System

Abstract

A system is provided.SOLUTION: A system, comprising: means for capturing an image of a receipt; means for transmitting the captured image to a server; means for extracting, at the server, text information from the received receipt image; means for storing the extracted text information in a database; means for analyzing a user's purchasing history and providing relevant bargain information; and means for transmitting the relevant bargain information to the user's terminal as a push notification.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] Personal financial management has become an important issue in modern society. However, due to busy lifestyles, accurately tracking daily expenses and manually creating a household ledger can be time-consuming and laborious. It is also difficult to centrally manage daily purchase histories, leading to missed opportunities for effective spending management and savings. Furthermore, there is a lack of methods to provide timely coupons and sales information based on individual purchase histories. Therefore, there is a need for a system that can easily and automatically create a household ledger and provide users with appropriate savings information. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. It includes a means for capturing an image of a receipt and a means for sending the captured image to a server, and the server includes a means for extracting text information from the received receipt image and a means for saving the extracted text information in a database. It also includes a means for analyzing a user's purchase history and providing related discount information, and a means for sending the discount information to the user's device as a push notification. This allows a user to automatically create a household ledger by simply capturing and sending a receipt, and to receive appropriate discount information based on the purchase data in real time.

[0006] A "receipt" is a certificate issued when purchasing goods or services, and is a paper or digital document that contains information such as the purchased item, price, purchase date and time, and store name.

[0007] "Means for taking an image" refers to equipment or software that uses a device such as a camera or scanner to capture an image of a physical receipt.

[0008] A "server" is a computer system that receives requests from clients via a network and processes data and manages information.

[0009] The "means for transmitting images to a server" refers to a device or software for transferring captured image data to a server via a communication network such as the Internet.

[0010] "Means for extracting text information" refers to devices or software that use image processing technology to identify information such as letters and numbers in an image and extract it as digital text.

[0011] A "database" is a collection of information that is organized in a specific structure that allows for efficient storage, retrieval, and management of data.

[0012] "Purchase history" is a record of products and services purchased by a user in the past, and is data including information such as the purchase date and time, purchased items, prices, and store names.

[0013] "Bargain information" is information that users can use efficiently in terms of prices and services, such as coupons, sales information, and promotions.

[0014] A "push notification" is a notification message proactively sent from a server to a client device, and is a means of instantly providing information based on a user's interest.

[0015] A "terminal" is a computer device operated by a user, such as a smartphone, tablet, or PC.

[0016] A "household accounting database" is a database for recording and managing an individual's income and expenses, and includes daily purchase records and statistical information by category.

[0017] "Categorization" is the process of grouping and organizing collected data based on specific criteria. In the case of household accounting, it refers to classifying data based on the type of expenditure or the items purchased.

[0018] A "coupon" is a voucher or code for purchasing goods or services at a discounted price, and is a discount offer that can be used under certain conditions.

[0019] "Sale information" is information about discount sales periods and special sale items at stores and online shops.

[0020] "Purchase data" is detailed information about products and services purchased by a user, including the purchase date and time, price, product name, store name, and so on. [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] This invention relates to a system that comprehensively handles everything from taking photos of receipts to automatically creating a household account book and providing discount information. This system automatically creates a household account book and provides optimal discount information to users by allowing users to simply take a photo of a receipt and send it to a server.

[0043] What the program does

[0044] This system performs processing in the following procedure.

[0045] 1. Take a photo of your receipt and send it

[0046] First, the user takes a photo of the receipt using a smartphone or other device. The captured image is then viewed through a transparent interface, and the user taps the "Send" button to send the image to the server. This process is extremely simple for the user, making it easy to manage household finances in their daily lives.

[0047] The device receives the image and uses a dedicated API to send the image data to a server over the Internet, where it is optimized to maintain image quality and transmitted without data loss.

[0048] 2. Server-side image recognition and data analysis

[0049] The server temporarily stores the received receipt image in a database and then launches an image recognition module to analyze it. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This allows it to obtain data such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase.

[0050] The acquired data is stored in a database in its original format. The data processing module then categorizes this information for each user, organizing it into categories such as "food," "daily necessities," and "entertainment." This categorization allows users to easily understand the breakdown of their expenses when checking their household account book later.

[0051] 3. Providing discount information

[0052] The server has an algorithm for analyzing the user's accumulated purchasing history. It analyzes frequently purchased items and visited stores over a specific period to understand the user's purchasing trends. Based on this, it searches the server's database for relevant deals (coupons, sales information, etc.) and extracts the most suitable information for the user.

[0053] The extracted deals are sent to the device as push notifications, allowing users to quickly receive useful information based on their purchasing patterns.

[0054] 4. Viewing household accounts

[0055] Users can open the household accounting app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format.

[0056] Additionally, the filtering feature allows users to easily view spending over a specific period or by category, allowing them to manage their finances more effectively.

[0057] Specific examples

[0058] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0059] At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "milk." This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0060] As a result, this system significantly simplifies household accounting management for users, while providing a practical solution that can provide valuable information based on purchasing patterns.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is activated, and the user takes a picture of the entire receipt.

[0064] Step 2:

[0065] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image to the server.

[0066] Step 3:

[0067] The device compresses the captured receipt image and sends the data to a server via the Internet using a dedicated API. The image data is then passed to the server's receiving module.

[0068] Step 4:

[0069] The server first temporarily stores the received receipt image data, then passes it to the image recognition module, which uses OCR technology to extract text information from the image.

[0070] Step 5:

[0071] The server's OCR module identifies information such as the store name, product name, price, and purchase date and time from the receipt image and extracts this data in text format. The extracted information is stored in a temporary memory area.

[0072] Step 6:

[0073] The server stores the extracted text information in a database for each user. Specifically, it records items such as store information, product name, price, and purchase date individually. It also automatically organizes each item into the appropriate category.

[0074] Step 7:

[0075] The server analyzes the user's purchasing history over a certain period of time and launches an analysis module to identify frequently purchased products and frequently visited stores. The analysis results are stored as a user profile.

[0076] Step 8:

[0077] The server's analytics module searches the database for relevant coupons and sales information based on the user profile, and if applicable deals are found, prepares them as push notification content.

[0078] Step 9:

[0079] The server then sends the prepared push notification to the user's device, allowing the user to instantly receive new coupons and sales information.

[0080] Step 10:

[0081] When the user restarts the device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the device. The user can check the details of their expenses and the breakdown by category. They can also use the filtering function to easily check expenses for a specific period or by category.

[0082] Through the above processing steps, the system of the present invention allows the user to automatically generate a household account book and provide advantageous information simply by taking a photo of a receipt and sending it.

[0083] Example 1

[0084] 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."

[0085] Conventional household accounting management systems required users to manually enter information and were unable to provide discount information based on their purchasing history. This made it difficult for users to automatically manage details of purchased items or obtain appropriate discount information based on their individual purchasing patterns. Furthermore, they lacked the functionality to easily check spending history by category.

[0086] 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.

[0087] In this invention, the server includes means for extracting text information from received receipt images, means for storing the extracted text information in a database, and means for analyzing a user's purchase history and providing related discount information. This allows users to automatically manage their household finances and obtain discount information based on their individual purchase history simply by taking and sending an image of their receipt. Through the household finance application, users can check their spending history and view spending by specific period or category, enabling more detailed and efficient household management.

[0088] A "receipt image" is digital image data obtained by capturing the contents of a receipt issued for a commercial transaction or the like.

[0089] A "terminal" is an electronic device such as a smartphone or tablet used by a user.

[0090] A "server" is a centralized computer system that receives and processes data sent from terminals.

[0091] "API" stands for Application Program Interface, an interface that allows data exchange between different software applications.

[0092] "OCR" stands for Optical Character Recognition, a technology that extracts text information from images.

[0093] A "database" is a system for efficiently storing and managing structured data.

[0094] The "household account book database" is a database for recording and organizing a user's spending history based on collected text information.

[0095] "Push notification" is a method of sending information from a server to a device in real time.

[0096] The "filtering function" is a function that selects and displays data based on specific conditions.

[0097] "Purchase history" is data that records detailed information about products purchased by a user in the past.

[0098] "Bargain information" is information that brings benefits, such as coupons and sales information, that is provided based on the user's purchasing history.

[0099] The present invention relates to a system that allows users to take images of receipts and send them to a server, automating the provision of discount information based on household accounting management and purchase history. The following describes the system's components and specific processing procedures in detail.

[0100] First, the user takes a picture of the receipt using a device such as a smartphone or tablet. The image taken using the device's camera app is then viewed through the application interface. The user confirms the image and taps the "Send" button.

[0101] Next, the device converts the captured image into a specific format (e.g., JPEG, PNG) and sends it to the server via a dedicated API. The image data is quality-preserving and optimized before being sent, so it arrives at the server in a clear state.

[0102] The server temporarily stores the received image data in a database and activates an image recognition module. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This technology can be used with an OCR engine such as Tesseract. The server extracts information such as the store name, product name, price, and purchase date and time in text format and stores it in the household accounting database.

[0103] The server then categorizes the extracted data for each user. For example, "Milk purchased at Supermarket A" is classified as a food item and saved along with price information. The data processing module automatically performs this task, allowing users to easily understand their spending.

[0104] The server also has an algorithm that analyzes the user's purchasing history, identifying the items frequently purchased and the stores visited over a specific period, and then searches the database for relevant deals (e.g., coupons, sales information). The relevant information found is then sent to the device as a push notification, allowing the user to receive useful information at the right time.

[0105] Finally, users can access the household accounting application on their smartphone or other device to check their spending history. The device retrieves the necessary information from the server and displays it in a visually easy-to-understand format. Filtering functions also allow users to easily check spending over specific periods or by category.

[0106] Specific examples

[0107] For example, a user buys groceries at a supermarket, takes a photo of the receipt, and sends it to the system. The server receives the image and uses OCR technology to extract information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This data is then stored in the household account book database and automatically categorized under the category "Food."

[0108] The server also analyzes the user's past purchase history and determines that they frequently purchase "milk." It then finds information about milk sales at related supermarkets and sends it to the user's device as a push notification. This allows the user to save money by using coupons the next time they shop.

[0109] Prompt Sentence Examples

[0110] Below are some example prompts to input to a generative AI model:

[0111] "Please extract the information that can be recognized from the receipt (store name, product name, price, purchase date, etc.) in text format."

[0112] "Analyze users' purchasing trends based on past purchase data and provide them with discount information based on those trends."

[0113] These prompts ensure that each processing step of the system is performed clearly.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Take a photo of your receipt and send it

[0116] Users take a photo of the receipt using a smartphone or other device. If the image is not clear, OCR technology cannot accurately extract the text information. Therefore, users first check the preview of the image through the app interface. After confirming that the image is correct, users tap the "Send" button.

[0117] Input: Physical image of the receipt

[0118] Output: A digital image of the receipt stored on the user's device

[0119] The device converts the captured image into a format such as JPEG or PNG and sends it to the server via API, where it is optimized to maintain image quality.

[0120] Input: Receipt image taken by the user

[0121] Output: High-quality receipt image data sent to the server

[0122] Step 2: Image recognition and data analysis on the server side

[0123] The server receives the receipt image sent from the terminal and temporarily stores it in a database.

[0124] Input: Receipt image data sent from the device

[0125] Output: Image data temporarily stored in a database

[0126] Next, the server launches an image recognition module and uses OCR technology to extract text information from the receipt. For example, an OCR engine such as Tesseract can be used to extract text such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023" from the image.

[0127] Input: Receipt images stored in the database

[0128] Output: Extracted text data (store name, product name, price, purchase date and time)

[0129] The extracted text data is stored in a household accounting database.

[0130] Input: Extracted text data

[0131] Output: Text data stored in the household accounting database

[0132] Step 3: Categorize the data

[0133] The server categorizes the extracted data for each user, for example, into categories such as "food," "daily necessities," and "entertainment." The data processing module automatically performs this process, and the data organized for each user is saved.

[0134] Input: Text data stored in the household accounting database

[0135] Output: Categorized text data (e.g., "Milk" classified into the food category)

[0136] Step 4: Offering deals

[0137] The server has an algorithm that analyzes a user's purchasing history. It identifies the items and stores frequently purchased over a specific period of time, and then searches the database for relevant deals based on that information. For example, it might detect that the user frequently purchases "milk," and find information about milk sales at Supermarket A.

[0138] Input: Categorized text data and user purchase history

[0139] Output: Deals based on purchase history

[0140] The extracted information is sent to the device as a push notification. The server sends this information in real time, and the user can receive it.

[0141] Input: Deals based on purchase history

[0142] Output: Push notification of the deals sent to your device

[0143] Step 5: View your household budget

[0144] Users can open a household accounting application on their smartphone or other device to check their spending history. At this time, the device sends a request to the server to obtain the necessary information. The obtained information is displayed in a visually easy-to-understand format.

[0145] Input: Data request from a household finance application

[0146] Output: Spending history displayed on the device

[0147] Users can also use the device's filtering function to easily check spending over specific periods or categories, allowing them to effectively manage their finances.

[0148] Input: Filtering criteria within the household accounting application (specific period or category)

[0149] Output: Filtered spending history display

[0150] (Application example 1)

[0151] 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."

[0152] Conventional household accounting management systems and discount information systems require users to manually enter data, making them difficult to use and lacking technology to significantly simplify the in-store shopping experience. This makes it difficult for users to effectively manage their spending and receive real-time discount information based on their purchasing patterns. To address this issue, a system is needed that can automatically generate a household accounting record from photographs of receipts and provide discount information based on purchase history.

[0153] 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.

[0154] In this invention, the server includes means for capturing an image of a receipt, means for transmitting the captured image to the server, means for extracting text information from the received receipt image in the server, means for storing the extracted text information in a database, means for analyzing the user's purchase history and providing related discount information, means for transmitting the related discount information to the user's terminal as a push notification, and means for the user to capture a photo of the receipt at the physical store. This allows the user to easily obtain receipt information when shopping at the physical store, update their household ledger in real time, and receive optimal discount information based on their purchase history.

[0155] The "means for taking an image of a receipt" is a function for obtaining information on a receipt, which is a record of a commercial transaction, as a digital image.

[0156] The "means for sending the captured image to the server" is a communication function for transferring the image of the receipt captured on the user's terminal to the cloud or a remote server.

[0157] "Means for extracting text information from a received receipt image on the server" refers to a technology that analyzes the image data of a receipt on the server side and automatically identifies character and numerical information.

[0158] The "means for storing the extracted text information in a database" is a process for storing the analyzed text information in a database as structured data.

[0159] "Means of analyzing a user's purchasing history and providing relevant discount information" refers to an algorithm that analyzes data on products and services a user has purchased in the past and provides discount and campaign information based on the results.

[0160] The "means for sending relevant discount information to the user's device as a push notification" is a function that sends analyzed discount information as a notification to the user's smartphone or device in real time.

[0161] A "means for users to take photos of receipts in physical stores" is a device or interface that allows users to instantly take a digital image of a receipt when shopping at a physical store.

[0162] This invention provides a system that allows users to easily manage their household accounts and receive information on special offers at a physical store. This system is realized using a terminal, a server, and a dedicated application.

[0163] First, after shopping at a physical store, the user takes a photo of the receipt using their smartphone. The device is equipped with a camera for taking an image of the receipt and a screen for reviewing the image. The user checks the image of the receipt and taps the "Send" button to send it to the server. In this step, a dedicated application on the smartphone sends the receipt image to the server at optimal quality.

[0164] The server temporarily stores the received receipt image in a database and extracts text information from the image using OCR technology. The open source Tesseract can be used as the OCR technology. The extracted text information is stored in a database and categorized by a data analysis module. Specifically, it is automatically classified into categories such as "food," "daily necessities," and "entertainment."

[0165] The server then performs further analysis and generates relevant deals based on the user's purchasing history. It analyzes data on frequently purchased items and visited stores over a specific period to search for relevant coupons and sales information. The generated deals are then sent to the user's device as push notifications. This process essentially allows the user to receive useful information based on their purchasing patterns in real time.

[0166] Users can check their household finances at any time through this application. The application retrieves the necessary data from the server and displays the household finances in a visually easy-to-understand format. Filtering functions also make it easy to check expenditures for specific periods or categories. This allows users to manage their finances more effectively.

[0167] For example:

[0168] For example, suppose a user buys groceries at a physical store one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract text information such as "Store A," "Milk," "200 yen," and "October 12, 2023." This information is stored in a household accounting database and automatically categorized under the "Food" category. At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "Milk," and finds information about milk sales at related stores. This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0169] Example prompt sentence:

[0170] A user took a photo of a receipt for a 200 yen bottle of milk purchased at Store A and sent it to us. Our application used OCR technology to extract the following information from the receipt:

[0171] Purchased at: Store A

[0172] Purchased item: Milk

[0173] Price: 200 yen

[0174] Purchase date: October 12, 2023

[0175] Based on this, analyze patterns from past purchase history and generate deals on milk from store A.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] After shopping at a physical store, users take a picture of the receipt with their smartphone.

[0179] Input: receipt from physical store, smartphone camera function

[0180] Output: Digital image data of receipt

[0181] Specific operation: The user launches the smartphone camera app and takes a picture of the receipt. After taking the picture, the user checks and saves the image.

[0182] Step 2:

[0183] The terminal sends the captured receipt image to the server via the application.

[0184] Input: Digital image data of receipt

[0185] Output: Image data transferred to the server

[0186] What happens: The user taps the "Send" button in the application, and the application compresses the image and sends it to the server with optimal quality.

[0187] Step 3:

[0188] The server stores the received receipt images in a database and uses OCR technology to extract text information from the images.

[0189] Input: Image data transferred to the server

[0190] Output: Extracted text information (e.g., "store name," "product name," "price," "purchase date and time")

[0191] Specific operation: Image data stored on the server is input into an OCR engine (Tesseract), and the character information in the image is extracted as text data.

[0192] Step 4:

[0193] The server stores the extracted text information in a database and organizes it by category.

[0194] Input: Extracted text information

[0195] Output: Text information organized by category (e.g., "food," "daily necessities," "entertainment," etc.)

[0196] Specific operation: The server analyzes the text information, classifies it into pre-defined categories, and stores it in a database.

[0197] Step 5:

[0198] The server analyzes the user's purchasing history and generates relevant deals.

[0199] Input: Text information organized by category, past purchase history

[0200] Output: Related deals (e.g. coupons and sales)

[0201] Specific operation: The server analyzes the user's purchasing history data stored in a database, identifies frequently purchased products and visited stores, and obtains the most appropriate coupon and sale information based on that.

[0202] Step 6:

[0203] The server sends the generated discount information to the user's device as a push notification.

[0204] Input: Generated Deals

[0205] Output: A push notification that appears on the user's smartphone.

[0206] Specific operation: The server's notification service uses the application's push notification function to send discount information to the user's device in real time.

[0207] Step 7:

[0208] Users can view their household budget within the application and use filtering features to easily view spending for specific periods or categories.

[0209] Input: User's household accounting data, filtering conditions

[0210] Output: Filtered household information

[0211] How it works: The user opens the application, selects the period and category of information they need, and displays their household finances information. The application retrieves the necessary data from the server and displays it in a visually easy-to-understand format.

[0212] 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.

[0213] This invention relates to a receipt management system that incorporates an emotion engine that recognizes the user's emotions. In addition to automatically generating a household ledger from photographing receipts and providing information on special offers, it can also provide information that takes the user's emotional state into account.

[0214] What the program does

[0215] 1. Take a photo of your receipt and send it

[0216] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the device's built-in emotion engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[0217] The device collects the image data of the photographed receipt and the emotion data analyzed by the emotion engine. When the user taps the "Send" button, the device sends this data to the server.

[0218] 2. Image Recognition and Data Analysis

[0219] The server first temporarily stores the received receipt image data and emotion data, then launches an image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is then registered in the household accounting database.

[0220] Emotional data is added to user profiles and used in subsequent analysis stages, adding emotional information to a user's purchasing history for more accurate analysis.

[0221] 3. Analysis of purchase history and provision of discount information

[0222] The server analyzes the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, it identifies frequently purchased products and frequently visited stores. The identified information is used to provide discount information tailored to the user's emotional state.

[0223] Specifically, the server's analysis module analyzes the user's feelings toward products and services they have purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products that have a lot of positive feelings, and providing information about alternative products for products that have a lot of negative feelings.

[0224] 4. Sending push notifications

[0225] The server sends optimized discount information to the user's device as a push notification. By using the emotion engine, it is possible to provide information that is in line with the user's current emotional state, which is expected to improve user satisfaction.

[0226] 5. Viewing household accounts

[0227] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0228] Specific examples

[0229] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0230] At the same time, if the emotion engine detects a positive emotion in the user's facial expression, it will use that information to provide push notifications with sales and promotions related to Supermarket A's milk. Conversely, if a negative emotion is detected, it will provide sales information for alternative products or promotions at other stores.

[0231] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing optimal information based on each individual's emotional state.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the emotion engine is also activated, detecting the user's facial expressions and voice.

[0235] Step 2:

[0236] The device's emotion engine analyzes the user's emotions from their facial expressions and voice, and generates emotion data such as "smiling" or "neutral" as a result of this analysis.

[0237] Step 3:

[0238] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image and emotion data to the server.

[0239] Step 4:

[0240] The device compresses the image data and emotion data and sends it to a server via the internet via a dedicated API, where it is received.

[0241] Step 5:

[0242] The server temporarily stores the received receipt image data and emotion data, then passes the data to the image recognition module. The server then uses OCR technology to extract text information from the image, such as the store name, product name, price, and purchase date and time.

[0243] Step 6:

[0244] The text information extracted by the server's OCR module is stored in the server's household accounting database, enabling centralized management of data.

[0245] Step 7:

[0246] The server's emotion analysis module analyzes the received emotion data and adds the user's emotional state to the user profile, thereby linking the user's purchasing history with the emotion data.

[0247] Step 8:

[0248] The server analyzes users' purchasing history and emotional data to identify frequently purchased products and frequently visited stores, and uses this information to find relevant coupons and sales information.

[0249] Step 9:

[0250] The server's analysis module optimizes the deals based on the user's emotional data. If there are a lot of positive emotions, it proactively provides relevant sales information and coupons. If there are a lot of negative emotions, it provides information on alternative products.

[0251] Step 10:

[0252] The server sends optimized discount information to the user's device as a push notification, allowing the user to receive appropriate information in an easy-to-use format.

[0253] Step 11:

[0254] When a user launches the app on their device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the user's device, allowing the user to check their spending history and emotional state at any time.

[0255] Through the above processing steps, the system of the present invention enables the user to automatically generate a household account book simply by photographing and sending a receipt, and provides valuable information based on the user's emotional state.

[0256] Example 2

[0257] 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."

[0258] Current receipt management systems simply take images of receipts and store that information in a database, which means they are unable to provide personalized information based on a user's purchasing history. Furthermore, they do not take the user's emotional state into account, making it difficult to provide information optimized for each individual user. This can hinder an improved user experience and potentially reduce satisfaction. The present invention aims to solve these problems by analyzing a user's emotional state and providing optimized information based on that information.

[0259] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0260] In this invention, the server includes means for analyzing the user's emotional state, means for transmitting the emotional state to the server, and means for extracting text information from the received receipt image, thereby enabling personalized information to be provided that takes the user's emotional state into consideration.

[0261] A "receipt" is a paper document that records detailed information about a product or service sold and is primarily provided to the purchaser as proof of receipt.

[0262] "Image capture means" means a method of recording visual information of a physical object in digital form using a device such as a camera or scanner.

[0263] A "server" is a computer system that receives requests from client devices over a network and provides services or data.

[0264] "Text information extraction means" is a general term for software and algorithms used to identify and retrieve text and numeric information from images and data.

[0265] A "database" is a system for organizing, storing, and managing information, and allows efficient searching, adding, and updating of data based on specific conditions.

[0266] "Means for analyzing the user's emotional state" refers to functions and algorithms for identifying and evaluating psychological states and emotions based on user input such as voice and images.

[0267] "Means for transmitting emotional state to a server" is a general term for the processes and technologies used to transmit analyzed emotional data to a server over a network.

[0268] "Purchase history" is a record of past purchases made by a specific user, and includes information such as purchase date, store name, product name, and price.

[0269] "Bargain information" is a general term for information that brings economic benefits to users, such as coupons, sales information, and special promotions.

[0270] "Push notifications" are a technology that sends notifications in real time from a server directly to a user's device, and is a way of displaying information to attract the user's attention.

[0271] A "user profile" is a data set that collects and manages information about individual users, recording their personal characteristics and behavioral history.

[0272] "Categorization" is a method of classifying data or information into groups based on specific criteria, and is a technique for making management and searching more efficient.

[0273] "Coupon" means a code or ticket used as proof of purchase of a particular product or service at a discounted price.

[0274] A "generative AI model" is an algorithm or machine learning model that learns from large amounts of data and generates new data and information.

[0275] A "prompt" is text that is input into a generative AI model to specify conditions and hints for the answer that the model should generate.

[0276] This invention combines an emotion engine that analyzes user emotions to provide an optimal system for receipt management. Its main functions include taking photos of receipts, image recognition, analyzing purchase history, emotion analysis, providing discount information, and viewing household accounts.

[0277] This system is composed of devices such as smartphones, servers, and network communication means. Specific hardware components include the smartphone's camera module, emotion engine, and network module. Software components include Tesseract OCR as OCR technology, database management software, and emotion analysis algorithms.

[0278] The user uses their smartphone to take a picture of the receipt they receive at the store. At the same time, the device's built-in emotion engine simultaneously captures the user's facial expressions and voice and analyzes their emotions. When the user taps the "Send" button, the device sends the receipt image data and analyzed emotion data to the server.

[0279] The server temporarily stores the received receipt image and emotion data. Next, it launches an image recognition module and uses Tesseract OCR technology to extract text information (store name, product name, price, purchase date, etc.) from the receipt image. The extracted information is registered in the household accounting database, and the emotion data is added to the user profile.

[0280] Using the analysis module, the server analyzes the user's purchase history and emotional data. This allows the server to analyze the user's past purchasing behavior and emotional patterns, identify frequently purchased products and frequently visited stores, and provide proactive sales information and coupons for products with a high percentage of positive emotions, and provide information on alternative products for products with a high percentage of negative emotions.

[0281] The optimized discount information is sent to the user's device as a push notification from the server. By providing information that is in line with the user's current emotional state, it is expected that user satisfaction will increase.

[0282] As a concrete example, consider the case where a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract information such as "supermarket," "milk," "200 yen," and "purchase date," and stores this information in the household accounting database. At the same time, if the emotion engine analyzes the user's facial expression to indicate a positive emotion, it uses that information to provide push notifications with information about sales and promotions related to the milk at the supermarket. Conversely, if a negative emotion is analyzed, it provides information about sales of alternative products or promotions at different stores.

[0283] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing information based on each individual's emotional state.

[0284] An example of a prompt is, "Take a photo of your supermarket receipt with your smartphone and send it to the system. The system will read the information on the receipt and recommend sales information based on your emotions."

[0285] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0286] Step 1:

[0287] The user activates the smartphone camera and takes a picture of the receipt. At this time, the device's built-in emotion engine also activates, capturing the user's facial expressions and voice and analyzing the emotion data.

[0288] Input: An image of the receipt taken by the user, as well as the user's facial expression and voice.

[0289] Output: Receipt image data, parsed emotion data.

[0290] Step 2:

[0291] The device temporarily stores the image data of the photographed receipt and the emotion data analyzed by the emotion engine. It then transmits this data to the server using the network module. The transmission begins when the user taps the "Send" button.

[0292] Input: Receipt image data, parsed emotion data.

[0293] Output: The data packet to send to the server.

[0294] Step 3:

[0295] The server temporarily stores the received receipt image data and emotion data. Next, it launches an image recognition module and uses OCR technology (e.g., Tesseract OCR) to extract text information (store name, product name, price, purchase date, etc.) from the receipt image.

[0296] Input: Submitted receipt image data, emotion data.

[0297] Output: Extracted text information, stored emotion data.

[0298] Step 4:

[0299] The server stores the extracted text information and emotion data in the household accounting database, and the emotion data is added to the user profile for subsequent analysis.

[0300] Input: Extracted text information, parsed sentiment data.

[0301] Output: Text information stored in the household accounting database, emotion data stored in the user profile.

[0302] Step 5:

[0303] The server performs analysis based on the user's purchasing history and emotional data. Using the analysis module, it identifies frequently purchased products and frequently visited stores based on past purchasing behavior and emotional state. The identified information is used to provide discount information tailored to the user's emotional state.

[0304] Input: Purchase history from the household accounting database, emotion data from the user profile.

[0305] Output: Analysis results (information about frequently purchased products and stores), generation of optimized deals.

[0306] Step 6:

[0307] The server then sends the generated discount information to the user's device as a push notification, with the content of the push notification matching the user's current emotional state.

[0308] Input: Optimized deals, user emotional state.

[0309] Output: A push notification sent to the user's device.

[0310] Step 7:

[0311] Users can open the household accounting app on their device to check their spending history. The app retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. Filtering functions make it easy to check spending for specific periods or categories.

[0312] Input: Purchase history from the household ledger database.

[0313] Output: A detailed spending history displayed on the user's device.

[0314] (Application example 2)

[0315] 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."

[0316] Conventional receipt management systems can manage users' purchase history and automatically generate household accounts, but they cannot provide information that takes into account their emotional state. This makes it difficult to improve each user's individual purchasing experience and fails to increase user satisfaction. Furthermore, there is a need for systems that can provide optimal promotional information based on the user's emotional state.

[0317] 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.

[0318] In this invention, the server includes a means for capturing an image of the receipt, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for extracting text information from the received receipt image, which enables purchase history management and the provision of optimal promotion information while taking the user's emotional state into consideration.

[0319] "Means for taking an image of a receipt" refers to a device or function that a user uses to take a photo of a receipt with a camera, including cameras on smartphones and smart glasses.

[0320] The "means for transmitting the captured image to the server" is a communication function for transferring the receipt image captured by the user device to the server via the Internet.

[0321] "Means for analyzing a user's emotional state using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions and voice and identify their emotions.

[0322] The "means for extracting text information from a received receipt image" is a function that uses OCR (Optical Character Recognition) technology to extract text data such as store name, product name, and price from the image.

[0323] "Means for storing extracted text information and emotion data in a database" refers to a function for recording data extracted by OCR technology or an emotion recognition engine in a database on a server.

[0324] "Means for analyzing a user's purchasing history and emotional data and providing relevant discount information" is a function that analyzes recorded purchasing history and emotional data to generate coupons and sale information optimized for the user.

[0325] The "means for sending related discount information to the user's device as a push notification" is a function for sending the generated discount information to the user's smartphone or other device via a notification function.

[0326] This invention is a receipt management system that combines an emotion engine that recognizes the user's emotions. This system allows the user to take a photo of a receipt and send the image and emotional state to a server, enabling automatic generation of a household account book and the provision of personalized discount information. Specific implementation methods are described below.

[0327] This system can be implemented using devices such as smartphones, smart glasses, and head-mounted displays. The user uses these devices to take a picture of the receipt they receive at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At this time, the device's built-in emotion recognition engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[0328] The device collects image data of the photographed receipt and emotional data analyzed by the emotion recognition engine. When the user taps the "Send" button, the device sends this data to the server. The server first temporarily stores the received receipt image data and emotional data, then launches the image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is registered in the household accounting database. The emotional data is added to the user profile and used in subsequent analysis stages.

[0329] The server performs analysis based on the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, frequently purchased products and frequently visited stores are identified. The identified information is used to provide discount information tailored to the user's emotional state. Specifically, the server's analysis module analyzes the user's feelings toward products and services purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products with a high level of positive emotion, and providing information about alternative products for products with a high level of negative emotion.

[0330] The server sends optimized discount information to the user's device as a push notification. By using an emotion recognition engine, it is possible to provide information that is appropriate for the user's current emotional state, which is expected to improve user satisfaction.

[0331] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0332] As a concrete example, suppose a user buys groceries at a supermarket, takes a photo of the receipt, and sends it. The server receives the image and uses OCR technology to extract text information such as "supermarket," "milk," "200 yen," and "purchase date." This information is stored in a household accounting database and automatically categorized under the "food" category. At the same time, if the emotion recognition engine detects a positive emotion from the user's facial expression, it will use that information to provide push notifications with information about sales and promotions related to milk at the supermarket. Conversely, if a negative emotion is detected, it will provide information about sales of alternative products or promotions at different stores.

[0333] An example of a prompt sentence is shown below.

[0334] "Take a photo of the receipt with your camera, press the 'Add to Household Account' button and upload the receipt image and emotion."

[0335]

[0336] "Your latest household accounting data has been updated based on the receipt data you captured. Open the app to check the details."

[0337] This not only simplifies the user's household accounting management, but also makes it possible to provide optimal information based on each individual's emotional state.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] The user uses a device such as a smartphone to take a photo of the receipt they receive at the store.

[0341] Input: User takes a photo of the receipt with the camera

[0342] Specific operation: The device's camera module is activated and takes a photo of the entire receipt.

[0343] Step 2:

[0344] At the same time as capturing the receipt image, an emotion recognition engine is used to analyze the user's emotional state.

[0345] Input: Photographed receipt image, user facial expression data

[0346] Specific operation: The emotion recognition engine installed in the device analyzes emotional data (e.g., positive, negative, etc.) from the user's facial expressions and voice.

[0347] Step 3:

[0348] The terminal collects image data of the photographed receipt and emotional data analyzed by an emotion recognition engine, and sends the data to the server.

[0349] Input: Receipt image data, emotion data

[0350] Specific operation: When the user taps the "Send" button, this data is sent from the device to the server.

[0351] Step 4:

[0352] The server temporarily stores the received receipt image data and emotion data.

[0353] Input: Receipt image data and emotion data sent from the device

[0354] Specific operation: The server stores the received data in a temporary storage area.

[0355] Step 5:

[0356] The server runs an image recognition module to extract text information from the receipt image.

[0357] Input: Received receipt image data

[0358] Specific operation: Using OCR technology, text information such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase is extracted from the receipt image.

[0359] Step 6:

[0360] The server stores the extracted text information and emotion data in a household accounting database.

[0361] Input: Extracted text information, emotion data

[0362] What it does: This data is added to each user's profile and stored in categories.

[0363] Step 7:

[0364] The server analyzes the user's purchasing history and emotional data and generates relevant discount information.

[0365] Input: purchase history data, emotion data

[0366] How it works: The analytics module combines past purchasing behavior and emotional state to identify frequently purchased products and frequently visited stores, generating optimal coupon and sale information.

[0367] Step 8:

[0368] The server sends the generated discount information to the user's device as a push notification.

[0369] Input: Generated Deals

[0370] Specific operation: Uses push notifications to send special offers to users' smartphones and other devices.

[0371] Step 9:

[0372] Users can open the household accounting app on their device and check their spending history.

[0373] Input: Household accounting data sent from the server

[0374] How it works: The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] [Second embodiment]

[0379] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0380] 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.

[0381] 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).

[0382] 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.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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."

[0391] This invention relates to a system that comprehensively handles everything from taking photos of receipts to automatically creating a household account book and providing discount information. This system automatically creates a household account book and provides optimal discount information to users by allowing users to simply take a photo of a receipt and send it to a server.

[0392] What the program does

[0393] This system performs processing in the following procedure.

[0394] 1. Take a photo of your receipt and send it

[0395] First, the user takes a photo of the receipt using a smartphone or other device. The captured image is then viewed through a transparent interface, and the user taps the "Send" button to send the image to the server. This process is extremely simple for the user, making it easy to manage household finances in their daily lives.

[0396] The device receives the image and uses a dedicated API to send the image data to a server over the Internet, where it is optimized to maintain image quality and transmitted without data loss.

[0397] 2. Server-side image recognition and data analysis

[0398] The server temporarily stores the received receipt image in a database and then launches an image recognition module to analyze it. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This allows it to obtain data such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase.

[0399] The acquired data is stored in a database in its original format. The data processing module then categorizes this information for each user, organizing it into categories such as "food," "daily necessities," and "entertainment." This categorization allows users to easily understand the breakdown of their expenses when checking their household account book later.

[0400] 3. Providing discount information

[0401] The server has an algorithm for analyzing the user's accumulated purchasing history. It analyzes frequently purchased items and visited stores over a specific period to understand the user's purchasing trends. Based on this, it searches the server's database for relevant deals (coupons, sales information, etc.) and extracts the most suitable information for the user.

[0402] The extracted deals are sent to the device as push notifications, allowing users to quickly receive useful information based on their purchasing patterns.

[0403] 4. Viewing household accounts

[0404] Users can open the household accounting app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format.

[0405] Additionally, the filtering feature allows users to easily view spending over a specific period or by category, allowing them to manage their finances more effectively.

[0406] Specific examples

[0407] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0408] At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "milk." This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0409] As a result, this system significantly simplifies household accounting management for users, while providing a practical solution that can provide valuable information based on purchasing patterns.

[0410] The processing flow will be explained below.

[0411] Step 1:

[0412] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is activated, and the user takes a picture of the entire receipt.

[0413] Step 2:

[0414] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image to the server.

[0415] Step 3:

[0416] The device compresses the captured receipt image and sends the data to a server via the Internet using a dedicated API. The image data is then passed to the server's receiving module.

[0417] Step 4:

[0418] The server first temporarily stores the received receipt image data, then passes it to the image recognition module, which uses OCR technology to extract text information from the image.

[0419] Step 5:

[0420] The server's OCR module identifies information such as the store name, product name, price, and purchase date and time from the receipt image and extracts this data in text format. The extracted information is stored in a temporary memory area.

[0421] Step 6:

[0422] The server stores the extracted text information in a database for each user. Specifically, it records items such as store information, product name, price, and purchase date individually. It also automatically organizes each item into the appropriate category.

[0423] Step 7:

[0424] The server analyzes the user's purchasing history over a certain period of time and launches an analysis module to identify frequently purchased products and frequently visited stores. The analysis results are stored as a user profile.

[0425] Step 8:

[0426] The server's analytics module searches the database for relevant coupons and sales information based on the user profile, and if applicable deals are found, prepares them as push notification content.

[0427] Step 9:

[0428] The server then sends the prepared push notification to the user's device, allowing the user to instantly receive new coupons and sales information.

[0429] Step 10:

[0430] When the user restarts the device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the device. The user can check the details of their expenses and the breakdown by category. They can also use the filtering function to easily check expenses for a specific period or by category.

[0431] Through the above processing steps, the system of the present invention allows the user to automatically generate a household account book and provide advantageous information simply by taking a photo of a receipt and sending it.

[0432] Example 1

[0433] 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."

[0434] Conventional household accounting management systems required users to manually enter information and were unable to provide discount information based on their purchasing history. This made it difficult for users to automatically manage details of purchased items or obtain appropriate discount information based on their individual purchasing patterns. Furthermore, they lacked the functionality to easily check spending history by category.

[0435] 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.

[0436] In this invention, the server includes means for extracting text information from received receipt images, means for storing the extracted text information in a database, and means for analyzing a user's purchase history and providing related discount information. This allows users to automatically manage their household finances and obtain discount information based on their individual purchase history simply by taking and sending an image of their receipt. Through the household finance application, users can check their spending history and view spending by specific period or category, enabling more detailed and efficient household management.

[0437] A "receipt image" is digital image data obtained by capturing the contents of a receipt issued for a commercial transaction or the like.

[0438] A "terminal" is an electronic device such as a smartphone or tablet used by a user.

[0439] A "server" is a centralized computer system that receives and processes data sent from terminals.

[0440] "API" stands for Application Program Interface, an interface that allows data exchange between different software applications.

[0441] "OCR" stands for Optical Character Recognition, a technology that extracts text information from images.

[0442] A "database" is a system for efficiently storing and managing structured data.

[0443] The "household account book database" is a database for recording and organizing a user's spending history based on collected text information.

[0444] "Push notification" is a method of sending information from a server to a device in real time.

[0445] The "filtering function" is a function that selects and displays data based on specific conditions.

[0446] "Purchase history" is data that records detailed information about products purchased by a user in the past.

[0447] "Bargain information" is information that brings benefits, such as coupons and sales information, that is provided based on the user's purchasing history.

[0448] The present invention relates to a system that allows users to take images of receipts and send them to a server, automating the provision of discount information based on household accounting management and purchase history. The following describes the system's components and specific processing procedures in detail.

[0449] First, the user takes a picture of the receipt using a device such as a smartphone or tablet. The image taken using the device's camera app is then viewed through the application interface. The user confirms the image and taps the "Send" button.

[0450] Next, the device converts the captured image into a specific format (e.g., JPEG, PNG) and sends it to the server via a dedicated API. The image data is quality-preserving and optimized before being sent, so it arrives at the server in a clear state.

[0451] The server temporarily stores the received image data in a database and activates an image recognition module. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This technology can be used with an OCR engine such as Tesseract. The server extracts information such as the store name, product name, price, and purchase date and time in text format and stores it in the household accounting database.

[0452] The server then categorizes the extracted data for each user. For example, "Milk purchased at Supermarket A" is classified as a food item and saved along with price information. The data processing module automatically performs this task, allowing users to easily understand their spending.

[0453] The server also has an algorithm that analyzes the user's purchasing history, identifying the items frequently purchased and the stores visited over a specific period, and then searches the database for relevant deals (e.g., coupons, sales information). The relevant information found is then sent to the device as a push notification, allowing the user to receive useful information at the right time.

[0454] Finally, users can access the household accounting application on their smartphone or other device to check their spending history. The device retrieves the necessary information from the server and displays it in a visually easy-to-understand format. Filtering functions also allow users to easily check spending over specific periods or by category.

[0455] Specific examples

[0456] For example, a user buys groceries at a supermarket, takes a photo of the receipt, and sends it to the system. The server receives the image and uses OCR technology to extract information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This data is then stored in the household account book database and automatically categorized under the category "Food."

[0457] The server also analyzes the user's past purchase history and determines that they frequently purchase "milk." It then finds information about milk sales at related supermarkets and sends it to the user's device as a push notification. This allows the user to save money by using coupons the next time they shop.

[0458] Prompt Sentence Examples

[0459] Below are some example prompts to input to a generative AI model:

[0460] "Please extract the information that can be recognized from the receipt (store name, product name, price, purchase date, etc.) in text format."

[0461] "Analyze users' purchasing trends based on past purchase data and provide them with discount information based on those trends."

[0462] These prompts ensure that each processing step of the system is performed clearly.

[0463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0464] Step 1: Take a photo of your receipt and send it

[0465] Users take a photo of the receipt using a smartphone or other device. If the image is not clear, OCR technology cannot accurately extract the text information. Therefore, users first check the preview of the image through the app interface. After confirming that the image is correct, users tap the "Send" button.

[0466] Input: Physical image of the receipt

[0467] Output: A digital image of the receipt stored on the user's device

[0468] The device converts the captured image into a format such as JPEG or PNG and sends it to the server via API, where it is optimized to maintain image quality.

[0469] Input: Receipt image taken by the user

[0470] Output: High-quality receipt image data sent to the server

[0471] Step 2: Image recognition and data analysis on the server side

[0472] The server receives the receipt image sent from the terminal and temporarily stores it in a database.

[0473] Input: Receipt image data sent from the device

[0474] Output: Image data temporarily stored in a database

[0475] Next, the server launches an image recognition module and uses OCR technology to extract text information from the receipt. For example, an OCR engine such as Tesseract can be used to extract text such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023" from the image.

[0476] Input: Receipt images stored in the database

[0477] Output: Extracted text data (store name, product name, price, purchase date and time)

[0478] The extracted text data is stored in a household accounting database.

[0479] Input: Extracted text data

[0480] Output: Text data stored in the household accounting database

[0481] Step 3: Categorize the data

[0482] The server categorizes the extracted data for each user, for example, into categories such as "food," "daily necessities," and "entertainment." The data processing module automatically performs this process, and the data organized for each user is saved.

[0483] Input: Text data stored in the household accounting database

[0484] Output: Categorized text data (e.g., "Milk" classified into the food category)

[0485] Step 4: Offering deals

[0486] The server has an algorithm that analyzes a user's purchasing history. It identifies the items and stores frequently purchased over a specific period of time, and then searches the database for relevant deals based on that information. For example, it might detect that the user frequently purchases "milk," and find information about milk sales at Supermarket A.

[0487] Input: Categorized text data and user purchase history

[0488] Output: Deals based on purchase history

[0489] The extracted information is sent to the device as a push notification. The server sends this information in real time, and the user can receive it.

[0490] Input: Deals based on purchase history

[0491] Output: Push notification of the deals sent to your device

[0492] Step 5: View your household budget

[0493] Users can open a household accounting application on their smartphone or other device to check their spending history. At this time, the device sends a request to the server to obtain the necessary information. The obtained information is displayed in a visually easy-to-understand format.

[0494] Input: Data request from a household finance application

[0495] Output: Spending history displayed on the device

[0496] Users can also use the device's filtering function to easily check spending over specific periods or categories, allowing them to effectively manage their finances.

[0497] Input: Filtering criteria within the household accounting application (specific period or category)

[0498] Output: Filtered spending history display

[0499] (Application example 1)

[0500] 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."

[0501] Conventional household accounting management systems and discount information systems require users to manually enter data, making them difficult to use and lacking technology to significantly simplify the in-store shopping experience. This makes it difficult for users to effectively manage their spending and receive real-time discount information based on their purchasing patterns. To address this issue, a system is needed that can automatically generate a household accounting record from photographs of receipts and provide discount information based on purchase history.

[0502] 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.

[0503] In this invention, the server includes means for capturing an image of a receipt, means for transmitting the captured image to the server, means for extracting text information from the received receipt image in the server, means for storing the extracted text information in a database, means for analyzing the user's purchase history and providing related discount information, means for transmitting the related discount information to the user's terminal as a push notification, and means for the user to capture a photo of the receipt at the physical store. This allows the user to easily obtain receipt information when shopping at the physical store, update their household ledger in real time, and receive optimal discount information based on their purchase history.

[0504] The "means for taking an image of a receipt" is a function for obtaining information on a receipt, which is a record of a commercial transaction, as a digital image.

[0505] The "means for sending the captured image to the server" is a communication function for transferring the image of the receipt captured on the user's terminal to the cloud or a remote server.

[0506] "Means for extracting text information from a received receipt image on the server" refers to a technology that analyzes the image data of a receipt on the server side and automatically identifies character and numerical information.

[0507] The "means for storing the extracted text information in a database" is a process for storing the analyzed text information in a database as structured data.

[0508] "Means of analyzing a user's purchasing history and providing relevant discount information" refers to an algorithm that analyzes data on products and services a user has purchased in the past and provides discount and campaign information based on the results.

[0509] The "means for sending relevant discount information to the user's device as a push notification" is a function that sends analyzed discount information as a notification to the user's smartphone or device in real time.

[0510] A "means for users to take photos of receipts in physical stores" is a device or interface that allows users to instantly take a digital image of a receipt when shopping at a physical store.

[0511] This invention provides a system that allows users to easily manage their household accounts and receive information on special offers at a physical store. This system is realized using a terminal, a server, and a dedicated application.

[0512] First, after shopping at a physical store, the user takes a photo of the receipt using their smartphone. The device is equipped with a camera for taking an image of the receipt and a screen for reviewing the image. The user checks the image of the receipt and taps the "Send" button to send it to the server. In this step, a dedicated application on the smartphone sends the receipt image to the server at optimal quality.

[0513] The server temporarily stores the received receipt image in a database and extracts text information from the image using OCR technology. The open source Tesseract can be used as the OCR technology. The extracted text information is stored in a database and categorized by a data analysis module. Specifically, it is automatically classified into categories such as "food," "daily necessities," and "entertainment."

[0514] The server then performs further analysis and generates relevant deals based on the user's purchasing history. It analyzes data on frequently purchased items and visited stores over a specific period to search for relevant coupons and sales information. The generated deals are then sent to the user's device as push notifications. This process essentially allows the user to receive useful information based on their purchasing patterns in real time.

[0515] Users can check their household finances at any time through this application. The application retrieves the necessary data from the server and displays the household finances in a visually easy-to-understand format. Filtering functions also make it easy to check expenditures for specific periods or categories. This allows users to manage their finances more effectively.

[0516] For example:

[0517] For example, suppose a user buys groceries at a physical store one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract text information such as "Store A," "Milk," "200 yen," and "October 12, 2023." This information is stored in a household accounting database and automatically categorized under the "Food" category. At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "Milk," and finds information about milk sales at related stores. This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0518] Example prompt sentence:

[0519] A user took a photo of a receipt for a 200 yen bottle of milk purchased at Store A and sent it to us. Our application used OCR technology to extract the following information from the receipt:

[0520] Purchased at: Store A

[0521] Purchased item: Milk

[0522] Price: 200 yen

[0523] Purchase date: October 12, 2023

[0524] Based on this, analyze patterns from past purchase history and generate deals on milk from store A.

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] After shopping at a physical store, users take a picture of the receipt with their smartphone.

[0528] Input: receipt from physical store, smartphone camera function

[0529] Output: Digital image data of receipt

[0530] Specific operation: The user launches the smartphone camera app and takes a picture of the receipt. After taking the picture, the user checks and saves the image.

[0531] Step 2:

[0532] The terminal sends the captured receipt image to the server via the application.

[0533] Input: Digital image data of receipt

[0534] Output: Image data transferred to the server

[0535] What happens: The user taps the "Send" button in the application, and the application compresses the image and sends it to the server with optimal quality.

[0536] Step 3:

[0537] The server stores the received receipt images in a database and uses OCR technology to extract text information from the images.

[0538] Input: Image data transferred to the server

[0539] Output: Extracted text information (e.g., "store name," "product name," "price," "purchase date and time")

[0540] Specific operation: Image data stored on the server is input into an OCR engine (Tesseract), and the character information in the image is extracted as text data.

[0541] Step 4:

[0542] The server stores the extracted text information in a database and organizes it by category.

[0543] Input: Extracted text information

[0544] Output: Text information organized by category (e.g., "food," "daily necessities," "entertainment," etc.)

[0545] Specific operation: The server analyzes the text information, classifies it into pre-defined categories, and stores it in a database.

[0546] Step 5:

[0547] The server analyzes the user's purchasing history and generates relevant deals.

[0548] Input: Text information organized by category, past purchase history

[0549] Output: Related deals (e.g. coupons and sales)

[0550] Specific operation: The server analyzes the user's purchasing history data stored in a database, identifies frequently purchased products and visited stores, and obtains the most appropriate coupon and sale information based on that.

[0551] Step 6:

[0552] The server sends the generated discount information to the user's device as a push notification.

[0553] Input: Generated Deals

[0554] Output: A push notification that appears on the user's smartphone.

[0555] Specific operation: The server's notification service uses the application's push notification function to send discount information to the user's device in real time.

[0556] Step 7:

[0557] Users can view their household budget within the application and use filtering features to easily view spending for specific periods or categories.

[0558] Input: User's household accounting data, filtering conditions

[0559] Output: Filtered household information

[0560] How it works: The user opens the application, selects the period and category of information they need, and displays their household finances information. The application retrieves the necessary data from the server and displays it in a visually easy-to-understand format.

[0561] 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.

[0562] This invention relates to a receipt management system that incorporates an emotion engine that recognizes the user's emotions. In addition to automatically generating a household ledger from photographing receipts and providing information on special offers, it can also provide information that takes the user's emotional state into account.

[0563] What the program does

[0564] 1. Take a photo of your receipt and send it

[0565] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the device's built-in emotion engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[0566] The device collects the image data of the photographed receipt and the emotion data analyzed by the emotion engine. When the user taps the "Send" button, the device sends this data to the server.

[0567] 2. Image Recognition and Data Analysis

[0568] The server first temporarily stores the received receipt image data and emotion data, then launches an image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is then registered in the household accounting database.

[0569] Emotional data is added to user profiles and used in subsequent analysis stages, adding emotional information to a user's purchasing history for more accurate analysis.

[0570] 3. Analysis of purchase history and provision of discount information

[0571] The server analyzes the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, it identifies frequently purchased products and frequently visited stores. The identified information is used to provide discount information tailored to the user's emotional state.

[0572] Specifically, the server's analysis module analyzes the user's feelings toward products and services they have purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products that have a lot of positive feelings, and providing information about alternative products for products that have a lot of negative feelings.

[0573] 4. Sending push notifications

[0574] The server sends optimized discount information to the user's device as a push notification. By using the emotion engine, it is possible to provide information that is in line with the user's current emotional state, which is expected to improve user satisfaction.

[0575] 5. Viewing household accounts

[0576] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0577] Specific examples

[0578] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0579] At the same time, if the emotion engine detects a positive emotion in the user's facial expression, it will use that information to provide push notifications with sales and promotions related to Supermarket A's milk. Conversely, if a negative emotion is detected, it will provide sales information for alternative products or promotions at other stores.

[0580] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing optimal information based on each individual's emotional state.

[0581] The processing flow will be explained below.

[0582] Step 1:

[0583] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the emotion engine is also activated, detecting the user's facial expressions and voice.

[0584] Step 2:

[0585] The device's emotion engine analyzes the user's emotions from their facial expressions and voice, and generates emotion data such as "smiling" or "neutral" as a result of this analysis.

[0586] Step 3:

[0587] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image and emotion data to the server.

[0588] Step 4:

[0589] The device compresses the image data and emotion data and sends it to a server via the internet via a dedicated API, where it is received.

[0590] Step 5:

[0591] The server temporarily stores the received receipt image data and emotion data, then passes the data to the image recognition module. The server then uses OCR technology to extract text information from the image, such as the store name, product name, price, and purchase date and time.

[0592] Step 6:

[0593] The text information extracted by the server's OCR module is stored in the server's household accounting database, enabling centralized management of data.

[0594] Step 7:

[0595] The server's emotion analysis module analyzes the received emotion data and adds the user's emotional state to the user profile, thereby linking the user's purchasing history with the emotion data.

[0596] Step 8:

[0597] The server analyzes users' purchasing history and emotional data to identify frequently purchased products and frequently visited stores, and uses this information to find relevant coupons and sales information.

[0598] Step 9:

[0599] The server's analysis module optimizes the deals based on the user's emotional data. If there are a lot of positive emotions, it proactively provides relevant sales information and coupons. If there are a lot of negative emotions, it provides information on alternative products.

[0600] Step 10:

[0601] The server sends optimized discount information to the user's device as a push notification, allowing the user to receive appropriate information in an easy-to-use format.

[0602] Step 11:

[0603] When a user launches the app on their device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the user's device, allowing the user to check their spending history and emotional state at any time.

[0604] Through the above processing steps, the system of the present invention enables the user to automatically generate a household account book simply by photographing and sending a receipt, and provides valuable information based on the user's emotional state.

[0605] Example 2

[0606] 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."

[0607] Current receipt management systems simply take images of receipts and store that information in a database, which means they are unable to provide personalized information based on a user's purchasing history. Furthermore, they do not take the user's emotional state into account, making it difficult to provide information optimized for each individual user. This can hinder an improved user experience and potentially reduce satisfaction. The present invention aims to solve these problems by analyzing a user's emotional state and providing optimized information based on that information.

[0608] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0609] In this invention, the server includes means for analyzing the user's emotional state, means for transmitting the emotional state to the server, and means for extracting text information from the received receipt image, thereby enabling personalized information to be provided that takes the user's emotional state into consideration.

[0610] A "receipt" is a paper document that records detailed information about a product or service sold and is primarily provided to the purchaser as proof of receipt.

[0611] "Image capture means" means a method of recording visual information of a physical object in digital form using a device such as a camera or scanner.

[0612] A "server" is a computer system that receives requests from client devices over a network and provides services or data.

[0613] "Text information extraction means" is a general term for software and algorithms used to identify and retrieve text and numeric information from images and data.

[0614] A "database" is a system for organizing, storing, and managing information, and allows efficient searching, adding, and updating of data based on specific conditions.

[0615] "Means for analyzing the user's emotional state" refers to functions and algorithms for identifying and evaluating psychological states and emotions based on user input such as voice and images.

[0616] "Means for transmitting emotional state to a server" is a general term for the processes and technologies used to transmit analyzed emotional data to a server over a network.

[0617] "Purchase history" is a record of past purchases made by a specific user, and includes information such as purchase date, store name, product name, and price.

[0618] "Bargain information" is a general term for information that brings economic benefits to users, such as coupons, sales information, and special promotions.

[0619] "Push notifications" are a technology that sends notifications in real time from a server directly to a user's device, and is a way of displaying information to attract the user's attention.

[0620] A "user profile" is a data set that collects and manages information about individual users, recording their personal characteristics and behavioral history.

[0621] "Categorization" is a method of classifying data or information into groups based on specific criteria, and is a technique for making management and searching more efficient.

[0622] "Coupon" means a code or ticket used as proof of purchase of a particular product or service at a discounted price.

[0623] A "generative AI model" is an algorithm or machine learning model that learns from large amounts of data and generates new data and information.

[0624] A "prompt" is text that is input into a generative AI model to specify conditions and hints for the answer that the model should generate.

[0625] This invention combines an emotion engine that analyzes user emotions to provide an optimal system for receipt management. Its main functions include taking photos of receipts, image recognition, analyzing purchase history, emotion analysis, providing discount information, and viewing household accounts.

[0626] This system is composed of devices such as smartphones, servers, and network communication means. Specific hardware components include the smartphone's camera module, emotion engine, and network module. Software components include Tesseract OCR as OCR technology, database management software, and emotion analysis algorithms.

[0627] The user uses their smartphone to take a picture of the receipt they receive at the store. At the same time, the device's built-in emotion engine simultaneously captures the user's facial expressions and voice and analyzes their emotions. When the user taps the "Send" button, the device sends the receipt image data and analyzed emotion data to the server.

[0628] The server temporarily stores the received receipt image and emotion data. Next, it launches an image recognition module and uses Tesseract OCR technology to extract text information (store name, product name, price, purchase date, etc.) from the receipt image. The extracted information is registered in the household accounting database, and the emotion data is added to the user profile.

[0629] Using the analysis module, the server analyzes the user's purchase history and emotional data. This allows the server to analyze the user's past purchasing behavior and emotional patterns, identify frequently purchased products and frequently visited stores, and provide proactive sales information and coupons for products with a high percentage of positive emotions, and provide information on alternative products for products with a high percentage of negative emotions.

[0630] The optimized discount information is sent to the user's device as a push notification from the server. By providing information that is in line with the user's current emotional state, it is expected that user satisfaction will increase.

[0631] As a concrete example, consider the case where a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract information such as "supermarket," "milk," "200 yen," and "purchase date," and stores this information in the household accounting database. At the same time, if the emotion engine analyzes the user's facial expression to indicate a positive emotion, it uses that information to provide push notifications with information about sales and promotions related to the milk at the supermarket. Conversely, if a negative emotion is analyzed, it provides information about sales of alternative products or promotions at different stores.

[0632] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing information based on each individual's emotional state.

[0633] An example of a prompt is, "Take a photo of your supermarket receipt with your smartphone and send it to the system. The system will read the information on the receipt and recommend sales information based on your emotions."

[0634] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0635] Step 1:

[0636] The user activates the smartphone camera and takes a picture of the receipt. At this time, the device's built-in emotion engine also activates, capturing the user's facial expressions and voice and analyzing the emotion data.

[0637] Input: An image of the receipt taken by the user, as well as the user's facial expression and voice.

[0638] Output: Receipt image data, parsed emotion data.

[0639] Step 2:

[0640] The device temporarily stores the image data of the photographed receipt and the emotion data analyzed by the emotion engine. It then transmits this data to the server using the network module. The transmission begins when the user taps the "Send" button.

[0641] Input: Receipt image data, parsed emotion data.

[0642] Output: The data packet to send to the server.

[0643] Step 3:

[0644] The server temporarily stores the received receipt image data and emotion data. Next, it launches an image recognition module and uses OCR technology (e.g., Tesseract OCR) to extract text information (store name, product name, price, purchase date, etc.) from the receipt image.

[0645] Input: Submitted receipt image data, emotion data.

[0646] Output: Extracted text information, stored emotion data.

[0647] Step 4:

[0648] The server stores the extracted text information and emotion data in the household accounting database, and the emotion data is added to the user profile for subsequent analysis.

[0649] Input: Extracted text information, parsed sentiment data.

[0650] Output: Text information stored in the household accounting database, emotion data stored in the user profile.

[0651] Step 5:

[0652] The server performs analysis based on the user's purchasing history and emotional data. Using the analysis module, it identifies frequently purchased products and frequently visited stores based on past purchasing behavior and emotional state. The identified information is used to provide discount information tailored to the user's emotional state.

[0653] Input: Purchase history from the household accounting database, emotion data from the user profile.

[0654] Output: Analysis results (information about frequently purchased products and stores), generation of optimized deals.

[0655] Step 6:

[0656] The server then sends the generated discount information to the user's device as a push notification, with the content of the push notification matching the user's current emotional state.

[0657] Input: Optimized deals, user emotional state.

[0658] Output: A push notification sent to the user's device.

[0659] Step 7:

[0660] Users can open the household accounting app on their device to check their spending history. The app retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. Filtering functions make it easy to check spending for specific periods or categories.

[0661] Input: Purchase history from the household ledger database.

[0662] Output: A detailed spending history displayed on the user's device.

[0663] (Application example 2)

[0664] 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."

[0665] Conventional receipt management systems can manage users' purchase history and automatically generate household accounts, but they cannot provide information that takes into account their emotional state. This makes it difficult to improve each user's individual purchasing experience and fails to increase user satisfaction. Furthermore, there is a need for systems that can provide optimal promotional information based on the user's emotional state.

[0666] 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.

[0667] In this invention, the server includes a means for capturing an image of the receipt, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for extracting text information from the received receipt image, which enables purchase history management and the provision of optimal promotion information while taking the user's emotional state into consideration.

[0668] "Means for taking an image of a receipt" refers to a device or function that a user uses to take a photo of a receipt with a camera, including cameras on smartphones and smart glasses.

[0669] The "means for transmitting the captured image to the server" is a communication function for transferring the receipt image captured by the user device to the server via the Internet.

[0670] "Means for analyzing a user's emotional state using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions and voice and identify their emotions.

[0671] The "means for extracting text information from a received receipt image" is a function that uses OCR (Optical Character Recognition) technology to extract text data such as store name, product name, and price from the image.

[0672] "Means for storing extracted text information and emotion data in a database" refers to a function for recording data extracted by OCR technology or an emotion recognition engine in a database on a server.

[0673] "Means for analyzing a user's purchasing history and emotional data and providing relevant discount information" is a function that analyzes recorded purchasing history and emotional data to generate coupons and sale information optimized for the user.

[0674] The "means for sending related discount information to the user's device as a push notification" is a function for sending the generated discount information to the user's smartphone or other device via a notification function.

[0675] This invention is a receipt management system that combines an emotion engine that recognizes the user's emotions. This system allows the user to take a photo of a receipt and send the image and emotional state to a server, enabling automatic generation of a household account book and the provision of personalized discount information. Specific implementation methods are described below.

[0676] This system can be implemented using devices such as smartphones, smart glasses, and head-mounted displays. The user uses these devices to take a picture of the receipt they receive at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At this time, the device's built-in emotion recognition engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[0677] The device collects image data of the photographed receipt and emotional data analyzed by the emotion recognition engine. When the user taps the "Send" button, the device sends this data to the server. The server first temporarily stores the received receipt image data and emotional data, then launches the image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is registered in the household accounting database. The emotional data is added to the user profile and used in subsequent analysis stages.

[0678] The server performs analysis based on the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, frequently purchased products and frequently visited stores are identified. The identified information is used to provide discount information tailored to the user's emotional state. Specifically, the server's analysis module analyzes the user's feelings toward products and services purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products with a high level of positive emotion, and providing information about alternative products for products with a high level of negative emotion.

[0679] The server sends optimized discount information to the user's device as a push notification. By using an emotion recognition engine, it is possible to provide information that is appropriate for the user's current emotional state, which is expected to improve user satisfaction.

[0680] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0681] As a concrete example, suppose a user buys groceries at a supermarket, takes a photo of the receipt, and sends it. The server receives the image and uses OCR technology to extract text information such as "supermarket," "milk," "200 yen," and "purchase date." This information is stored in a household accounting database and automatically categorized under the "food" category. At the same time, if the emotion recognition engine detects a positive emotion from the user's facial expression, it will use that information to provide push notifications with information about sales and promotions related to milk at the supermarket. Conversely, if a negative emotion is detected, it will provide information about sales of alternative products or promotions at different stores.

[0682] An example of a prompt sentence is shown below.

[0683] "Take a photo of the receipt with your camera, press the 'Add to Household Account' button and upload the receipt image and emotion."

[0684]

[0685] "Your latest household accounting data has been updated based on the receipt data you captured. Open the app to check the details."

[0686] This not only simplifies the user's household accounting management, but also makes it possible to provide optimal information based on each individual's emotional state.

[0687] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0688] Step 1:

[0689] The user uses a device such as a smartphone to take a photo of the receipt they receive at the store.

[0690] Input: User takes a photo of the receipt with the camera

[0691] Specific operation: The device's camera module is activated and takes a photo of the entire receipt.

[0692] Step 2:

[0693] At the same time as capturing the receipt image, an emotion recognition engine is used to analyze the user's emotional state.

[0694] Input: Photographed receipt image, user facial expression data

[0695] Specific operation: The emotion recognition engine installed in the device analyzes emotional data (e.g., positive, negative, etc.) from the user's facial expressions and voice.

[0696] Step 3:

[0697] The terminal collects image data of the photographed receipt and emotional data analyzed by an emotion recognition engine, and sends the data to the server.

[0698] Input: Receipt image data, emotion data

[0699] Specific operation: When the user taps the "Send" button, this data is sent from the device to the server.

[0700] Step 4:

[0701] The server temporarily stores the received receipt image data and emotion data.

[0702] Input: Receipt image data and emotion data sent from the device

[0703] Specific operation: The server stores the received data in a temporary storage area.

[0704] Step 5:

[0705] The server runs an image recognition module to extract text information from the receipt image.

[0706] Input: Received receipt image data

[0707] Specific operation: Using OCR technology, text information such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase is extracted from the receipt image.

[0708] Step 6:

[0709] The server stores the extracted text information and emotion data in a household accounting database.

[0710] Input: Extracted text information, emotion data

[0711] What it does: This data is added to each user's profile and stored in categories.

[0712] Step 7:

[0713] The server analyzes the user's purchasing history and emotional data and generates relevant discount information.

[0714] Input: purchase history data, emotion data

[0715] How it works: The analytics module combines past purchasing behavior and emotional state to identify frequently purchased products and frequently visited stores, generating optimal coupon and sale information.

[0716] Step 8:

[0717] The server sends the generated discount information to the user's device as a push notification.

[0718] Input: Generated Deals

[0719] Specific operation: Uses push notifications to send special offers to users' smartphones and other devices.

[0720] Step 9:

[0721] Users can open the household accounting app on their device and check their spending history.

[0722] Input: Household accounting data sent from the server

[0723] How it works: The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] [Third embodiment]

[0728] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0729] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0730] 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).

[0731] 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.

[0732] 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.

[0733] 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).

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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."

[0740] This invention relates to a system that comprehensively handles everything from taking photos of receipts to automatically creating a household account book and providing discount information. This system automatically creates a household account book and provides optimal discount information to users by allowing users to simply take a photo of a receipt and send it to a server.

[0741] What the program does

[0742] This system performs processing in the following procedure.

[0743] 1. Take a photo of your receipt and send it

[0744] First, the user takes a photo of the receipt using a smartphone or other device. The captured image is then viewed through a transparent interface, and the user taps the "Send" button to send the image to the server. This process is extremely simple for the user, making it easy to manage household finances in their daily lives.

[0745] The device receives the image and uses a dedicated API to send the image data to a server over the Internet, where it is optimized to maintain image quality and transmitted without data loss.

[0746] 2. Server-side image recognition and data analysis

[0747] The server temporarily stores the received receipt image in a database and then launches an image recognition module to analyze it. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This allows it to obtain data such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase.

[0748] The acquired data is stored in a database in its original format. The data processing module then categorizes this information for each user, organizing it into categories such as "food," "daily necessities," and "entertainment." This categorization allows users to easily understand the breakdown of their expenses when checking their household account book later.

[0749] 3. Providing discount information

[0750] The server has an algorithm for analyzing the user's accumulated purchasing history. It analyzes frequently purchased items and visited stores over a specific period to understand the user's purchasing trends. Based on this, it searches the server's database for relevant deals (coupons, sales information, etc.) and extracts the most suitable information for the user.

[0751] The extracted deals are sent to the device as push notifications, allowing users to quickly receive useful information based on their purchasing patterns.

[0752] 4. Viewing household accounts

[0753] Users can open the household accounting app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format.

[0754] Additionally, the filtering feature allows users to easily view spending over a specific period or by category, allowing them to manage their finances more effectively.

[0755] Specific examples

[0756] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0757] At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "milk." This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0758] As a result, this system significantly simplifies household accounting management for users, while providing a practical solution that can provide valuable information based on purchasing patterns.

[0759] The processing flow will be explained below.

[0760] Step 1:

[0761] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is activated, and the user takes a picture of the entire receipt.

[0762] Step 2:

[0763] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image to the server.

[0764] Step 3:

[0765] The device compresses the captured receipt image and sends the data to a server via the Internet using a dedicated API. The image data is then passed to the server's receiving module.

[0766] Step 4:

[0767] The server first temporarily stores the received receipt image data, then passes it to the image recognition module, which uses OCR technology to extract text information from the image.

[0768] Step 5:

[0769] The server's OCR module identifies information such as the store name, product name, price, and purchase date and time from the receipt image and extracts this data in text format. The extracted information is stored in a temporary memory area.

[0770] Step 6:

[0771] The server stores the extracted text information in a database for each user. Specifically, it records items such as store information, product name, price, and purchase date individually. It also automatically organizes each item into the appropriate category.

[0772] Step 7:

[0773] The server analyzes the user's purchasing history over a certain period of time and launches an analysis module to identify frequently purchased products and frequently visited stores. The analysis results are stored as a user profile.

[0774] Step 8:

[0775] The server's analytics module searches the database for relevant coupons and sales information based on the user profile, and if applicable deals are found, prepares them as push notification content.

[0776] Step 9:

[0777] The server then sends the prepared push notification to the user's device, allowing the user to instantly receive new coupons and sales information.

[0778] Step 10:

[0779] When the user restarts the device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the device. The user can check the details of their expenses and the breakdown by category. They can also use the filtering function to easily check expenses for a specific period or by category.

[0780] Through the above processing steps, the system of the present invention allows the user to automatically generate a household account book and provide advantageous information simply by taking a photo of a receipt and sending it.

[0781] Example 1

[0782] 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."

[0783] Conventional household accounting management systems required users to manually enter information and were unable to provide discount information based on their purchasing history. This made it difficult for users to automatically manage details of purchased items or obtain appropriate discount information based on their individual purchasing patterns. Furthermore, they lacked the functionality to easily check spending history by category.

[0784] 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.

[0785] In this invention, the server includes means for extracting text information from received receipt images, means for storing the extracted text information in a database, and means for analyzing a user's purchase history and providing related discount information. This allows users to automatically manage their household finances and obtain discount information based on their individual purchase history simply by taking and sending an image of their receipt. Through the household finance application, users can check their spending history and view spending by specific period or category, enabling more detailed and efficient household management.

[0786] A "receipt image" is digital image data obtained by capturing the contents of a receipt issued for a commercial transaction or the like.

[0787] A "terminal" is an electronic device such as a smartphone or tablet used by a user.

[0788] A "server" is a centralized computer system that receives and processes data sent from terminals.

[0789] "API" stands for Application Program Interface, an interface that allows data exchange between different software applications.

[0790] "OCR" stands for Optical Character Recognition, a technology that extracts text information from images.

[0791] A "database" is a system for efficiently storing and managing structured data.

[0792] The "household account book database" is a database for recording and organizing a user's spending history based on collected text information.

[0793] "Push notification" is a method of sending information from a server to a device in real time.

[0794] The "filtering function" is a function that selects and displays data based on specific conditions.

[0795] "Purchase history" is data that records detailed information about products purchased by a user in the past.

[0796] "Bargain information" is information that brings benefits, such as coupons and sales information, that is provided based on the user's purchasing history.

[0797] The present invention relates to a system that allows users to take images of receipts and send them to a server, automating the provision of discount information based on household accounting management and purchase history. The following describes the system's components and specific processing procedures in detail.

[0798] First, the user takes a picture of the receipt using a device such as a smartphone or tablet. The image taken using the device's camera app is then viewed through the application interface. The user confirms the image and taps the "Send" button.

[0799] Next, the device converts the captured image into a specific format (e.g., JPEG, PNG) and sends it to the server via a dedicated API. The image data is quality-preserving and optimized before being sent, so it arrives at the server in a clear state.

[0800] The server temporarily stores the received image data in a database and activates an image recognition module. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This technology can be used with an OCR engine such as Tesseract. The server extracts information such as the store name, product name, price, and purchase date and time in text format and stores it in the household accounting database.

[0801] The server then categorizes the extracted data for each user. For example, "Milk purchased at Supermarket A" is classified as a food item and saved along with price information. The data processing module automatically performs this task, allowing users to easily understand their spending.

[0802] The server also has an algorithm that analyzes the user's purchasing history, identifying the items frequently purchased and the stores visited over a specific period, and then searches the database for relevant deals (e.g., coupons, sales information). The relevant information found is then sent to the device as a push notification, allowing the user to receive useful information at the right time.

[0803] Finally, users can access the household accounting application on their smartphone or other device to check their spending history. The device retrieves the necessary information from the server and displays it in a visually easy-to-understand format. Filtering functions also allow users to easily check spending over specific periods or by category.

[0804] Specific examples

[0805] For example, a user buys groceries at a supermarket, takes a photo of the receipt, and sends it to the system. The server receives the image and uses OCR technology to extract information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This data is then stored in the household account book database and automatically categorized under the category "Food."

[0806] The server also analyzes the user's past purchase history and determines that they frequently purchase "milk." It then finds information about milk sales at related supermarkets and sends it to the user's device as a push notification. This allows the user to save money by using coupons the next time they shop.

[0807] Prompt Sentence Examples

[0808] Below are some example prompts to input to a generative AI model:

[0809] "Please extract the information that can be recognized from the receipt (store name, product name, price, purchase date, etc.) in text format."

[0810] "Analyze users' purchasing trends based on past purchase data and provide them with discount information based on those trends."

[0811] These prompts ensure that each processing step of the system is performed clearly.

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1: Take a photo of your receipt and send it

[0814] Users take a photo of the receipt using a smartphone or other device. If the image is not clear, OCR technology cannot accurately extract the text information. Therefore, users first check the preview of the image through the app interface. After confirming that the image is correct, users tap the "Send" button.

[0815] Input: Physical image of the receipt

[0816] Output: A digital image of the receipt stored on the user's device

[0817] The device converts the captured image into a format such as JPEG or PNG and sends it to the server via API, where it is optimized to maintain image quality.

[0818] Input: Receipt image taken by the user

[0819] Output: High-quality receipt image data sent to the server

[0820] Step 2: Image recognition and data analysis on the server side

[0821] The server receives the receipt image sent from the terminal and temporarily stores it in a database.

[0822] Input: Receipt image data sent from the device

[0823] Output: Image data temporarily stored in a database

[0824] Next, the server launches an image recognition module and uses OCR technology to extract text information from the receipt. For example, an OCR engine such as Tesseract can be used to extract text such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023" from the image.

[0825] Input: Receipt images stored in the database

[0826] Output: Extracted text data (store name, product name, price, purchase date and time)

[0827] The extracted text data is stored in a household accounting database.

[0828] Input: Extracted text data

[0829] Output: Text data stored in the household accounting database

[0830] Step 3: Categorize the data

[0831] The server categorizes the extracted data for each user, for example, into categories such as "food," "daily necessities," and "entertainment." The data processing module automatically performs this process, and the data organized for each user is saved.

[0832] Input: Text data stored in the household accounting database

[0833] Output: Categorized text data (e.g., "Milk" classified into the food category)

[0834] Step 4: Offering deals

[0835] The server has an algorithm that analyzes a user's purchasing history. It identifies the items and stores frequently purchased over a specific period of time, and then searches the database for relevant deals based on that information. For example, it might detect that the user frequently purchases "milk," and find information about milk sales at Supermarket A.

[0836] Input: Categorized text data and user purchase history

[0837] Output: Deals based on purchase history

[0838] The extracted information is sent to the device as a push notification. The server sends this information in real time, and the user can receive it.

[0839] Input: Deals based on purchase history

[0840] Output: Push notification of the deals sent to your device

[0841] Step 5: View your household budget

[0842] Users can open a household accounting application on their smartphone or other device to check their spending history. At this time, the device sends a request to the server to obtain the necessary information. The obtained information is displayed in a visually easy-to-understand format.

[0843] Input: Data request from a household finance application

[0844] Output: Spending history displayed on the device

[0845] Users can also use the device's filtering function to easily check spending over specific periods or categories, allowing them to effectively manage their finances.

[0846] Input: Filtering criteria within the household accounting application (specific period or category)

[0847] Output: Filtered spending history display

[0848] (Application example 1)

[0849] 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."

[0850] Conventional household accounting management systems and discount information systems require users to manually enter data, making them difficult to use and lacking technology to significantly simplify the in-store shopping experience. This makes it difficult for users to effectively manage their spending and receive real-time discount information based on their purchasing patterns. To address this issue, a system is needed that can automatically generate a household accounting record from photographs of receipts and provide discount information based on purchase history.

[0851] 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.

[0852] In this invention, the server includes means for capturing an image of a receipt, means for transmitting the captured image to the server, means for extracting text information from the received receipt image in the server, means for storing the extracted text information in a database, means for analyzing the user's purchase history and providing related discount information, means for transmitting the related discount information to the user's terminal as a push notification, and means for the user to capture a photo of the receipt at the physical store. This allows the user to easily obtain receipt information when shopping at the physical store, update their household ledger in real time, and receive optimal discount information based on their purchase history.

[0853] The "means for taking an image of a receipt" is a function for obtaining information on a receipt, which is a record of a commercial transaction, as a digital image.

[0854] The "means for sending the captured image to the server" is a communication function for transferring the image of the receipt captured on the user's terminal to the cloud or a remote server.

[0855] "Means for extracting text information from a received receipt image on the server" refers to a technology that analyzes the image data of a receipt on the server side and automatically identifies character and numerical information.

[0856] The "means for storing the extracted text information in a database" is a process for storing the analyzed text information in a database as structured data.

[0857] "Means of analyzing a user's purchasing history and providing relevant discount information" refers to an algorithm that analyzes data on products and services a user has purchased in the past and provides discount and campaign information based on the results.

[0858] The "means for sending relevant discount information to the user's device as a push notification" is a function that sends analyzed discount information as a notification to the user's smartphone or device in real time.

[0859] A "means for users to take photos of receipts in physical stores" is a device or interface that allows users to instantly take a digital image of a receipt when shopping at a physical store.

[0860] This invention provides a system that allows users to easily manage their household accounts and receive information on special offers at a physical store. This system is realized using a terminal, a server, and a dedicated application.

[0861] First, after shopping at a physical store, the user takes a photo of the receipt using their smartphone. The device is equipped with a camera for taking an image of the receipt and a screen for reviewing the image. The user checks the image of the receipt and taps the "Send" button to send it to the server. In this step, a dedicated application on the smartphone sends the receipt image to the server at optimal quality.

[0862] The server temporarily stores the received receipt image in a database and extracts text information from the image using OCR technology. The open source Tesseract can be used as the OCR technology. The extracted text information is stored in a database and categorized by a data analysis module. Specifically, it is automatically classified into categories such as "food," "daily necessities," and "entertainment."

[0863] The server then performs further analysis and generates relevant deals based on the user's purchasing history. It analyzes data on frequently purchased items and visited stores over a specific period to search for relevant coupons and sales information. The generated deals are then sent to the user's device as push notifications. This process essentially allows the user to receive useful information based on their purchasing patterns in real time.

[0864] Users can check their household finances at any time through this application. The application retrieves the necessary data from the server and displays the household finances in a visually easy-to-understand format. Filtering functions also make it easy to check expenditures for specific periods or categories. This allows users to manage their finances more effectively.

[0865] For example:

[0866] For example, suppose a user buys groceries at a physical store one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract text information such as "Store A," "Milk," "200 yen," and "October 12, 2023." This information is stored in a household accounting database and automatically categorized under the "Food" category. At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "Milk," and finds information about milk sales at related stores. This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[0867] Example prompt sentence:

[0868] A user took a photo of a receipt for a 200 yen bottle of milk purchased at Store A and sent it to us. Our application used OCR technology to extract the following information from the receipt:

[0869] Purchased at: Store A

[0870] Purchased item: Milk

[0871] Price: 200 yen

[0872] Purchase date: October 12, 2023

[0873] Based on this, analyze patterns from past purchase history and generate deals on milk from store A.

[0874] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0875] Step 1:

[0876] After shopping at a physical store, users take a picture of the receipt with their smartphone.

[0877] Input: receipt from physical store, smartphone camera function

[0878] Output: Digital image data of receipt

[0879] Specific operation: The user launches the smartphone camera app and takes a picture of the receipt. After taking the picture, the user checks and saves the image.

[0880] Step 2:

[0881] The terminal sends the captured receipt image to the server via the application.

[0882] Input: Digital image data of receipt

[0883] Output: Image data transferred to the server

[0884] What happens: The user taps the "Send" button in the application, and the application compresses the image and sends it to the server with optimal quality.

[0885] Step 3:

[0886] The server stores the received receipt images in a database and uses OCR technology to extract text information from the images.

[0887] Input: Image data transferred to the server

[0888] Output: Extracted text information (e.g., "store name," "product name," "price," "purchase date and time")

[0889] Specific operation: Image data stored on the server is input into an OCR engine (Tesseract), and the character information in the image is extracted as text data.

[0890] Step 4:

[0891] The server stores the extracted text information in a database and organizes it by category.

[0892] Input: Extracted text information

[0893] Output: Text information organized by category (e.g., "food," "daily necessities," "entertainment," etc.)

[0894] Specific operation: The server analyzes the text information, classifies it into pre-defined categories, and stores it in a database.

[0895] Step 5:

[0896] The server analyzes the user's purchasing history and generates relevant deals.

[0897] Input: Text information organized by category, past purchase history

[0898] Output: Related deals (e.g. coupons and sales)

[0899] Specific operation: The server analyzes the user's purchasing history data stored in a database, identifies frequently purchased products and visited stores, and obtains the most appropriate coupon and sale information based on that.

[0900] Step 6:

[0901] The server sends the generated discount information to the user's device as a push notification.

[0902] Input: Generated Deals

[0903] Output: A push notification that appears on the user's smartphone.

[0904] Specific operation: The server's notification service uses the application's push notification function to send discount information to the user's device in real time.

[0905] Step 7:

[0906] Users can view their household budget within the application and use filtering features to easily view spending for specific periods or categories.

[0907] Input: User's household accounting data, filtering conditions

[0908] Output: Filtered household information

[0909] How it works: The user opens the application, selects the period and category of information they need, and displays their household finances information. The application retrieves the necessary data from the server and displays it in a visually easy-to-understand format.

[0910] 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.

[0911] This invention relates to a receipt management system that incorporates an emotion engine that recognizes the user's emotions. In addition to automatically generating a household ledger from photographing receipts and providing information on special offers, it can also provide information that takes the user's emotional state into account.

[0912] What the program does

[0913] 1. Take a photo of your receipt and send it

[0914] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the device's built-in emotion engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[0915] The device collects the image data of the photographed receipt and the emotion data analyzed by the emotion engine. When the user taps the "Send" button, the device sends this data to the server.

[0916] 2. Image Recognition and Data Analysis

[0917] The server first temporarily stores the received receipt image data and emotion data, then launches an image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is then registered in the household accounting database.

[0918] Emotional data is added to user profiles and used in subsequent analysis stages, adding emotional information to a user's purchasing history for more accurate analysis.

[0919] 3. Analysis of purchase history and provision of discount information

[0920] The server analyzes the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, it identifies frequently purchased products and frequently visited stores. The identified information is used to provide discount information tailored to the user's emotional state.

[0921] Specifically, the server's analysis module analyzes the user's feelings toward products and services they have purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products that have a lot of positive feelings, and providing information about alternative products for products that have a lot of negative feelings.

[0922] 4. Sending push notifications

[0923] The server sends optimized discount information to the user's device as a push notification. By using the emotion engine, it is possible to provide information that is in line with the user's current emotional state, which is expected to improve user satisfaction.

[0924] 5. Viewing household accounts

[0925] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[0926] Specific examples

[0927] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[0928] At the same time, if the emotion engine detects a positive emotion in the user's facial expression, it will use that information to provide push notifications with sales and promotions related to Supermarket A's milk. Conversely, if a negative emotion is detected, it will provide sales information for alternative products or promotions at other stores.

[0929] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing optimal information based on each individual's emotional state.

[0930] The processing flow will be explained below.

[0931] Step 1:

[0932] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the emotion engine is also activated, detecting the user's facial expressions and voice.

[0933] Step 2:

[0934] The device's emotion engine analyzes the user's emotions from their facial expressions and voice, and generates emotion data such as "smiling" or "neutral" as a result of this analysis.

[0935] Step 3:

[0936] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image and emotion data to the server.

[0937] Step 4:

[0938] The device compresses the image data and emotion data and sends it to a server via the internet via a dedicated API, where it is received.

[0939] Step 5:

[0940] The server temporarily stores the received receipt image data and emotion data, then passes the data to the image recognition module. The server then uses OCR technology to extract text information from the image, such as the store name, product name, price, and purchase date and time.

[0941] Step 6:

[0942] The text information extracted by the server's OCR module is stored in the server's household accounting database, enabling centralized management of data.

[0943] Step 7:

[0944] The server's emotion analysis module analyzes the received emotion data and adds the user's emotional state to the user profile, thereby linking the user's purchasing history with the emotion data.

[0945] Step 8:

[0946] The server analyzes users' purchasing history and emotional data to identify frequently purchased products and frequently visited stores, and uses this information to find relevant coupons and sales information.

[0947] Step 9:

[0948] The server's analysis module optimizes the deals based on the user's emotional data. If there are a lot of positive emotions, it proactively provides relevant sales information and coupons. If there are a lot of negative emotions, it provides information on alternative products.

[0949] Step 10:

[0950] The server sends optimized discount information to the user's device as a push notification, allowing the user to receive appropriate information in an easy-to-use format.

[0951] Step 11:

[0952] When a user launches the app on their device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the user's device, allowing the user to check their spending history and emotional state at any time.

[0953] Through the above processing steps, the system of the present invention enables the user to automatically generate a household account book simply by photographing and sending a receipt, and provides valuable information based on the user's emotional state.

[0954] Example 2

[0955] 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."

[0956] Current receipt management systems simply take images of receipts and store that information in a database, which means they are unable to provide personalized information based on a user's purchasing history. Furthermore, they do not take the user's emotional state into account, making it difficult to provide information optimized for each individual user. This can hinder an improved user experience and potentially reduce satisfaction. The present invention aims to solve these problems by analyzing a user's emotional state and providing optimized information based on that information.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0958] In this invention, the server includes means for analyzing the user's emotional state, means for transmitting the emotional state to the server, and means for extracting text information from the received receipt image, thereby enabling personalized information to be provided that takes the user's emotional state into consideration.

[0959] A "receipt" is a paper document that records detailed information about a product or service sold and is primarily provided to the purchaser as proof of receipt.

[0960] "Image capture means" means a method of recording visual information of a physical object in digital form using a device such as a camera or scanner.

[0961] A "server" is a computer system that receives requests from client devices over a network and provides services or data.

[0962] "Text information extraction means" is a general term for software and algorithms used to identify and retrieve text and numeric information from images and data.

[0963] A "database" is a system for organizing, storing, and managing information, and allows efficient searching, adding, and updating of data based on specific conditions.

[0964] "Means for analyzing the user's emotional state" refers to functions and algorithms for identifying and evaluating psychological states and emotions based on user input such as voice and images.

[0965] "Means for transmitting emotional state to a server" is a general term for the processes and technologies used to transmit analyzed emotional data to a server over a network.

[0966] "Purchase history" is a record of past purchases made by a specific user, and includes information such as purchase date, store name, product name, and price.

[0967] "Bargain information" is a general term for information that brings economic benefits to users, such as coupons, sales information, and special promotions.

[0968] "Push notifications" are a technology that sends notifications in real time from a server directly to a user's device, and is a way of displaying information to attract the user's attention.

[0969] A "user profile" is a data set that collects and manages information about individual users, recording their personal characteristics and behavioral history.

[0970] "Categorization" is a method of classifying data or information into groups based on specific criteria, and is a technique for making management and searching more efficient.

[0971] "Coupon" means a code or ticket used as proof of purchase of a particular product or service at a discounted price.

[0972] A "generative AI model" is an algorithm or machine learning model that learns from large amounts of data and generates new data and information.

[0973] A "prompt" is text that is input into a generative AI model to specify conditions and hints for the answer that the model should generate.

[0974] This invention combines an emotion engine that analyzes user emotions to provide an optimal system for receipt management. Its main functions include taking photos of receipts, image recognition, analyzing purchase history, emotion analysis, providing discount information, and viewing household accounts.

[0975] This system is composed of devices such as smartphones, servers, and network communication means. Specific hardware components include the smartphone's camera module, emotion engine, and network module. Software components include Tesseract OCR as OCR technology, database management software, and emotion analysis algorithms.

[0976] The user uses their smartphone to take a picture of the receipt they receive at the store. At the same time, the device's built-in emotion engine simultaneously captures the user's facial expressions and voice and analyzes their emotions. When the user taps the "Send" button, the device sends the receipt image data and analyzed emotion data to the server.

[0977] The server temporarily stores the received receipt image and emotion data. Next, it launches an image recognition module and uses Tesseract OCR technology to extract text information (store name, product name, price, purchase date, etc.) from the receipt image. The extracted information is registered in the household accounting database, and the emotion data is added to the user profile.

[0978] Using the analysis module, the server analyzes the user's purchase history and emotional data. This allows the server to analyze the user's past purchasing behavior and emotional patterns, identify frequently purchased products and frequently visited stores, and provide proactive sales information and coupons for products with a high percentage of positive emotions, and provide information on alternative products for products with a high percentage of negative emotions.

[0979] The optimized discount information is sent to the user's device as a push notification from the server. By providing information that is in line with the user's current emotional state, it is expected that user satisfaction will increase.

[0980] As a concrete example, consider the case where a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract information such as "supermarket," "milk," "200 yen," and "purchase date," and stores this information in the household accounting database. At the same time, if the emotion engine analyzes the user's facial expression to indicate a positive emotion, it uses that information to provide push notifications with information about sales and promotions related to the milk at the supermarket. Conversely, if a negative emotion is analyzed, it provides information about sales of alternative products or promotions at different stores.

[0981] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing information based on each individual's emotional state.

[0982] An example of a prompt is, "Take a photo of your supermarket receipt with your smartphone and send it to the system. The system will read the information on the receipt and recommend sales information based on your emotions."

[0983] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0984] Step 1:

[0985] The user activates the smartphone camera and takes a picture of the receipt. At this time, the device's built-in emotion engine also activates, capturing the user's facial expressions and voice and analyzing the emotion data.

[0986] Input: An image of the receipt taken by the user, as well as the user's facial expression and voice.

[0987] Output: Receipt image data, parsed emotion data.

[0988] Step 2:

[0989] The device temporarily stores the image data of the photographed receipt and the emotion data analyzed by the emotion engine. It then transmits this data to the server using the network module. The transmission begins when the user taps the "Send" button.

[0990] Input: Receipt image data, parsed emotion data.

[0991] Output: The data packet to send to the server.

[0992] Step 3:

[0993] The server temporarily stores the received receipt image data and emotion data. Next, it launches an image recognition module and uses OCR technology (e.g., Tesseract OCR) to extract text information (store name, product name, price, purchase date, etc.) from the receipt image.

[0994] Input: Submitted receipt image data, emotion data.

[0995] Output: Extracted text information, stored emotion data.

[0996] Step 4:

[0997] The server stores the extracted text information and emotion data in the household accounting database, and the emotion data is added to the user profile for subsequent analysis.

[0998] Input: Extracted text information, parsed sentiment data.

[0999] Output: Text information stored in the household accounting database, emotion data stored in the user profile.

[1000] Step 5:

[1001] The server performs analysis based on the user's purchasing history and emotional data. Using the analysis module, it identifies frequently purchased products and frequently visited stores based on past purchasing behavior and emotional state. The identified information is used to provide discount information tailored to the user's emotional state.

[1002] Input: Purchase history from the household accounting database, emotion data from the user profile.

[1003] Output: Analysis results (information about frequently purchased products and stores), generation of optimized deals.

[1004] Step 6:

[1005] The server then sends the generated discount information to the user's device as a push notification, with the content of the push notification matching the user's current emotional state.

[1006] Input: Optimized deals, user emotional state.

[1007] Output: A push notification sent to the user's device.

[1008] Step 7:

[1009] Users can open the household accounting app on their device to check their spending history. The app retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. Filtering functions make it easy to check spending for specific periods or categories.

[1010] Input: Purchase history from the household ledger database.

[1011] Output: A detailed spending history displayed on the user's device.

[1012] (Application example 2)

[1013] 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."

[1014] Conventional receipt management systems can manage users' purchase history and automatically generate household accounts, but they cannot provide information that takes into account their emotional state. This makes it difficult to improve each user's individual purchasing experience and fails to increase user satisfaction. Furthermore, there is a need for systems that can provide optimal promotional information based on the user's emotional state.

[1015] 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.

[1016] In this invention, the server includes a means for capturing an image of the receipt, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for extracting text information from the received receipt image, which enables purchase history management and the provision of optimal promotion information while taking the user's emotional state into consideration.

[1017] "Means for taking an image of a receipt" refers to a device or function that a user uses to take a photo of a receipt with a camera, including cameras on smartphones and smart glasses.

[1018] The "means for transmitting the captured image to the server" is a communication function for transferring the receipt image captured by the user device to the server via the Internet.

[1019] "Means for analyzing a user's emotional state using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions and voice and identify their emotions.

[1020] The "means for extracting text information from a received receipt image" is a function that uses OCR (Optical Character Recognition) technology to extract text data such as store name, product name, and price from the image.

[1021] "Means for storing extracted text information and emotion data in a database" refers to a function for recording data extracted by OCR technology or an emotion recognition engine in a database on a server.

[1022] "Means for analyzing a user's purchasing history and emotional data and providing relevant discount information" is a function that analyzes recorded purchasing history and emotional data to generate coupons and sale information optimized for the user.

[1023] The "means for sending related discount information to the user's device as a push notification" is a function for sending the generated discount information to the user's smartphone or other device via a notification function.

[1024] This invention is a receipt management system that combines an emotion engine that recognizes the user's emotions. This system allows the user to take a photo of a receipt and send the image and emotional state to a server, enabling automatic generation of a household account book and the provision of personalized discount information. Specific implementation methods are described below.

[1025] This system can be implemented using devices such as smartphones, smart glasses, and head-mounted displays. The user uses these devices to take a picture of the receipt they receive at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At this time, the device's built-in emotion recognition engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[1026] The device collects image data of the photographed receipt and emotional data analyzed by the emotion recognition engine. When the user taps the "Send" button, the device sends this data to the server. The server first temporarily stores the received receipt image data and emotional data, then launches the image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is registered in the household accounting database. The emotional data is added to the user profile and used in subsequent analysis stages.

[1027] The server performs analysis based on the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, frequently purchased products and frequently visited stores are identified. The identified information is used to provide discount information tailored to the user's emotional state. Specifically, the server's analysis module analyzes the user's feelings toward products and services purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products with a high level of positive emotion, and providing information about alternative products for products with a high level of negative emotion.

[1028] The server sends optimized discount information to the user's device as a push notification. By using an emotion recognition engine, it is possible to provide information that is appropriate for the user's current emotional state, which is expected to improve user satisfaction.

[1029] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[1030] As a concrete example, suppose a user buys groceries at a supermarket, takes a photo of the receipt, and sends it. The server receives the image and uses OCR technology to extract text information such as "supermarket," "milk," "200 yen," and "purchase date." This information is stored in a household accounting database and automatically categorized under the "food" category. At the same time, if the emotion recognition engine detects a positive emotion from the user's facial expression, it will use that information to provide push notifications with information about sales and promotions related to milk at the supermarket. Conversely, if a negative emotion is detected, it will provide information about sales of alternative products or promotions at different stores.

[1031] An example of a prompt sentence is shown below.

[1032] "Take a photo of the receipt with your camera, press the 'Add to Household Account' button and upload the receipt image and emotion."

[1033]

[1034] "Your latest household accounting data has been updated based on the receipt data you captured. Open the app to check the details."

[1035] This not only simplifies the user's household accounting management, but also makes it possible to provide optimal information based on each individual's emotional state.

[1036] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1037] Step 1:

[1038] The user uses a device such as a smartphone to take a photo of the receipt they receive at the store.

[1039] Input: User takes a photo of the receipt with the camera

[1040] Specific operation: The device's camera module is activated and takes a photo of the entire receipt.

[1041] Step 2:

[1042] At the same time as capturing the receipt image, an emotion recognition engine is used to analyze the user's emotional state.

[1043] Input: Photographed receipt image, user facial expression data

[1044] Specific operation: The emotion recognition engine installed in the device analyzes emotional data (e.g., positive, negative, etc.) from the user's facial expressions and voice.

[1045] Step 3:

[1046] The terminal collects image data of the photographed receipt and emotional data analyzed by an emotion recognition engine, and sends the data to the server.

[1047] Input: Receipt image data, emotion data

[1048] Specific operation: When the user taps the "Send" button, this data is sent from the device to the server.

[1049] Step 4:

[1050] The server temporarily stores the received receipt image data and emotion data.

[1051] Input: Receipt image data and emotion data sent from the device

[1052] Specific operation: The server stores the received data in a temporary storage area.

[1053] Step 5:

[1054] The server runs an image recognition module to extract text information from the receipt image.

[1055] Input: Received receipt image data

[1056] Specific operation: Using OCR technology, text information such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase is extracted from the receipt image.

[1057] Step 6:

[1058] The server stores the extracted text information and emotion data in a household accounting database.

[1059] Input: Extracted text information, emotion data

[1060] What it does: This data is added to each user's profile and stored in categories.

[1061] Step 7:

[1062] The server analyzes the user's purchasing history and emotional data and generates relevant discount information.

[1063] Input: purchase history data, emotion data

[1064] How it works: The analytics module combines past purchasing behavior and emotional state to identify frequently purchased products and frequently visited stores, generating optimal coupon and sale information.

[1065] Step 8:

[1066] The server sends the generated discount information to the user's device as a push notification.

[1067] Input: Generated Deals

[1068] Specific operation: Uses push notifications to send special offers to users' smartphones and other devices.

[1069] Step 9:

[1070] Users can open the household accounting app on their device and check their spending history.

[1071] Input: Household accounting data sent from the server

[1072] How it works: The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Fourth embodiment]

[1077] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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."

[1090] This invention relates to a system that comprehensively handles everything from taking photos of receipts to automatically creating a household account book and providing discount information. This system automatically creates a household account book and provides optimal discount information to users by allowing users to simply take a photo of a receipt and send it to a server.

[1091] What the program does

[1092] This system performs processing in the following procedure.

[1093] 1. Take a photo of your receipt and send it

[1094] First, the user takes a photo of the receipt using a smartphone or other device. The captured image is then viewed through a transparent interface, and the user taps the "Send" button to send the image to the server. This process is extremely simple for the user, making it easy to manage household finances in their daily lives.

[1095] The device receives the image and uses a dedicated API to send the image data to a server over the Internet, where it is optimized to maintain image quality and transmitted without data loss.

[1096] 2. Server-side image recognition and data analysis

[1097] The server temporarily stores the received receipt image in a database and then launches an image recognition module to analyze it. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This allows it to obtain data such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase.

[1098] The acquired data is stored in a database in its original format. The data processing module then categorizes this information for each user, organizing it into categories such as "food," "daily necessities," and "entertainment." This categorization allows users to easily understand the breakdown of their expenses when checking their household account book later.

[1099] 3. Providing discount information

[1100] The server has an algorithm for analyzing the user's accumulated purchasing history. It analyzes frequently purchased items and visited stores over a specific period to understand the user's purchasing trends. Based on this, it searches the server's database for relevant deals (coupons, sales information, etc.) and extracts the most suitable information for the user.

[1101] The extracted deals are sent to the device as push notifications, allowing users to quickly receive useful information based on their purchasing patterns.

[1102] 4. Viewing household accounts

[1103] Users can open the household accounting app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format.

[1104] Additionally, the filtering feature allows users to easily view spending over a specific period or by category, allowing them to manage their finances more effectively.

[1105] Specific examples

[1106] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[1107] At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "milk." This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[1108] As a result, this system significantly simplifies household accounting management for users, while providing a practical solution that can provide valuable information based on purchasing patterns.

[1109] The processing flow will be explained below.

[1110] Step 1:

[1111] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is activated, and the user takes a picture of the entire receipt.

[1112] Step 2:

[1113] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image to the server.

[1114] Step 3:

[1115] The device compresses the captured receipt image and sends the data to a server via the Internet using a dedicated API. The image data is then passed to the server's receiving module.

[1116] Step 4:

[1117] The server first temporarily stores the received receipt image data, then passes it to the image recognition module, which uses OCR technology to extract text information from the image.

[1118] Step 5:

[1119] The server's OCR module identifies information such as the store name, product name, price, and purchase date and time from the receipt image and extracts this data in text format. The extracted information is stored in a temporary memory area.

[1120] Step 6:

[1121] The server stores the extracted text information in a database for each user. Specifically, it records items such as store information, product name, price, and purchase date individually. It also automatically organizes each item into the appropriate category.

[1122] Step 7:

[1123] The server analyzes the user's purchasing history over a certain period of time and launches an analysis module to identify frequently purchased products and frequently visited stores. The analysis results are stored as a user profile.

[1124] Step 8:

[1125] The server's analytics module searches the database for relevant coupons and sales information based on the user profile, and if applicable deals are found, prepares them as push notification content.

[1126] Step 9:

[1127] The server then sends the prepared push notification to the user's device, allowing the user to instantly receive new coupons and sales information.

[1128] Step 10:

[1129] When the user restarts the device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the device. The user can check the details of their expenses and the breakdown by category. They can also use the filtering function to easily check expenses for a specific period or by category.

[1130] Through the above processing steps, the system of the present invention allows the user to automatically generate a household account book and provide advantageous information simply by taking a photo of a receipt and sending it.

[1131] Example 1

[1132] 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."

[1133] Conventional household accounting management systems required users to manually enter information and were unable to provide discount information based on their purchasing history. This made it difficult for users to automatically manage details of purchased items or obtain appropriate discount information based on their individual purchasing patterns. Furthermore, they lacked the functionality to easily check spending history by category.

[1134] 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.

[1135] In this invention, the server includes means for extracting text information from received receipt images, means for storing the extracted text information in a database, and means for analyzing a user's purchase history and providing related discount information. This allows users to automatically manage their household finances and obtain discount information based on their individual purchase history simply by taking and sending an image of their receipt. Through the household finance application, users can check their spending history and view spending by specific period or category, enabling more detailed and efficient household management.

[1136] A "receipt image" is digital image data obtained by capturing the contents of a receipt issued for a commercial transaction or the like.

[1137] A "terminal" is an electronic device such as a smartphone or tablet used by a user.

[1138] A "server" is a centralized computer system that receives and processes data sent from terminals.

[1139] "API" stands for Application Program Interface, an interface that allows data exchange between different software applications.

[1140] "OCR" stands for Optical Character Recognition, a technology that extracts text information from images.

[1141] A "database" is a system for efficiently storing and managing structured data.

[1142] The "household account book database" is a database for recording and organizing a user's spending history based on collected text information.

[1143] "Push notification" is a method of sending information from a server to a device in real time.

[1144] The "filtering function" is a function that selects and displays data based on specific conditions.

[1145] "Purchase history" is data that records detailed information about products purchased by a user in the past.

[1146] "Bargain information" is information that brings benefits, such as coupons and sales information, that is provided based on the user's purchasing history.

[1147] The present invention relates to a system that allows users to take images of receipts and send them to a server, automating the provision of discount information based on household accounting management and purchase history. The following describes the system's components and specific processing procedures in detail.

[1148] First, the user takes a picture of the receipt using a device such as a smartphone or tablet. The image taken using the device's camera app is then viewed through the application interface. The user confirms the image and taps the "Send" button.

[1149] Next, the device converts the captured image into a specific format (e.g., JPEG, PNG) and sends it to the server via a dedicated API. The image data is quality-preserving and optimized before being sent, so it arrives at the server in a clear state.

[1150] The server temporarily stores the received image data in a database and activates an image recognition module. Specifically, it uses OCR (optical character recognition) technology to extract the text information written on the receipt. This technology can be used with an OCR engine such as Tesseract. The server extracts information such as the store name, product name, price, and purchase date and time in text format and stores it in the household accounting database.

[1151] The server then categorizes the extracted data for each user. For example, "Milk purchased at Supermarket A" is classified as a food item and saved along with price information. The data processing module automatically performs this task, allowing users to easily understand their spending.

[1152] The server also has an algorithm that analyzes the user's purchasing history, identifying the items frequently purchased and the stores visited over a specific period, and then searches the database for relevant deals (e.g., coupons, sales information). The relevant information found is then sent to the device as a push notification, allowing the user to receive useful information at the right time.

[1153] Finally, users can access the household accounting application on their smartphone or other device to check their spending history. The device retrieves the necessary information from the server and displays it in a visually easy-to-understand format. Filtering functions also allow users to easily check spending over specific periods or by category.

[1154] Specific examples

[1155] For example, a user buys groceries at a supermarket, takes a photo of the receipt, and sends it to the system. The server receives the image and uses OCR technology to extract information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This data is then stored in the household account book database and automatically categorized under the category "Food."

[1156] The server also analyzes the user's past purchase history and determines that they frequently purchase "milk." It then finds information about milk sales at related supermarkets and sends it to the user's device as a push notification. This allows the user to save money by using coupons the next time they shop.

[1157] Prompt Sentence Examples

[1158] Below are some example prompts to input to a generative AI model:

[1159] "Please extract the information that can be recognized from the receipt (store name, product name, price, purchase date, etc.) in text format."

[1160] "Analyze users' purchasing trends based on past purchase data and provide them with discount information based on those trends."

[1161] These prompts ensure that each processing step of the system is performed clearly.

[1162] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1163] Step 1: Take a photo of your receipt and send it

[1164] Users take a photo of the receipt using a smartphone or other device. If the image is not clear, OCR technology cannot accurately extract the text information. Therefore, users first check the preview of the image through the app interface. After confirming that the image is correct, users tap the "Send" button.

[1165] Input: Physical image of the receipt

[1166] Output: A digital image of the receipt stored on the user's device

[1167] The device converts the captured image into a format such as JPEG or PNG and sends it to the server via API, where it is optimized to maintain image quality.

[1168] Input: Receipt image taken by the user

[1169] Output: High-quality receipt image data sent to the server

[1170] Step 2: Image recognition and data analysis on the server side

[1171] The server receives the receipt image sent from the terminal and temporarily stores it in a database.

[1172] Input: Receipt image data sent from the device

[1173] Output: Image data temporarily stored in a database

[1174] Next, the server launches an image recognition module and uses OCR technology to extract text information from the receipt. For example, an OCR engine such as Tesseract can be used to extract text such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023" from the image.

[1175] Input: Receipt images stored in the database

[1176] Output: Extracted text data (store name, product name, price, purchase date and time)

[1177] The extracted text data is stored in a household accounting database.

[1178] Input: Extracted text data

[1179] Output: Text data stored in the household accounting database

[1180] Step 3: Categorize the data

[1181] The server categorizes the extracted data for each user, for example, into categories such as "food," "daily necessities," and "entertainment." The data processing module automatically performs this process, and the data organized for each user is saved.

[1182] Input: Text data stored in the household accounting database

[1183] Output: Categorized text data (e.g., "Milk" classified into the food category)

[1184] Step 4: Offering deals

[1185] The server has an algorithm that analyzes a user's purchasing history. It identifies the items and stores frequently purchased over a specific period of time, and then searches the database for relevant deals based on that information. For example, it might detect that the user frequently purchases "milk," and find information about milk sales at Supermarket A.

[1186] Input: Categorized text data and user purchase history

[1187] Output: Deals based on purchase history

[1188] The extracted information is sent to the device as a push notification. The server sends this information in real time, and the user can receive it.

[1189] Input: Deals based on purchase history

[1190] Output: Push notification of the deals sent to your device

[1191] Step 5: View your household budget

[1192] Users can open a household accounting application on their smartphone or other device to check their spending history. At this time, the device sends a request to the server to obtain the necessary information. The obtained information is displayed in a visually easy-to-understand format.

[1193] Input: Data request from a household finance application

[1194] Output: Spending history displayed on the device

[1195] Users can also use the device's filtering function to easily check spending over specific periods or categories, allowing them to effectively manage their finances.

[1196] Input: Filtering criteria within the household accounting application (specific period or category)

[1197] Output: Filtered spending history display

[1198] (Application example 1)

[1199] 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."

[1200] Conventional household accounting management systems and discount information systems require users to manually enter data, making them difficult to use and lacking technology to significantly simplify the in-store shopping experience. This makes it difficult for users to effectively manage their spending and receive real-time discount information based on their purchasing patterns. To address this issue, a system is needed that can automatically generate a household accounting record from photographs of receipts and provide discount information based on purchase history.

[1201] 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.

[1202] In this invention, the server includes means for capturing an image of a receipt, means for transmitting the captured image to the server, means for extracting text information from the received receipt image in the server, means for storing the extracted text information in a database, means for analyzing the user's purchase history and providing related discount information, means for transmitting the related discount information to the user's terminal as a push notification, and means for the user to capture a photo of the receipt at the physical store. This allows the user to easily obtain receipt information when shopping at the physical store, update their household ledger in real time, and receive optimal discount information based on their purchase history.

[1203] The "means for taking an image of a receipt" is a function for obtaining information on a receipt, which is a record of a commercial transaction, as a digital image.

[1204] The "means for sending the captured image to the server" is a communication function for transferring the image of the receipt captured on the user's terminal to the cloud or a remote server.

[1205] "Means for extracting text information from a received receipt image on the server" refers to a technology that analyzes the image data of a receipt on the server side and automatically identifies character and numerical information.

[1206] The "means for storing the extracted text information in a database" is a process for storing the analyzed text information in a database as structured data.

[1207] "Means of analyzing a user's purchasing history and providing relevant discount information" refers to an algorithm that analyzes data on products and services a user has purchased in the past and provides discount and campaign information based on the results.

[1208] The "means for sending relevant discount information to the user's device as a push notification" is a function that sends analyzed discount information as a notification to the user's smartphone or device in real time.

[1209] A "means for users to take photos of receipts in physical stores" is a device or interface that allows users to instantly take a digital image of a receipt when shopping at a physical store.

[1210] This invention provides a system that allows users to easily manage their household accounts and receive information on special offers at a physical store. This system is realized using a terminal, a server, and a dedicated application.

[1211] First, after shopping at a physical store, the user takes a photo of the receipt using their smartphone. The device is equipped with a camera for taking an image of the receipt and a screen for reviewing the image. The user checks the image of the receipt and taps the "Send" button to send it to the server. In this step, a dedicated application on the smartphone sends the receipt image to the server at optimal quality.

[1212] The server temporarily stores the received receipt image in a database and extracts text information from the image using OCR technology. The open source Tesseract can be used as the OCR technology. The extracted text information is stored in a database and categorized by a data analysis module. Specifically, it is automatically classified into categories such as "food," "daily necessities," and "entertainment."

[1213] The server then performs further analysis and generates relevant deals based on the user's purchasing history. It analyzes data on frequently purchased items and visited stores over a specific period to search for relevant coupons and sales information. The generated deals are then sent to the user's device as push notifications. This process essentially allows the user to receive useful information based on their purchasing patterns in real time.

[1214] Users can check their household finances at any time through this application. The application retrieves the necessary data from the server and displays the household finances in a visually easy-to-understand format. Filtering functions also make it easy to check expenditures for specific periods or categories. This allows users to manage their finances more effectively.

[1215] For example:

[1216] For example, suppose a user buys groceries at a physical store one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract text information such as "Store A," "Milk," "200 yen," and "October 12, 2023." This information is stored in a household accounting database and automatically categorized under the "Food" category. At the same time, the server analyzes the user's past purchase history and finds out that they frequently purchase "Milk," and finds information about milk sales at related stores. This information is sent to the user as a push notification, allowing them to use coupons to save money on their next purchase.

[1217] Example prompt sentence:

[1218] A user took a photo of a receipt for a 200 yen bottle of milk purchased at Store A and sent it to us. Our application used OCR technology to extract the following information from the receipt:

[1219] Purchased at: Store A

[1220] Purchased item: Milk

[1221] Price: 200 yen

[1222] Purchase date: October 12, 2023

[1223] Based on this, analyze patterns from past purchase history and generate deals on milk from store A.

[1224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1225] Step 1:

[1226] After shopping at a physical store, users take a picture of the receipt with their smartphone.

[1227] Input: receipt from physical store, smartphone camera function

[1228] Output: Digital image data of receipt

[1229] Specific operation: The user launches the smartphone camera app and takes a picture of the receipt. After taking the picture, the user checks and saves the image.

[1230] Step 2:

[1231] The terminal sends the captured receipt image to the server via the application.

[1232] Input: Digital image data of receipt

[1233] Output: Image data transferred to the server

[1234] What happens: The user taps the "Send" button in the application, and the application compresses the image and sends it to the server with optimal quality.

[1235] Step 3:

[1236] The server stores the received receipt images in a database and uses OCR technology to extract text information from the images.

[1237] Input: Image data transferred to the server

[1238] Output: Extracted text information (e.g., "store name," "product name," "price," "purchase date and time")

[1239] Specific operation: Image data stored on the server is input into an OCR engine (Tesseract), and the character information in the image is extracted as text data.

[1240] Step 4:

[1241] The server stores the extracted text information in a database and organizes it by category.

[1242] Input: Extracted text information

[1243] Output: Text information organized by category (e.g., "food," "daily necessities," "entertainment," etc.)

[1244] Specific operation: The server analyzes the text information, classifies it into pre-defined categories, and stores it in a database.

[1245] Step 5:

[1246] The server analyzes the user's purchasing history and generates relevant deals.

[1247] Input: Text information organized by category, past purchase history

[1248] Output: Related deals (e.g. coupons and sales)

[1249] Specific operation: The server analyzes the user's purchasing history data stored in a database, identifies frequently purchased products and visited stores, and obtains the most appropriate coupon and sale information based on that.

[1250] Step 6:

[1251] The server sends the generated discount information to the user's device as a push notification.

[1252] Input: Generated Deals

[1253] Output: A push notification that appears on the user's smartphone.

[1254] Specific operation: The server's notification service uses the application's push notification function to send discount information to the user's device in real time.

[1255] Step 7:

[1256] Users can view their household budget within the application and use filtering features to easily view spending for specific periods or categories.

[1257] Input: User's household accounting data, filtering conditions

[1258] Output: Filtered household information

[1259] How it works: The user opens the application, selects the period and category of information they need, and displays their household finances information. The application retrieves the necessary data from the server and displays it in a visually easy-to-understand format.

[1260] 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.

[1261] This invention relates to a receipt management system that incorporates an emotion engine that recognizes the user's emotions. In addition to automatically generating a household ledger from photographing receipts and providing information on special offers, it can also provide information that takes the user's emotional state into account.

[1262] What the program does

[1263] 1. Take a photo of your receipt and send it

[1264] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the device's built-in emotion engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[1265] The device collects the image data of the photographed receipt and the emotion data analyzed by the emotion engine. When the user taps the "Send" button, the device sends this data to the server.

[1266] 2. Image Recognition and Data Analysis

[1267] The server first temporarily stores the received receipt image data and emotion data, then launches an image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is then registered in the household accounting database.

[1268] Emotional data is added to user profiles and used in subsequent analysis stages, adding emotional information to a user's purchasing history for more accurate analysis.

[1269] 3. Analysis of purchase history and provision of discount information

[1270] The server analyzes the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, it identifies frequently purchased products and frequently visited stores. The identified information is used to provide discount information tailored to the user's emotional state.

[1271] Specifically, the server's analysis module analyzes the user's feelings toward products and services they have purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products that have a lot of positive feelings, and providing information about alternative products for products that have a lot of negative feelings.

[1272] 4. Sending push notifications

[1273] The server sends optimized discount information to the user's device as a push notification. By using the emotion engine, it is possible to provide information that is in line with the user's current emotional state, which is expected to improve user satisfaction.

[1274] 5. Viewing household accounts

[1275] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[1276] Specific examples

[1277] For example, suppose a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it to the server. The server receives the image and uses OCR technology to extract text information such as "Supermarket A," "Milk," "200 yen," and "October 12, 2023." This information is stored in the household accounting database and automatically categorized under the category "Food."

[1278] At the same time, if the emotion engine detects a positive emotion in the user's facial expression, it will use that information to provide push notifications with sales and promotions related to Supermarket A's milk. Conversely, if a negative emotion is detected, it will provide sales information for alternative products or promotions at other stores.

[1279] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing optimal information based on each individual's emotional state.

[1280] The processing flow will be explained below.

[1281] Step 1:

[1282] The user uses a device such as a smartphone to take a picture of the receipt they received at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At the same time, the emotion engine is also activated, detecting the user's facial expressions and voice.

[1283] Step 2:

[1284] The device's emotion engine analyzes the user's emotions from their facial expressions and voice, and generates emotion data such as "smiling" or "neutral" as a result of this analysis.

[1285] Step 3:

[1286] The user checks the image of the receipt they have taken, and after making sure that the image is clear, taps the "Send" button. The device prepares to send the receipt image and emotion data to the server.

[1287] Step 4:

[1288] The device compresses the image data and emotion data and sends it to a server via the internet via a dedicated API, where it is received.

[1289] Step 5:

[1290] The server temporarily stores the received receipt image data and emotion data, then passes the data to the image recognition module. The server then uses OCR technology to extract text information from the image, such as the store name, product name, price, and purchase date and time.

[1291] Step 6:

[1292] The text information extracted by the server's OCR module is stored in the server's household accounting database, enabling centralized management of data.

[1293] Step 7:

[1294] The server's emotion analysis module analyzes the received emotion data and adds the user's emotional state to the user profile, thereby linking the user's purchasing history with the emotion data.

[1295] Step 8:

[1296] The server analyzes users' purchasing history and emotional data to identify frequently purchased products and frequently visited stores, and uses this information to find relevant coupons and sales information.

[1297] Step 9:

[1298] The server's analysis module optimizes the deals based on the user's emotional data. If there are a lot of positive emotions, it proactively provides relevant sales information and coupons. If there are a lot of negative emotions, it provides information on alternative products.

[1299] Step 10:

[1300] The server sends optimized discount information to the user's device as a push notification, allowing the user to receive appropriate information in an easy-to-use format.

[1301] Step 11:

[1302] When a user launches the app on their device and opens the household accounting app, the latest household accounting data is synchronized from the server and displayed on the user's device, allowing the user to check their spending history and emotional state at any time.

[1303] Through the above processing steps, the system of the present invention enables the user to automatically generate a household account book simply by photographing and sending a receipt, and provides valuable information based on the user's emotional state.

[1304] Example 2

[1305] 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."

[1306] Current receipt management systems simply take images of receipts and store that information in a database, which means they are unable to provide personalized information based on a user's purchasing history. Furthermore, they do not take the user's emotional state into account, making it difficult to provide information optimized for each individual user. This can hinder an improved user experience and potentially reduce satisfaction. The present invention aims to solve these problems by analyzing a user's emotional state and providing optimized information based on that information.

[1307] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1308] In this invention, the server includes means for analyzing the user's emotional state, means for transmitting the emotional state to the server, and means for extracting text information from the received receipt image, thereby enabling personalized information to be provided that takes the user's emotional state into consideration.

[1309] A "receipt" is a paper document that records detailed information about a product or service sold and is primarily provided to the purchaser as proof of receipt.

[1310] "Image capture means" means a method of recording visual information of a physical object in digital form using a device such as a camera or scanner.

[1311] A "server" is a computer system that receives requests from client devices over a network and provides services or data.

[1312] "Text information extraction means" is a general term for software and algorithms used to identify and retrieve text and numeric information from images and data.

[1313] A "database" is a system for organizing, storing, and managing information, and allows efficient searching, adding, and updating of data based on specific conditions.

[1314] "Means for analyzing the user's emotional state" refers to functions and algorithms for identifying and evaluating psychological states and emotions based on user input such as voice and images.

[1315] "Means for transmitting emotional state to a server" is a general term for the processes and technologies used to transmit analyzed emotional data to a server over a network.

[1316] "Purchase history" is a record of past purchases made by a specific user, and includes information such as purchase date, store name, product name, and price.

[1317] "Bargain information" is a general term for information that brings economic benefits to users, such as coupons, sales information, and special promotions.

[1318] "Push notifications" are a technology that sends notifications in real time from a server directly to a user's device, and is a way of displaying information to attract the user's attention.

[1319] A "user profile" is a data set that collects and manages information about individual users, recording their personal characteristics and behavioral history.

[1320] "Categorization" is a method of classifying data or information into groups based on specific criteria, and is a technique for making management and searching more efficient.

[1321] "Coupon" means a code or ticket used as proof of purchase of a particular product or service at a discounted price.

[1322] A "generative AI model" is an algorithm or machine learning model that learns from large amounts of data and generates new data and information.

[1323] A "prompt" is text that is input into a generative AI model to specify conditions and hints for the answer that the model should generate.

[1324] This invention combines an emotion engine that analyzes user emotions to provide an optimal system for receipt management. Its main functions include taking photos of receipts, image recognition, analyzing purchase history, emotion analysis, providing discount information, and viewing household accounts.

[1325] This system is composed of devices such as smartphones, servers, and network communication means. Specific hardware components include the smartphone's camera module, emotion engine, and network module. Software components include Tesseract OCR as OCR technology, database management software, and emotion analysis algorithms.

[1326] The user uses their smartphone to take a picture of the receipt they receive at the store. At the same time, the device's built-in emotion engine simultaneously captures the user's facial expressions and voice and analyzes their emotions. When the user taps the "Send" button, the device sends the receipt image data and analyzed emotion data to the server.

[1327] The server temporarily stores the received receipt image and emotion data. Next, it launches an image recognition module and uses Tesseract OCR technology to extract text information (store name, product name, price, purchase date, etc.) from the receipt image. The extracted information is registered in the household accounting database, and the emotion data is added to the user profile.

[1328] Using the analysis module, the server analyzes the user's purchase history and emotional data. This allows the server to analyze the user's past purchasing behavior and emotional patterns, identify frequently purchased products and frequently visited stores, and provide proactive sales information and coupons for products with a high percentage of positive emotions, and provide information on alternative products for products with a high percentage of negative emotions.

[1329] The optimized discount information is sent to the user's device as a push notification from the server. By providing information that is in line with the user's current emotional state, it is expected that user satisfaction will increase.

[1330] As a concrete example, consider the case where a user buys groceries at a supermarket one day and takes a photo of the receipt and sends it. The server receives the image and uses OCR technology to extract information such as "supermarket," "milk," "200 yen," and "purchase date," and stores this information in the household accounting database. At the same time, if the emotion engine analyzes the user's facial expression to indicate a positive emotion, it uses that information to provide push notifications with information about sales and promotions related to the milk at the supermarket. Conversely, if a negative emotion is analyzed, it provides information about sales of alternative products or promotions at different stores.

[1331] In this way, this system not only simplifies the user's household accounting management, but also increases overall satisfaction by providing information based on each individual's emotional state.

[1332] An example of a prompt is, "Take a photo of your supermarket receipt with your smartphone and send it to the system. The system will read the information on the receipt and recommend sales information based on your emotions."

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1:

[1335] The user activates the smartphone camera and takes a picture of the receipt. At this time, the device's built-in emotion engine also activates, capturing the user's facial expressions and voice and analyzing the emotion data.

[1336] Input: An image of the receipt taken by the user, as well as the user's facial expression and voice.

[1337] Output: Receipt image data, parsed emotion data.

[1338] Step 2:

[1339] The device temporarily stores the image data of the photographed receipt and the emotion data analyzed by the emotion engine. It then transmits this data to the server using the network module. The transmission begins when the user taps the "Send" button.

[1340] Input: Receipt image data, parsed emotion data.

[1341] Output: The data packet to send to the server.

[1342] Step 3:

[1343] The server temporarily stores the received receipt image data and emotion data. Next, it launches an image recognition module and uses OCR technology (e.g., Tesseract OCR) to extract text information (store name, product name, price, purchase date, etc.) from the receipt image.

[1344] Input: Submitted receipt image data, emotion data.

[1345] Output: Extracted text information, stored emotion data.

[1346] Step 4:

[1347] The server stores the extracted text information and emotion data in the household accounting database, and the emotion data is added to the user profile for subsequent analysis.

[1348] Input: Extracted text information, parsed sentiment data.

[1349] Output: Text information stored in the household accounting database, emotion data stored in the user profile.

[1350] Step 5:

[1351] The server performs analysis based on the user's purchasing history and emotional data. Using the analysis module, it identifies frequently purchased products and frequently visited stores based on past purchasing behavior and emotional state. The identified information is used to provide discount information tailored to the user's emotional state.

[1352] Input: Purchase history from the household accounting database, emotion data from the user profile.

[1353] Output: Analysis results (information about frequently purchased products and stores), generation of optimized deals.

[1354] Step 6:

[1355] The server then sends the generated discount information to the user's device as a push notification, with the content of the push notification matching the user's current emotional state.

[1356] Input: Optimized deals, user emotional state.

[1357] Output: A push notification sent to the user's device.

[1358] Step 7:

[1359] Users can open the household accounting app on their device to check their spending history. The app retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. Filtering functions make it easy to check spending for specific periods or categories.

[1360] Input: Purchase history from the household ledger database.

[1361] Output: A detailed spending history displayed on the user's device.

[1362] (Application example 2)

[1363] 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."

[1364] Conventional receipt management systems can manage users' purchase history and automatically generate household accounts, but they cannot provide information that takes into account their emotional state. This makes it difficult to improve each user's individual purchasing experience and fails to increase user satisfaction. Furthermore, there is a need for systems that can provide optimal promotional information based on the user's emotional state.

[1365] 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.

[1366] In this invention, the server includes a means for capturing an image of the receipt, a means for analyzing the user's emotional state using an emotion recognition engine, and a means for extracting text information from the received receipt image, which enables purchase history management and the provision of optimal promotion information while taking the user's emotional state into consideration.

[1367] "Means for taking an image of a receipt" refers to a device or function that a user uses to take a photo of a receipt with a camera, including cameras on smartphones and smart glasses.

[1368] The "means for transmitting the captured image to the server" is a communication function for transferring the receipt image captured by the user device to the server via the Internet.

[1369] "Means for analyzing a user's emotional state using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions and voice and identify their emotions.

[1370] The "means for extracting text information from a received receipt image" is a function that uses OCR (Optical Character Recognition) technology to extract text data such as store name, product name, and price from the image.

[1371] "Means for storing extracted text information and emotion data in a database" refers to a function for recording data extracted by OCR technology or an emotion recognition engine in a database on a server.

[1372] "Means for analyzing a user's purchasing history and emotional data and providing relevant discount information" is a function that analyzes recorded purchasing history and emotional data to generate coupons and sale information optimized for the user.

[1373] The "means for sending related discount information to the user's device as a push notification" is a function for sending the generated discount information to the user's smartphone or other device via a notification function.

[1374] This invention is a receipt management system that combines an emotion engine that recognizes the user's emotions. This system allows the user to take a photo of a receipt and send the image and emotional state to a server, enabling automatic generation of a household account book and the provision of personalized discount information. Specific implementation methods are described below.

[1375] This system can be implemented using devices such as smartphones, smart glasses, and head-mounted displays. The user uses these devices to take a picture of the receipt they receive at the store. The device's camera module is then activated, and the user takes a picture of the entire receipt. At this time, the device's built-in emotion recognition engine is also activated, and the emotion is analyzed from the user's facial expressions and voice.

[1376] The device collects image data of the photographed receipt and emotional data analyzed by the emotion recognition engine. When the user taps the "Send" button, the device sends this data to the server. The server first temporarily stores the received receipt image data and emotional data, then launches the image recognition module for analysis. Specifically, OCR technology is used to extract text information (store name, product name, price, purchase date and time, etc.) from the receipt image. The extracted information is registered in the household accounting database. The emotional data is added to the user profile and used in subsequent analysis stages.

[1377] The server performs analysis based on the user's purchasing history and emotional data. Based on past purchasing behavior and emotional state, frequently purchased products and frequently visited stores are identified. The identified information is used to provide discount information tailored to the user's emotional state. Specifically, the server's analysis module analyzes the user's feelings toward products and services purchased in the past, and performs optimization such as providing more proactive sales information and coupons for products with a high level of positive emotion, and providing information about alternative products for products with a high level of negative emotion.

[1378] The server sends optimized discount information to the user's device as a push notification. By using an emotion recognition engine, it is possible to provide information that is appropriate for the user's current emotional state, which is expected to improve user satisfaction.

[1379] Users can open the household account book app on their device at any time to check their spending history. The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[1380] As a concrete example, suppose a user buys groceries at a supermarket, takes a photo of the receipt, and sends it. The server receives the image and uses OCR technology to extract text information such as "supermarket," "milk," "200 yen," and "purchase date." This information is stored in a household accounting database and automatically categorized under the "food" category. At the same time, if the emotion recognition engine detects a positive emotion from the user's facial expression, it will use that information to provide push notifications with information about sales and promotions related to milk at the supermarket. Conversely, if a negative emotion is detected, it will provide information about sales of alternative products or promotions at different stores.

[1381] An example of a prompt sentence is shown below.

[1382] "Take a photo of the receipt with your camera, press the 'Add to Household Account' button and upload the receipt image and emotion."

[1383]

[1384] "Your latest household accounting data has been updated based on the receipt data you captured. Open the app to check the details."

[1385] This not only simplifies the user's household accounting management, but also makes it possible to provide optimal information based on each individual's emotional state.

[1386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1387] Step 1:

[1388] The user uses a device such as a smartphone to take a photo of the receipt they receive at the store.

[1389] Input: User takes a photo of the receipt with the camera

[1390] Specific operation: The device's camera module is activated and takes a photo of the entire receipt.

[1391] Step 2:

[1392] At the same time as capturing the receipt image, an emotion recognition engine is used to analyze the user's emotional state.

[1393] Input: Photographed receipt image, user facial expression data

[1394] Specific operation: The emotion recognition engine installed in the device analyzes emotional data (e.g., positive, negative, etc.) from the user's facial expressions and voice.

[1395] Step 3:

[1396] The terminal collects image data of the photographed receipt and emotional data analyzed by an emotion recognition engine, and sends the data to the server.

[1397] Input: Receipt image data, emotion data

[1398] Specific operation: When the user taps the "Send" button, this data is sent from the device to the server.

[1399] Step 4:

[1400] The server temporarily stores the received receipt image data and emotion data.

[1401] Input: Receipt image data and emotion data sent from the device

[1402] Specific operation: The server stores the received data in a temporary storage area.

[1403] Step 5:

[1404] The server runs an image recognition module to extract text information from the receipt image.

[1405] Input: Received receipt image data

[1406] Specific operation: Using OCR technology, text information such as the name of the store where the purchase was made, the product name, price, and the date and time of purchase is extracted from the receipt image.

[1407] Step 6:

[1408] The server stores the extracted text information and emotion data in a household accounting database.

[1409] Input: Extracted text information, emotion data

[1410] What it does: This data is added to each user's profile and stored in categories.

[1411] Step 7:

[1412] The server analyzes the user's purchasing history and emotional data and generates relevant discount information.

[1413] Input: purchase history data, emotion data

[1414] How it works: The analytics module combines past purchasing behavior and emotional state to identify frequently purchased products and frequently visited stores, generating optimal coupon and sale information.

[1415] Step 8:

[1416] The server sends the generated discount information to the user's device as a push notification.

[1417] Input: Generated Deals

[1418] Specific operation: Uses push notifications to send special offers to users' smartphones and other devices.

[1419] Step 9:

[1420] Users can open the household accounting app on their device and check their spending history.

[1421] Input: Household accounting data sent from the server

[1422] How it works: The device retrieves the necessary information (purchase date, store name, purchased item, price, etc.) from the server and displays it in a visually easy-to-understand format. The filtering function makes it easy to check spending for a specific period or by category.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1428] 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.

[1429] 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).

[1430] 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.

[1431] 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."

[1432] 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.

[1433] 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).

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1444] The following is further disclosed regarding the above embodiment.

[1445] (Claim 1)

[1446] means for capturing an image of a receipt;

[1447] means for transmitting the captured image to a server;

[1448] A server extracts text information from the received receipt image;

[1449] means for storing the extracted text information in a database;

[1450] A means for analyzing a user's purchasing history and providing relevant deals;

[1451] means for sending relevant deals to the user's device as push notifications;

[1452] A system including:

[1453] (Claim 2)

[1454] a means for storing the extracted text information in a household account book database in the server;

[1455] further comprising means for categorizing the stored data by user;

[1456] 10. The system of claim 1.

[1457] (Claim 3)

[1458] A means of analyzing users' past purchasing data to identify frequently purchased products and frequently visited stores,

[1459] The method further includes means for extracting related coupon and sale information based on the identified information.

[1460] 10. The system of claim 1.

[1461] "Example 1"

[1462] (Claim 1)

[1463] means for capturing an image of a receipt;

[1464] means for transmitting the captured image to a server;

[1465] A server extracts text information from the received receipt image;

[1466] means for storing the extracted text information in a database;

[1467] A means for analyzing a user's purchasing history and providing relevant deals;

[1468] means for sending relevant deals to the user's device as push notifications;

[1469] Users can open a household accounting application on their device to check their spending history and use the filtering function to display spending for specific periods or categories.

[1470] A system including:

[1471] (Claim 2)

[1472] a means for storing the extracted text information in a household account book database in the server;

[1473] further comprising means for categorizing the stored data by user;

[1474] 10. The system of claim 1.

[1475] (Claim 3)

[1476] A means for a user to preview an image taken, check necessary parts, and send them to a server;

[1477] the server further comprising means for optimizing data processing while preserving image quality;

[1478] 10. The system of claim 1.

[1479] "Application Example 1"

[1480] (Claim 1)

[1481] means for capturing an image of a receipt;

[1482] means for transmitting the captured image to a server;

[1483] A server extracts text information from the received receipt image;

[1484] means for storing the extracted text information in a database;

[1485] A means for analyzing a user's purchasing history and providing relevant deals;

[1486] means for sending relevant deals to the user's device as push notifications;

[1487] A means for a user to take a photo of a receipt at a physical store;

[1488] A system including:

[1489] (Claim 2)

[1490] a means for storing the extracted text information in a household account book database in the server;

[1491] further comprising means for categorizing the stored data by user;

[1492] A means for a user to take a photo of a receipt at a physical store,

[1493] 10. The system of claim 1.

[1494] (Claim 3)

[1495] A means of analyzing users' past purchasing data to identify frequently purchased products and frequently visited stores,

[1496] The method further includes means for extracting related coupon and sale information based on the identified information.

[1497] includes a means for generating relevant offers;

[1498] 10. The system of claim 1.

[1499] "Example 2: Combining Emotion Engines"

[1500] New Claims

[1501] (Claim 1)

[1502] means for capturing an image of a receipt;

[1503] means for transmitting the captured image to a server;

[1504] means for analyzing the emotional state of a user;

[1505] means for transmitting the emotional state to a server;

[1506] A server extracts text information from the received receipt image;

[1507] a means for storing the extracted text information and emotion data in a database;

[1508] A means of analyzing users' purchasing history and emotional data to provide relevant deals;

[1509] means for sending relevant deals to the user's device as push notifications;

[1510] A system including:

[1511] (Claim 2)

[1512] a means for storing the extracted text information in a household account book database in the server;

[1513] means for adding emotion data to a user profile;

[1514] further comprising means for categorizing the stored data by user;

[1515] 10. The system of claim 1.

[1516] (Claim 3)

[1517] A means to analyze users' past purchase data and emotional data to identify frequently purchased products and frequently visited stores,

[1518] The method further includes means for extracting related coupon and sale information based on the identified information.

[1519] 10. The system of claim 1.

[1520] "Application example 2 when combining emotion engines"

[1521] (Claim 1)

[1522] means for capturing an image of a receipt;

[1523] means for transmitting the captured image to a server;

[1524] means for analyzing a user's emotional state using an emotion recognition engine;

[1525] A server extracts text information from the received receipt image;

[1526] a means for storing the extracted text information and emotion data in a database;

[1527] A means for analyzing a user's purchase history and emotional data and providing relevant deals;

[1528] means for sending relevant deals to the user's device as push notifications;

[1529] A system including:

[1530] (Claim 2)

[1531] a means for storing the extracted text information and emotion data in a household account book database in the server;

[1532] further comprising means for categorizing the stored data by user;

[1533] 10. The system of claim 1.

[1534] (Claim 3)

[1535] A means for analyzing a user's past purchase data and emotional data to identify frequently purchased products and frequently visited stores;

[1536] The method further includes means for extracting related coupon and sale information based on the identified information.

[1537] 10. The system of claim 1. [Explanation of symbols]

[1538] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing an image of a receipt; means for transmitting the captured image to a server; A server extracts text information from the received receipt image; means for storing the extracted text information in a database; A means for analyzing a user's purchasing history and providing relevant deals; means for sending relevant deals to the user's device as push notifications; A system including:

2. a means for storing the extracted text information in a household account book database in the server; further comprising means for categorizing the stored data by user; The system of claim 1 .

3. A means of analyzing users' past purchasing data to identify frequently purchased products and frequently visited stores, The method further includes means for extracting related coupon and sale information based on the identified information. The system of claim 1 .

Images