adjusted display content and messages to the user.

[1705] Step 21:

[1706] The user checks the estimate results and the displayed messages and makes additional adjustments if necessary.

[1707] Example 2

[1708] 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."

[1709] Conventional moving estimate systems require users to manually input information about their belongings, moving dates, and destinations, which can be time-consuming and can result in inaccurate estimates. Furthermore, the user interface is often unintuitive and does not take into account the user's feelings or satisfaction, which can often cause frustration for users. This can lead to problems such as difficulty in understanding or agreeing with the estimate results.

[1710] 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 receiving an image of a room taken by a user with a terminal, means for analyzing the received image to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for analyzing the user's emotions using an emotion recognition engine, and means for dynamically adjusting the user interface based on the analyzed emotions. This allows the user to obtain an accurate and detailed estimate without any hassle, and the provision of an interface that corresponds to the user's emotions enables a more user-friendly experience.

[1711] A "user" is someone who uses the system to take photos of their room and request a moving estimate.

[1712] A "terminal" is a mobile information device such as a smartphone or tablet used by a user.

[1713] A "server" is a central computer system that receives, analyzes, and processes image data sent by users.

[1714] An "image analysis module" is a software or hardware component that processes received image data and extracts features of household items.

[1715] "Feature extraction" is the process of analyzing image data such as contours, shape, size, and color to extract important attributes.

[1716] An "object recognition module" is a software or hardware component that has the functionality to identify the type of household item based on extracted features.

[1717] "Size estimation" is an algorithm that determines the size of an item based on a known standard (e.g., door height).

[1718] "Weight estimation" is the process of calculating the weight of household goods, and is estimated based on past database information and size information.

[1719] The "moving cost calculation means" is a component that has a function of automatically calculating moving costs including basic transportation charges, additional charges, distance charges, seasonally variable charges, and special requirement charges.

[1720] An "emotion recognition engine" is a software or hardware component that analyzes a user's voice data and facial expression data to recognize emotions.

[1721] "User interface adaptation" is the process of dynamically changing display content and messages based on perceived user emotions.

[1722] "Deep learning" is a technology that uses multi-layered neural networks to analyze data and discover patterns and relationships.

[1723] A "segmentation algorithm" is an algorithm for dividing an image into multiple segments (regions) and identifying the contours of objects.

[1724] This invention is a system in which users take photos of their rooms using their devices, and AI automatically generates moving estimates based on those photos. This invention also incorporates an emotion engine that recognizes the user's emotions, providing a more user-friendly interface and service.

[1725] Hardware and Software

[1726] Hardware

[1727] Smartphones and tablets (devices)

[1728] Server (Central Computer System)

[1729] Camera (built into the device)

[1730] Microphone (built into the device)

[1731] software

[1732] Dedicated application

[1733] Image Analysis Module

[1734] Deep learning models (e.g. TensorFlow, PyTorch)

[1735] Emotion recognition engine (e.g., OpenCV, AWS Rekognition)

[1736] Specific details of processing

[1737] User operations

[1738] The user activates the smartphone camera and takes a photo of the room to be moved. Then, they launch the dedicated application, select the photo, tap the upload button, and send the image data to the server. The user then enters the moving date, the new address, and any special requirements (such as transporting a piano) through the application.

[1739] Processing on the server

[1740] The server passes the photo data received from the user to the image analysis module. This image analysis module analyzes the received image data using a deep learning-based segmentation algorithm to extract the features of the household items present in the room. The extracted features are then passed to the object recognition module, which identifies the type of each item. For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[1741] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door), and also references a database to estimate the typical weight of each household item.

[1742] Based on the collected information, the server uses an estimate calculation module to calculate the moving costs, which include the following factors:

[1743] Basic freight charge: Rate based on distance traveled and basic service

[1744] Weight-based surcharge: A surcharge based on the total weight of your belongings.

[1745] Distance-based surcharge: Charges are added based on the distance traveled

[1746] Seasonal price fluctuations: Prices vary depending on peak and off-peak seasons.

[1747] Extra charges based on special requirements: Extra charges based on special requests entered by the user (e.g. piano transport fees)

[1748] Furthermore, an emotion recognition engine is used to analyze the user's voice data and facial expression data to recognize the user's emotions (e.g., surprise, sadness, joy, anger, etc.). The emotion recognition engine collects data from the device's microphone and camera when the user uploads photos or checks the estimate results.

[1749] Emotion-based interface adjustment

[1750] The emotion recognition engine dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion. For example, if the user is dissatisfied or uncertain, the system can alleviate the user's anxiety by providing additional explanations or payment options in installments. Conversely, if the user is satisfied, the system can display only a concise message.

[1751] Displaying the estimate results

[1752] Once the calculation is complete, the server sends the results to the user's device. The user's smartphone displays the details and breakdown of the estimate via a user interface, allowing the user to see a transparent estimate of moving costs. The emotion recognition engine provides appropriate support based on the user's emotions.

[1753] Specific examples

[1754] For example, consider a case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion recognition engine detects this and alleviates the user's anxiety by offering additional explanations and the option to pay in installments.

[1755] Prompt Sentence Examples

[1756] "Describe a system that takes a photo of a room and automatically calculates an estimate for moving, taking into account the time of the move, the destination, and any special requirements. Also include a requirement to recognize the user's emotions and display an appropriate interface."

[1757] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1758] Step 1:

[1759] A user takes a photo of a room using a smartphone. The user activates the smartphone camera and takes a photo that shows the entire room. At this time, the user should be conscious of taking a photo that clearly shows the furniture.

[1760] Step 2:

[1761] The user launches the dedicated application, selects the photo they have taken, and taps the upload button. This sends the image data to the server. The input is the photo data taken by the user, and the output is the image data transferred to the server.

[1762] Step 3:

[1763] The server receives the photo data sent by the user. The server first checks the format and content of the sent data and prepares to pass it to the appropriate image analysis module. The input is the image data sent by the user, and the output is the image data passed to the image analysis module.

[1764] Step 4:

[1765] The server passes the received image data to the image analysis module, which then analyzes the image using a segmentation algorithm based on deep learning. Specifically, it uses TensorFlow and PyTorch to extract the contours and features of household items in the image. The input is the image data, and the output is the extracted feature data.

[1766] Step 5:

[1767] The server receives the feature data extracted from the image analysis module and passes it to the object recognition module. The object recognition module identifies the type of household item based on this feature data. For example, it recognizes sofas, tables, beds, refrigerators, etc. The input is the feature data, and the output is the recognized type data of the household item.

[1768] Step 6:

[1769] Based on the item type data received from the object recognition module, the server uses a size estimation algorithm to estimate the size of each item. This estimation uses known objects in the photo (e.g., the height of a door) as a reference. The input is the item type data, and the output is the estimated size data.

[1770] Step 7:

[1771] The server uses the estimated size data to estimate the general weight of each household item by referencing a database, such as a furniture catalog database or historical data. The input is size data, and the output is estimated weight data.

[1772] Step 8:

[1773] The server receives information about the moving date and destination entered by the user. The user enters this information through a dedicated application. The input is the moving date and destination information, and the output is this information stored on the server.

[1774] Step 9:

[1775] The server uses the estimate calculation module to calculate the moving costs based on the collected information (type of household goods, size, weight, moving time, and moving destination). The calculation includes basic shipping charges, additional charges based on the weight of household goods, additional charges based on distance, seasonal variations in rates, and additional charges based on special requirements. The input is all the collected data, and the output is the calculated moving costs.

[1776] Step 10:

[1777] The server sends the calculated moving costs to the user's device. The user can check the details and breakdown of the estimated costs through a dedicated application. The input is the calculated moving cost data, and the output is the estimated results displayed on the user's device.

[1778] Step 11:

[1779] At the same time, the server uses an emotion recognition engine to analyze the user's emotional data. It analyzes the voice data and facial expression data collected from the device's microphone and camera to recognize the user's emotions. The input is the emotional data collected from the device, and the output is the recognized emotional information.

[1780] Step 12:

[1781] Based on the emotions recognized by the emotion recognition engine, the server dynamically adjusts the content and messages displayed in the user interface. For example, if the user feels surprised or anxious, additional explanations or support messages are displayed. The input is the recognized emotional information, and the output is the adjusted user interface.

[1782] Step 13:

[1783] The user checks the quotation results through the application and takes necessary actions (for example, accepting the quotation or requesting additional information). The system executes the next action according to the user's actions. The input is the user's actions, and the output is the system's response to them.

[1784] (Application example 2)

[1785] 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."

[1786] Conventional moving estimate systems require users to manually input information about their belongings, which is time-consuming and laborious. Furthermore, if the estimate results are difficult for users to understand, they may not be able to provide sufficient support. This can cause stress for users when planning a move. Furthermore, the hassle of recognizing products and obtaining information when shopping face-to-face can also detract from the shopping experience.

[1787] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1788] In this invention, the server includes means for receiving images of a room taken by a user with a terminal, means for analyzing the received images to extract features of household goods, means for recognizing the type of household goods based on the extracted features, means for estimating the size and weight of the recognized household goods, means for receiving information on the moving date and moving destination entered by the user, means for calculating moving expenses based on the received information, means for presenting the calculated moving expenses to the user, means for recognizing the user's emotions by analyzing voice and facial expressions, and means for dynamically adjusting the user interface based on the recognized emotions. This enables users to obtain accurate estimates without hassle and receive appropriate support in real time, thereby improving the quality of their shopping experience.

[1789] "Images of a room taken by a user using a terminal" refers to image data of a room taken by a user using a device such as a smartphone or tablet.

[1790] "Means for receiving" refers to the function by which a server or cloud system receives data sent from a user.

[1791] "Means for analyzing and extracting the characteristics of household items" refers to a method that uses image analysis technology to identify characteristics such as the shape, color, and arrangement of furniture and household items from images of a room.

[1792] "Means for recognizing the type of household goods" refers to technology that identifies the type of specific furniture or home appliances, such as sofas or tables, based on extracted features.

[1793] "Size and weight estimation means" refers to an algorithm that calculates the size and weight of a recognized household item.

[1794] The "means for receiving information about the moving date and new address" refers to a function for collecting information such as the moving date and new address provided by the user.

[1795] "Means for calculating moving costs" refers to a calculation function that calculates the total cost of moving based on the collected information.

[1796] The "means for presenting the calculated moving costs to the user" refers to an interface that displays the estimated amount calculated by the server to the user.

[1797] "Means for recognizing a user's emotions by analyzing voice and facial expressions" refers to technology that uses the device's camera and microphone to analyze emotions from the user's voice and facial expressions.

[1798] "Means for dynamically adjusting the user interface based on recognized emotions" refers to a function that changes the displayed messages and layout depending on the user's emotional state.

[1799] "Means for recognizing products and visually presenting their location and information to the user" refers to technology that uses smart glasses or cameras to identify products in a store and display details of them to the user in real time.

[1800] "Means of providing additional recommended information and details to users based on product recognition information and user sentiment" refers to a function that provides detailed information about products that interest users and suggests related products.

[1801] This invention is a system that allows a user to take pictures of a room using a device such as a smartphone or tablet, and automatically provides a moving estimate based on those pictures. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it provides a more user-friendly interface and service. Below, specific embodiments of the invention are described.

[1802] System configuration

[1803] The system consists of the following main components:

[1804] 1. Terminal

[1805] It is used by users to take and upload photos of their rooms, and can be a smartphone or tablet.

[1806] It has a built-in camera and microphone for emotion recognition.

[1807] 2. Server

[1808] Receives and analyzes photo data.

[1809] It is equipped with an image analysis module that uses deep learning.

[1810] It is equipped with an emotion recognition engine that recognizes emotions from the user's facial expressions and voice data.

[1811] Calculate the moving costs and present the results to the user.

[1812] Implementation Procedure

[1813] 1. User operations

[1814] First, the user takes a photo of the room they are moving into using their smartphone. Then, they launch a dedicated application, select the photo they have taken, and tap the upload button to send the image data to the server. Furthermore, the user enters the moving date, the address of the new location, and any special requirements (e.g., transporting a piano) through the application.

[1815] 2. Processing on the server

[1816] The server passes the photo data received from the user to the image analysis module, which uses a deep learning-based segmentation algorithm to extract the characteristics of the household items in the room.Then, based on the extracted features, it identifies the type of household item.For example, it recognizes common household objects such as sofas, tables, beds, and refrigerators.

[1817] 3. Estimate the size and weight of your belongings

[1818] For each recognized household item, the server uses a size estimation algorithm to estimate the size of each object, using known objects in the photo as references (e.g., the height of a door) as well as reference data provided by the user. Using this size information, the server then references a database to estimate the typical weight of the household item.

[1819] 4. Estimate calculation

[1820] The server uses the collected information to calculate the cost of the move, including the basic freight charge, additional charges based on the weight of the belongings, additional charges based on distance, seasonal variations, and additional charges based on special requirements.

[1821] 5. Implementing the Emotion Engine

[1822] When the user reviews the photos and quotes, the server uses the device's camera and microphone to analyze the user's facial expressions and voice to recognize emotions. Based on the recognized emotions, the server dynamically adjusts the interface and displays additional explanations and payment options as needed.

[1823] Specific examples

[1824] For example, consider the case where a user moves from an urban apartment to a suburban house in February. The user takes a photo of the room and sends it to the server via a dedicated application. The server analyzes the photo and recognizes the sofa and bed. It then estimates the size and weight and calculates the shipping fee based on the moving date (February) and destination (suburbs). In this case, the basic shipping fee, household goods weight fee, distance fee, and peak season fee are all added together, and the user is presented with an estimate of 150,000 yen in total. If the user shows surprise at the presented amount, the emotion engine detects this and alleviates the user's anxiety by offering additional explanations and payment options in installments.

[1825] Prompt Sentence Examples

[1826] Input to the product recognition model: We train the model using a large number of images of shelves and products, with the following prompt: 'Identify and output the name, price, and details of the product in this image.'

[1827] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1828] Step 1:

[1829] The user takes a photo of the room with their smartphone, launches the dedicated application, selects the photo, and taps the upload button.

[1830] Input: A photo of a room taken with a smartphone.

[1831] Output: Image data sent to the server.

[1832] Specific operation: The user operates the application to select a photo and taps the upload button, which sends the image data to the server.

[1833] Step 2:

[1834] The server acquires the photo data received from the user and passes it to the image analysis module.

[1835] Input: Room image data sent by the user.

[1836] Output: Data input to the image analysis module.

[1837] Specific operation: The server stores the received photo data in memory and passes it to the image analysis module.

[1838] Step 3:

[1839] The image analysis module on the server uses deep learning to analyze the images and extract the characteristics of the household items in the room.

[1840] Input: Image data of the room input to the image analysis module.

[1841] Output: Extracted feature data of household items (e.g., furniture shape and layout).

[1842] How it works: The deep learning model uses a segmentation algorithm to identify furniture and appliances in the image and generate feature data.

[1843] Step 4:

[1844] Based on the extracted feature data, the server identifies the type of household item.

[1845] Input: Household property characteristics data.

[1846] Output: Identified household item type data (e.g. sofa, table, bed).

[1847] Specific operation: By referring to the feature data, the deep learning object recognition algorithm identifies the type of household item.

[1848] Step 5:

[1849] The server runs an algorithm to estimate the size and weight of recognized household items.

[1850] Input: Household item type data.

[1851] Output: Estimated household item size and weight data.

[1852] What it does: Using known objects (e.g., door height) or user-provided reference data, the size estimation algorithm calculates the size and weight of household items.

[1853] Step 6:

[1854] The user enters the moving date, new address, and any special requirements through a dedicated application, and then sends the data to the server.

[1855] Input: User-entered moving information, including when and where to move, and any special requirements.

[1856] Output: The moving information data sent to the server.

[1857] Specific operation: The user enters moving information into the application form and taps the submit button, which sends the data to the server.

[1858] Step 7:

[1859] The server calculates the moving expenses based on the received moving information data and the estimated size and weight data of the household goods.

[1860] Input: Moving information data, size and weight data of household goods.

[1861] Output: Calculated moving cost data.

[1862] Specific operation: The server calculates the basic transportation fee, additional fees based on the weight of the belongings, additional fees based on the distance, seasonal variations in fees, and additional fees based on special requirements, and then calculates the final moving cost.

[1863] Step 8:

[1864] When a user uploads a photo or checks the estimate results, the server uses the device's camera and microphone to collect the user's voice and facial expressions, which are then analyzed by the emotion engine.

[1865] Input: User voice and facial expression data collected by the device's camera and microphone.

[1866] Output: Recognized user emotional state data.

[1867] Specific operation: The emotion engine analyzes the tone of the voice data and facial expression data to classify the user's emotions.

[1868] Step 9:

[1869] The server dynamically adjusts the content and messages displayed in the user interface based on the recognized emotion, providing additional explanations and payment instalment options as needed.

[1870] Input: Recognized emotional state data.

[1871] Output: Dynamically adjusted interface display and messages.

[1872] Specific behavior: If the user expresses surprise or dissatisfaction, an interface is generated that displays additional explanations and options.

[1873] Step 10:

[1874] The final calculated moving cost, along with the details and breakdown of the estimate, are displayed on the user's smartphone via a user interface tailored by the emotion engine's results.

[1875] Input: Calculated moving cost data, dynamically adjusted interface data.

[1876] Output: Quote details and breakdown displayed on the user's smartphone.

[1877] Specific operation: The server sends the calculation results and adjusted interface data to the user terminal and displays them for the user to check.

[1878] The above are the specific processing steps of the program for the system that realizes the application example.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] 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.

[1883] FIG. 9 illustrates 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 behaviors 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.

[1884] 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.

[1885] 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).

[1886] 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.

[1887] 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."

[1888] 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.

[1889] 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).

[1890] 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.

[1891] 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.

[1892] 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.

[1893] 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.

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1899] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by re...

Claims

1. means for receiving an image of a room taken by a user using a terminal; means for analyzing the received images to extract features of the household goods; A means for recognizing the type of household item based on the extracted features; a means for estimating the size and weight of recognized household items; means for receiving information on the moving date and moving destination input by a user; means for calculating moving costs based on the received information; means for presenting the calculated moving costs to the user; A system including:

2. 2. The system of claim 1, wherein the means for calculating moving costs calculates a basic freight charge, an additional charge based on the weight of the belongings, an additional charge based on distance, a rate that varies with the season, and an additional charge based on special requirements.

3. 2. The system of claim 1, wherein the means for analyzing the image identifies contours of objects using a segmentation algorithm that uses deep learning.

Images