System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining image information; means for using a generative model to analyze and convert the image information into text data; and means for transmitting the text data to a plurality of systems.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] Even in today's paperless world, there is still the task of manually inputting paper documents into in-house systems, which reduces work efficiency and causes input errors. To solve this problem, documents need to be digitized and processed efficiently. [Means for solving the problem]

[0005] The present invention provides a system that acquires image information, analyzes the image information, converts the image information into text data, and transmits the text data to multiple systems. Specifically, the system includes a means for acquiring image information, a means for converting the acquired image information into text data using a generative model, and a means for transmitting the generated text data to multiple systems. Furthermore, by transmitting captured image information to a central processing unit and configuring the generative model using a machine learning algorithm, the system can efficiently and accurately convert image information into text data. This improves operational efficiency and reduces input errors.

[0006] "Means for acquiring image information" refers to technologies and methods for capturing images of paper media such as documents and application forms using devices such as smartphones or digital cameras, and storing and transmitting them in digital format.

[0007] "Means using a generative model to analyze the image information and convert it into text data" refers to techniques or methods that use machine learning algorithms or generative AI to recognize characters or symbols from captured images and convert that information into text format.

[0008] "Means for transmitting the text data to multiple systems" refers to a technique or method for transmitting the generated text data to multiple different computer systems or applications via a network, and performing the necessary processing and storage in each system.

[0009] "Means for transmitting captured image information to a central processing unit" refers to the technology or method for transmitting image data captured by a smartphone or camera to a central computer or server via the Internet or a dedicated communication network.

[0010] "The generative model is constructed using a machine learning algorithm" refers to training and operating the model using a type of machine learning, such as a neural network or deep learning, to generate text data from images. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] System configuration and processing overview

[0033] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. This system captures images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and then transmits the converted text data to multiple systems.

[0034] User operations

[0035] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0036] Terminal handling

[0037] The device performs operations to send the captured image to the server. Specifically, it sends the image data to the server using an HTTP POST request. At this time, the image data is compressed if necessary and converted into a format suitable for transmission.

[0038] Server Processing

[0039] The server receives the image data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion.

[0040] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0041] Specific examples

[0042] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0043] 1. The user takes a photo of the receipt using the smartphone camera.

[0044] 2. The device sends the captured image data to the server.

[0045] 3. The server passes the received image data to the generation AI and converts it into text data.

[0046] 4. The generated text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0047] 5. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0048] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data capture and processing. This system is expected to significantly reduce operation time and eliminate input errors.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0052] Step 2:

[0053] The device sends the captured image data to the server. The device then sends the saved image file to the server in the form of an HTTP POST request. At this time, the image data is compressed and, if necessary, encrypted before being sent.

[0054] Step 3:

[0055] The server receives the image data sent from the device. The server receives a request at a specific endpoint (e.g., / upload) and retrieves the image data.

[0056] Step 4:

[0057] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0058] Step 5:

[0059] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0060] Step 6:

[0061] The server sends text data to multiple systems. The server sends an HTTP POST request to the API endpoint of each system to send the text data. The destination systems are expense reimbursement systems, accounting systems, etc.

[0062] Step 7:

[0063] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0064] Step 8:

[0065] The user checks the results. Once the process is complete, the user can check the status of the document they sent through the application. Check whether the text conversion and data saving were successful.

[0066] These are the steps required to digitize image data and efficiently import it into multiple systems as text data, improving operational efficiency and significantly reducing the risk of data entry errors.

[0067] Example 1

[0068] 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."

[0069] Digitizing traditional paper documents and application forms requires manual data entry, which wastes time and effort and introduces the risk of input errors. It is necessary to solve this problem and provide an efficient and accurate way to convert paper documents into digital form.

[0070] 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.

[0071] In this invention, the server includes means for acquiring image information on a terminal, means for transmitting the image information to the server using an HTTP POST request, means for converting the image information into text data using a generative AI model on the server, and means for transmitting the text data to API endpoints of multiple external systems. This allows a user to photograph a document, generate accurate digital data with simple operations, and automatically import it into various systems.

[0072] A "terminal" is a portable information terminal for acquiring images and transmitting data via communication.

[0073] "Image information" refers to digital data obtained by capturing paper documents or application forms using a photographing device such as a camera.

[0074] An "HTTP POST request" is a type of communication protocol for sending data from a client to a server over the Internet.

[0075] A "server" is a computing device that processes the received image information and converts it into text data using a generative AI model.

[0076] A "generative AI model" is an artificial intelligence technology that uses machine learning algorithms to analyze image information and convert character information into text data.

[0077] "Text data" is digital data containing text information extracted from image information by a generative AI model.

[0078] An "API endpoint" refers to an interface configured to communicate with another system, and is an access point for sending and receiving data.

[0079] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. Specifically, the system allows users to acquire image information using their devices, convert it into text using a generative AI model via a server, and then transmit the converted text data to multiple systems.

[0080] User operations

[0081] The user uses the device's camera to take a photo of a paper document or application form. Once the photo is taken, the image is saved on the device. The user then uses a specific application to send the saved image to the server. To do this, the user simply takes the photo and presses the send button as instructed by the application.

[0082] Terminal handling

[0083] The device uses an HTTP POST request to send the captured image information to the server. At this time, the image data is compressed if necessary and converted into a format suitable for transmission (e.g., JPEG or PNG). The device also has the function to compress image information and convert it into a format suitable for transmission.

[0084] Server Processing

[0085] The server receives the image data sent from the device. After receiving the data, the server uses a generative AI model to convert the image information into text data. The generative AI model uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion. An example of a prompt sent to the generative AI model could be, "Please convert the characters in this image into text data." The converted text data is returned to the server.

[0086] After receiving the converted text data, the server sends it to various systems. Specifically, the server sequentially calls the API endpoints of multiple systems and sends the generated text data. Each system automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0087] Specific examples

[0088] For example, when a user scans a receipt for expense reimbursement, the process goes something like this: The user takes a picture of the receipt using the camera on their smartphone and sends the image data to a server via a specific application. The server passes the received image data to a generative AI model and converts it into text data. The generated text data is then sent to multiple internal systems, such as expense reimbursement systems and accounting systems. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0089] With such a system, all a user has to do is take a photo of a document and send it, and all processing is done automatically, which is expected to significantly reduce operation time and eliminate input errors.

[0090] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0091] Step 1: The user takes a photo of the document on their device

[0092] The user takes a photo of a paper document or application form using the device's camera. The input is the paper document, and the output is digital image data. Once the photo is taken, the image data is saved in the device. Specifically, the user launches the camera app, positions the document within the camera's screen, and presses the shutter button.

[0093] Step 2: The device sends the image to the server

[0094] The device compresses the stored image data and converts it into a format suitable for transmission. The input is the stored image data, and the output is the compressed image data. Specifically, an HTTP POST request is created and a payload containing the image data is sent to the server. The user performs this operation using a specific application. Specifically, the user launches the application, selects an image, and presses the send button.

[0095] Step 3: The server receives the image data.

[0096] The server receives the HTTP POST request sent from the terminal and retrieves the image data. The input is the image data sent from the terminal, and the output is the image data stored on the server. After receiving the data, the server checks the integrity of the data and whether the image is corrupted. Specifically, the server listens for HTTP requests, extracts the image data, and temporarily stores it.

[0097] Step 4: The server uses the generative AI model to convert the image into text data.

[0098] The server inputs the saved image data into the generative AI model and sends it along with the prompt "Please convert the characters in this image into text data." The input is the image data and the prompt, and the output is the generated text data. The generative AI model uses a machine learning algorithm to analyze the image information and extract and convert the text information. Specifically, the server passes the image data to the generative AI model and obtains the analysis results.

[0099] Step 5: The server sends the text data to multiple systems

[0100] After receiving the generated text data, the server sends it sequentially to the API endpoints of various systems. The input is the generated text data, and the output is the text data sent to each system. Specifically, the API endpoints of multiple systems are called and the generated text data is sent. In concrete terms, the server creates an HTTP POST request to each endpoint and sends the data.

[0101] In this way, by adding detailed descriptions of the specific operations performed at each processing step and their inputs and outputs, the overall flow and operation of the system becomes clearer.

[0102] (Application example 1)

[0103] 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."

[0104] There is a need to efficiently digitize paper-based information such as coupons and receipts in physical stores and instantly link it to related systems to ensure fast and accurate data exchange between customers and stores. Another important issue is reducing the workload associated with the manual processing of coupons and receipts and improving the accuracy of data management.

[0105] 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.

[0106] In this invention, the server includes means for acquiring image information, means for analyzing the image information and using a generative model to convert it into text data, means for linking the converted text data to a sales data management system, and means for linking the text data to an inventory management system. This makes it possible to efficiently digitize information on paper media and instantly link it to related systems automatically.

[0107] "Means for acquiring image information" refers to a function for acquiring images of paper coupons and receipts using a photographing device such as a smartphone or camera.

[0108] "Means for using a generative model to analyze image information and convert it into text data" refers to a function for analyzing an acquired image using an AI model, in particular a generative AI model, and converting the text information in the image into digital text.

[0109] The "means for transmitting the converted text data to a plurality of systems" is a function for transmitting the generated text data to a plurality of systems, such as a sales data management system and an inventory management system, via a server.

[0110] The "means for linking the text data to a sales data management system" is a function for instantly linking the text data to a store's sales data management system, making it available as sales-related data.

[0111] The "means for linking the text data to an inventory management system" is a function for transmitting the converted text data to an inventory management system and managing and updating inventory in real time.

[0112] This invention provides a system that converts paper coupons and receipts from physical stores into digital format and instantly connects with related systems.

[0113] Program Generation

[0114] The system for realizing the present invention uses the following hardware and software.

[0115] Smartphone: A device that allows users to take pictures of paper coupons and receipts.

[0116] Server: A device that receives image data and performs analysis and text conversion.

[0117] Generative AI models are used to extract textual information from captured images and convert it into text data. Examples include Google Cloud Vision and AWS Rekognition.

[0118] Sales data management system and inventory management system: A system that receives converted text data and processes the data.

[0119] Processing Description

[0120] Smartphone

[0121] A user uses a smartphone to take a picture of a paper coupon or receipt, and the image data is compressed and sent to the server using an HTTP POST request.

[0122] server

[0123] The server receives the captured image data and passes it to the generative AI model for text conversion. The generative AI model uses a machine learning algorithm to extract text information from the image with high accuracy and convert it into text data. The converted text data is then sent to the sales data management system and inventory management system.

[0124] Sales data management system and inventory management system

[0125] These systems receive text data and update and manage the data in real time. For example, information on coupons used by customers is aggregated in a sales data management system, and inventory information is updated in an inventory management system.

[0126] Specific examples

[0127] For example, when a customer takes a photo of a coupon to be used at a store with their smartphone, the following process takes place.

[0128] 1. The user takes a photo of the coupon using their smartphone camera.

[0129] 2. The smartphone compresses the captured image and sends it to the server.

[0130] 3. The server passes the received image to the generative AI model and converts it into text data.

[0131] 4. The server sends the converted text data to the sales data management system and the inventory management system.

[0132] 5. The system uses the received data to record coupon redemptions and update inventory information.

[0133] Prompt Sentence Examples

[0134] The company will build a system that converts coupons and receipts into digital format and instantly transmits the data to store sales data management systems and inventory management systems. The system will have functions for taking images with a smartphone, converting them into text using a generative AI model, and automatically linking data.

[0135] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0136] Step 1:

[0137] A user takes a photo of a paper coupon or receipt with their smartphone camera. The user opens the camera app, frames the subject, and presses the shutter button. The input is the paper (coupon or receipt), and the output is digital image data.

[0138] Step 2:

[0139] The device compresses the captured image data and sends it to the server using an HTTP POST request. This reduces the size of the image data and improves communication speed. The input is digital image data, and the output is compressed image data (binary data).

[0140] Step 3:

[0141] The server takes the image data received via the HTTP POST request and decompresses it into the appropriate format. The server then decompresses the received binary data into image data. The input is the compressed image data, and the output is the original digital image data.

[0142] Step 4:

[0143] The server passes the extracted image data to a generative AI model, which extracts character information and converts it into text data. The generative AI model uses a machine learning algorithm to analyze the characters in the image. The input is digital image data, and the output is analyzed text data.

[0144] Step 5:

[0145] The server sends the generated text data to the sales data management system and the inventory management system. The server transfers the text data to each system via an API endpoint. The input is the parsed text data, and the output is the text data sent to each system.

[0146] Step 6:

[0147] The sales data management system and inventory management system use the received text data to update and manage data. This allows coupon usage information and inventory information to be updated in real time. The input is the received text data, and the output is the updated sales data and inventory data.

[0148] This processing step enables paper-based information in physical stores to be efficiently digitized and instantly linked to related systems.

[0149] 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.

[0150] System configuration and processing overview

[0151] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them into multiple systems as text data. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as the "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple systems. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0152] User operations

[0153] Users use their device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0154] Terminal handling

[0155] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the image data and determines the user's emotions.

[0156] Server Processing

[0157] The server receives the image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0158] The converted text data is adjusted based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff.

[0159] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0160] Specific examples

[0161] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0162] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0163] 2. The device sends the captured image data and the user's facial expression data to the server.

[0164] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0165] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0166] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0167] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0168] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0169] The processing flow will be explained below.

[0170] Step 1:

[0171] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0172] Step 2:

[0173] The user's facial expressions are also captured simultaneously: the application detects the user's face using the front or back camera and saves the facial expressions as image data.

[0174] Step 3:

[0175] The device sends the captured image data and the user's facial expression data to the server. The device then sends the saved image file and facial expression data to the server in the form of an HTTP POST request. At this time, the image data and facial expression data are compressed and, if necessary, encrypted before being sent.

[0176] Step 4:

[0177] The server receives the image data and facial expression data sent from the terminal. The server receives a request at a specific endpoint (e.g., / upload) and obtains the image data and facial expression data.

[0178] Step 5:

[0179] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0180] Step 6:

[0181] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0182] Step 7:

[0183] The server uses an emotion engine to analyze the emotion data. The server passes the facial expression data to the emotion engine to analyze the user's emotion. The emotion engine uses a facial expression analysis algorithm to determine the user's emotion.

[0184] Step 8:

[0185] The server adjusts the text data based on the results of the sentiment analysis. For example, if it determines that the user is feeling stressed, it adds a specific annotation to the text data and notifies the support staff.

[0186] Step 9:

[0187] The server sends the adjusted text data to multiple systems. The server makes HTTP POST requests to the API endpoints of the multiple systems to send the text data.

[0188] Step 10:

[0189] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0190] Step 11:

[0191] The user checks the processing results. Once processing is complete, the user can check the status of the document they sent and the results of the sentiment analysis through the application. They can check whether the text conversion and data storage were successful, and whether any actions were taken based on the sentiment analysis results.

[0192] These are the steps in a series of processes that digitize image data and emotion data and efficiently import them into multiple systems as text data. This system improves operational efficiency and significantly reduces the risk of input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0193] Example 2

[0194] 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."

[0195] Conventional image data to text data conversion systems are successful in extracting textual information from images, but they are unable to provide an optimal user experience because they are unable to consider the user's emotional state. Furthermore, the accuracy of the text data and the adjustment of the transmitted information are insufficient, resulting in input errors and inefficient data processing. To solve these issues, a system that simultaneously achieves high-precision text conversion and an improved user experience is required.

[0196] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring image information and user facial expression information, a means for analyzing the image information and using a generative model to convert it into text data, and a means for analyzing emotions based on the user facial expression information. This enables not only highly accurate text conversion but also appropriate adjustments based on the user's emotions, thereby improving the user experience and enabling efficient data processing.

[0197] "Image information" refers to visual data obtained using an input device such as a camera or scanner.

[0198] "User's facial expression information" refers to data of the user's facial expression captured using a camera or the like of the terminal.

[0199] A "generative model" is an AI model that uses machine learning algorithms to analyze image data and convert it into text data.

[0200] An "information processing device" is a computer system, such as a server or client system, that receives, processes, and stores various types of data.

[0201] "Central Processing Unit" means a central computer system that processes information, including a server.

[0202] An "emotion engine" is an algorithm or model that analyzes a user's facial expression data and recognizes and judges their emotional state.

[0203] "Text data" refers to character information extracted by analyzing image data using a generative model.

[0204] An "HTTP POST request" is a request method for sending data from a client to a server using the Internet protocol HTTP.

[0205] "OCR (Optical Character Recognition) technology" is a technology that reads character information from image data and converts it into text format.

[0206] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them as text data into multiple information processing devices. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple information processing devices. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0207] User operations

[0208] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0209] Terminal handling

[0210] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the facial expression data acquired by the device and determines the user's emotion.

[0211] Server Processing

[0212] The server receives image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0213] The converted text data is adjusted based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff. After the data is converted into text data, the server prepares it to be sent to various information processing devices. The server sequentially calls the API endpoints of multiple information processing devices and sends the generated text data. Each information processing device automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0214] Specific examples

[0215] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0216] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0217] 2. The device sends the captured image data and the user's facial expression data to the server.

[0218] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0219] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0220] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0221] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0222] Example prompt for a generative AI model:

[0223] The image below contains an expense receipt. Please convert this image to text format. At the same time, please analyze the user's facial expressions to determine their emotions and include the results.

[0224] In this way, with the system of the present invention, all a user has to do is take a photo of a document and send it; all processing is done automatically on the server side, realizing efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0226] Step 1:

[0227] The user takes an image of a paper document or application form using the device's camera. The input is the image information acquired through the camera, and the output is an image file stored inside the device. Specifically, the user takes the image by tapping the "take a photo" button in the dedicated application.

[0228] Step 2:

[0229] After taking a picture, the user sends the image data to the server via an application on the device. The input is the captured image file, and the output is the HTTP POST request data sent to the server. Specifically, the user taps the "Send" button in the application.

[0230] Step 3:

[0231] The device sends the captured image data and the user's facial expression data to the server via an HTTP POST request. The input is the image data and facial expression data, and the output is the HTTP request data sent to the server. Specifically, the device automatically analyzes the facial expression data captured by the camera and sends it together with the image data.

[0232] Step 4:

[0233] The server receives the HTTP POST request sent from the device and obtains the image data and facial expression data. The input is the HTTP POST request data, and the output is the storage of the image data and facial expression data within the server. Specifically, the server analyzes the request content and stores the data in an appropriate format.

[0234] Step 5:

[0235] The server uses a generative AI model to convert the received image data into text data. The input is the received image data, and the output is text data. The generative AI model uses a machine learning algorithm to extract text information from the image. Specifically, the server passes the image data to the generative AI model, which then uses OCR technology to convert it into text format.

[0236] Step 6:

[0237] The server uses an emotion engine to analyze emotions from the user's facial expression data. The input is facial expression data, and the output is analyzed emotional state data. Specifically, the server passes the facial expression data to the emotion engine, which then executes an algorithm to determine the user's emotion.

[0238] Step 7:

[0239] The server adjusts the text data generated by the generative AI model based on the analysis results of the emotion engine. The input is text data and emotional state data, and the output is the adjusted text data. Specifically, the server makes appropriate adjustments to the text data based on the analysis results. For example, if the user is feeling stressed, it adds an additional support message.

[0240] Step 8:

[0241] The adjusted text data is sequentially transmitted from the server to the API endpoints of the multiple information processing devices. The input is the adjusted text data, and the output is the data transmitted to each information processing device. Specifically, the server calls the API of each information processing device and transmits the data.

[0242] Step 9:

[0243] Each information processing device automatically processes the received text data, saving it in the required database or using it in a specific application. The input is the transmitted text data, and the output is saving the processed data or using it in an application. Specifically, each information processing device stores the data received via API in its internal system and automatically executes the business process.

[0244] (Application example 2)

[0245] 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."

[0246] In today's world, the digitization of paper documents and application forms requires rapid and accurate conversion. However, with conventional systems, this conversion process takes time and effort, and input errors and inaccuracies in data are particularly problematic. Furthermore, to improve the user experience, systems must be able to understand users' emotions and provide appropriate support, but there are few systems with such capabilities.

[0247] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image information, means for using a generative model to analyze the image information and convert it into text data, emotion recognition means for analyzing a user's emotion, means for adjusting the text data based on the emotion information analyzed by the emotion recognition means, and means for transmitting the text data to multiple systems. This enables users to easily convert paper documents and application forms into digital format and further receive appropriate support according to the user's emotion.

[0248] "Image information" is image data of paper documents or application forms photographed by a user.

[0249] A "generative model" is a model used to convert image information into text data using machine learning algorithms.

[0250] The "emotion recognition means" is a means for analyzing emotions from the user's facial expressions and actions and acquiring the results as data.

[0251] "Text data" is data that includes character information analyzed from image information.

[0252] "Central Processing Unit" refers to the central device or system that analyzes and transforms data and performs emotion recognition.

[0253] "Emotion information" is data obtained as a result of analyzing a user's emotions.

[0254] "Multiple systems" refers to multiple information processing systems that work together to receive and process text data.

[0255] System configuration and processing overview

[0256] This invention is a system that allows users to convert paper documents and application forms into digital formats and further improves the user experience by recognizing the user's emotions. The system acquires images using a smartphone or other mobile device, converts them into text using a generative model via a central processing unit (server), and then transmits the converted text data to multiple systems. It also includes emotion recognition means that analyzes emotions based on the user's facial expressions and operating status.

[0257] User operations

[0258] The user takes an image of a document or application form using the device's camera. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, emotion recognition is performed by the emotion recognition means based on the user's facial expressions and operational status. The user does not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0259] Terminal handling

[0260] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion recognition means incorporates an algorithm that analyzes the image data and determines the user's emotion.

[0261] Server Processing

[0262] The server receives image data and emotion data sent from the device. The received image data is processed by a generative model, and the character information in the image is converted into text data. The generative model uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0263] The converted text data is adjusted based on the user's emotions as recognized by the emotion recognition means. For example, if the user is feeling stressed, a corresponding message can be added to notify the support staff.

[0264] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0265] Specific examples

[0266] For example, when a user scans a receipt for electronic payment, the following process occurs:

[0267] 1. The user takes a photo of the receipt using the smartphone camera. At the same time, the user's facial expression is captured.

[0268] 2. The device sends the captured image data and the user's facial expression data to the server.

[0269] 3. The server passes the received image data to the generative model and converts it into text data. At the same time, the emotion recognition means analyzes the user's emotions.

[0270] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion recognition means. For example, if the user is feeling stressed, a message such as "The user may be feeling anxious about making a payment" is added.

[0271] 5. The adjusted text data is sent to the payment system.

[0272] 6. The payment system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis, enhancing user support.

[0273] Prompt Sentence Examples

[0274] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0275] This allows users to simply take a photo of a document and send it, with all processing performed automatically on the server side, enabling efficient data capture and processing. Furthermore, combining it with emotion recognition means can improve the user experience.

[0276] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0277] Step 1:

[0278] The user uses the device's camera to take a photo of a paper document or application form. When taking the photo, the user's facial expression is also captured. This allows the image data and facial expression data to be input into the device.

[0279] Step 2:

[0280] The device sends the captured image data and the user's facial expression data to the server using an HTTP POST request, and the server receives the data.

[0281] Step 3:

[0282] The server passes the received image data to a generative model, which analyzes the text information in the image and converts it into text data. This generative model uses a machine learning algorithm to perform advanced pattern recognition on the input image data and output the text data.

[0283] Step 4:

[0284] At the same time, the server uses emotion recognition means to analyze the received user facial expression data. The emotion recognition means determines the user's emotions based on the image data and outputs the results as emotional information. Specifically, it identifies whether the user is happy or stressed based on changes in facial expressions and feature points.

[0285] Step 5:

[0286] The server then adjusts the text data appropriately based on the text data converted by the generative model and the emotion information obtained by the emotion recognition means. For example, if the user is feeling stressed, the server may add a message saying, "The user may need additional support."

[0287] Step 6:

[0288] The server then sequentially sends the adjusted text data to the API endpoints of multiple systems. This allows each system to receive the necessary data and automatically process it internally, registering it in each system's database or using it in specific applications.

[0289] Step 7:

[0290] As a concrete example, a payment system can automatically process expense settlements and accounting based on received text data, and can also enhance user support based on emotional information. For example, if a user feels anxious, the system can display an additional support message.

[0291] Prompt Sentence Examples

[0292] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0293] 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.

[0294] 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.

[0295] 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.

[0296] [Second embodiment]

[0297] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0298] 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.

[0299] 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).

[0300] 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.

[0301] 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.

[0302] 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).

[0303] 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.

[0304] 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.

[0305] 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.

[0306] 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.

[0307] 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.

[0308] 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."

[0309] System configuration and processing overview

[0310] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. This system captures images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and then transmits the converted text data to multiple systems.

[0311] User operations

[0312] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0313] Terminal handling

[0314] The device performs operations to send the captured image to the server. Specifically, it sends the image data to the server using an HTTP POST request. At this time, the image data is compressed if necessary and converted into a format suitable for transmission.

[0315] Server Processing

[0316] The server receives the image data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion.

[0317] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0318] Specific examples

[0319] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0320] 1. The user takes a photo of the receipt using the smartphone camera.

[0321] 2. The device sends the captured image data to the server.

[0322] 3. The server passes the received image data to the generation AI and converts it into text data.

[0323] 4. The generated text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0324] 5. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0325] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data capture and processing. This system is expected to significantly reduce operation time and eliminate input errors.

[0326] The processing flow will be explained below.

[0327] Step 1:

[0328] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0329] Step 2:

[0330] The device sends the captured image data to the server. The device then sends the saved image file to the server in the form of an HTTP POST request. At this time, the image data is compressed and, if necessary, encrypted before being sent.

[0331] Step 3:

[0332] The server receives the image data sent from the device. The server receives a request at a specific endpoint (e.g., / upload) and retrieves the image data.

[0333] Step 4:

[0334] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0335] Step 5:

[0336] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0337] Step 6:

[0338] The server sends text data to multiple systems. The server sends an HTTP POST request to the API endpoint of each system to send the text data. The destination systems are expense reimbursement systems, accounting systems, etc.

[0339] Step 7:

[0340] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0341] Step 8:

[0342] The user checks the results. Once the process is complete, the user can check the status of the document they sent through the application. Check whether the text conversion and data saving were successful.

[0343] These are the steps required to digitize image data and efficiently import it into multiple systems as text data, improving operational efficiency and significantly reducing the risk of data entry errors.

[0344] Example 1

[0345] 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."

[0346] Digitizing traditional paper documents and application forms requires manual data entry, which wastes time and effort and introduces the risk of input errors. It is necessary to solve this problem and provide an efficient and accurate way to convert paper documents into digital form.

[0347] 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.

[0348] In this invention, the server includes means for acquiring image information on a terminal, means for transmitting the image information to the server using an HTTP POST request, means for converting the image information into text data using a generative AI model on the server, and means for transmitting the text data to API endpoints of multiple external systems. This allows a user to photograph a document, generate accurate digital data with simple operations, and automatically import it into various systems.

[0349] A "terminal" is a portable information terminal for acquiring images and transmitting data via communication.

[0350] "Image information" refers to digital data obtained by capturing paper documents or application forms using a photographing device such as a camera.

[0351] An "HTTP POST request" is a type of communication protocol for sending data from a client to a server over the Internet.

[0352] A "server" is a computing device that processes the received image information and converts it into text data using a generative AI model.

[0353] A "generative AI model" is an artificial intelligence technology that uses machine learning algorithms to analyze image information and convert character information into text data.

[0354] "Text data" is digital data containing text information extracted from image information by a generative AI model.

[0355] An "API endpoint" refers to an interface configured to communicate with another system, and is an access point for sending and receiving data.

[0356] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. Specifically, the system allows users to acquire image information using their devices, convert it into text using a generative AI model via a server, and then transmit the converted text data to multiple systems.

[0357] User operations

[0358] The user uses the device's camera to take a photo of a paper document or application form. Once the photo is taken, the image is saved on the device. The user then uses a specific application to send the saved image to the server. To do this, the user simply takes the photo and presses the send button as instructed by the application.

[0359] Terminal handling

[0360] The device uses an HTTP POST request to send the captured image information to the server. At this time, the image data is compressed if necessary and converted into a format suitable for transmission (e.g., JPEG or PNG). The device also has the function to compress image information and convert it into a format suitable for transmission.

[0361] Server Processing

[0362] The server receives the image data sent from the device. After receiving the data, the server uses a generative AI model to convert the image information into text data. The generative AI model uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion. An example of a prompt sent to the generative AI model could be, "Please convert the characters in this image into text data." The converted text data is returned to the server.

[0363] After receiving the converted text data, the server sends it to various systems. Specifically, the server sequentially calls the API endpoints of multiple systems and sends the generated text data. Each system automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0364] Specific examples

[0365] For example, when a user scans a receipt for expense reimbursement, the process goes something like this: The user takes a picture of the receipt using the camera on their smartphone and sends the image data to a server via a specific application. The server passes the received image data to a generative AI model and converts it into text data. The generated text data is then sent to multiple internal systems, such as expense reimbursement systems and accounting systems. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0366] With such a system, all a user has to do is take a photo of a document and send it, and all processing is done automatically, which is expected to significantly reduce operation time and eliminate input errors.

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

[0368] Step 1: The user takes a photo of the document on their device

[0369] The user takes a photo of a paper document or application form using the device's camera. The input is the paper document, and the output is digital image data. Once the photo is taken, the image data is saved in the device. Specifically, the user launches the camera app, positions the document within the camera's screen, and presses the shutter button.

[0370] Step 2: The device sends the image to the server

[0371] The device compresses the stored image data and converts it into a format suitable for transmission. The input is the stored image data, and the output is the compressed image data. Specifically, an HTTP POST request is created and a payload containing the image data is sent to the server. The user performs this operation using a specific application. Specifically, the user launches the application, selects an image, and presses the send button.

[0372] Step 3: The server receives the image data.

[0373] The server receives the HTTP POST request sent from the terminal and retrieves the image data. The input is the image data sent from the terminal, and the output is the image data stored on the server. After receiving the data, the server checks the integrity of the data and whether the image is corrupted. Specifically, the server listens for HTTP requests, extracts the image data, and temporarily stores it.

[0374] Step 4: The server uses the generative AI model to convert the image into text data.

[0375] The server inputs the saved image data into the generative AI model and sends it along with the prompt "Please convert the characters in this image into text data." The input is the image data and the prompt, and the output is the generated text data. The generative AI model uses a machine learning algorithm to analyze the image information and extract and convert the text information. Specifically, the server passes the image data to the generative AI model and obtains the analysis results.

[0376] Step 5: The server sends the text data to multiple systems

[0377] After receiving the generated text data, the server sends it sequentially to the API endpoints of various systems. The input is the generated text data, and the output is the text data sent to each system. Specifically, the API endpoints of multiple systems are called and the generated text data is sent. In concrete terms, the server creates an HTTP POST request to each endpoint and sends the data.

[0378] In this way, by adding detailed descriptions of the specific operations performed at each processing step and their inputs and outputs, the overall flow and operation of the system becomes clearer.

[0379] (Application example 1)

[0380] 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."

[0381] There is a need to efficiently digitize paper-based information such as coupons and receipts in physical stores and instantly link it to related systems to ensure fast and accurate data exchange between customers and stores. Another important issue is reducing the workload associated with the manual processing of coupons and receipts and improving the accuracy of data management.

[0382] 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.

[0383] In this invention, the server includes means for acquiring image information, means for analyzing the image information and using a generative model to convert it into text data, means for linking the converted text data to a sales data management system, and means for linking the text data to an inventory management system. This makes it possible to efficiently digitize information on paper media and instantly link it to related systems automatically.

[0384] "Means for acquiring image information" refers to a function for acquiring images of paper coupons and receipts using a photographing device such as a smartphone or camera.

[0385] "Means for using a generative model to analyze image information and convert it into text data" refers to a function for analyzing an acquired image using an AI model, in particular a generative AI model, and converting the text information in the image into digital text.

[0386] The "means for transmitting the converted text data to a plurality of systems" is a function for transmitting the generated text data to a plurality of systems, such as a sales data management system and an inventory management system, via a server.

[0387] The "means for linking the text data to a sales data management system" is a function for instantly linking the text data to a store's sales data management system, making it available as sales-related data.

[0388] The "means for linking the text data to an inventory management system" is a function for transmitting the converted text data to an inventory management system and managing and updating inventory in real time.

[0389] This invention provides a system that converts paper coupons and receipts from physical stores into digital format and instantly connects with related systems.

[0390] Program Generation

[0391] The system for realizing the present invention uses the following hardware and software.

[0392] Smartphone: A device that allows users to take pictures of paper coupons and receipts.

[0393] Server: A device that receives image data and performs analysis and text conversion.

[0394] Generative AI models are used to extract textual information from captured images and convert it into text data. Examples include Google Cloud Vision and AWS Rekognition.

[0395] Sales data management system and inventory management system: A system that receives converted text data and processes the data.

[0396] Processing Description

[0397] Smartphone

[0398] A user uses a smartphone to take a picture of a paper coupon or receipt, and the image data is compressed and sent to the server using an HTTP POST request.

[0399] server

[0400] The server receives the captured image data and passes it to the generative AI model for text conversion. The generative AI model uses a machine learning algorithm to extract text information from the image with high accuracy and convert it into text data. The converted text data is then sent to the sales data management system and inventory management system.

[0401] Sales data management system and inventory management system

[0402] These systems receive text data and update and manage the data in real time. For example, information on coupons used by customers is aggregated in a sales data management system, and inventory information is updated in an inventory management system.

[0403] Specific examples

[0404] For example, when a customer takes a photo of a coupon to be used at a store with their smartphone, the following process takes place.

[0405] 1. The user takes a photo of the coupon using their smartphone camera.

[0406] 2. The smartphone compresses the captured image and sends it to the server.

[0407] 3. The server passes the received image to the generative AI model and converts it into text data.

[0408] 4. The server sends the converted text data to the sales data management system and the inventory management system.

[0409] 5. The system uses the received data to record coupon redemptions and update inventory information.

[0410] Prompt Sentence Examples

[0411] The company will build a system that converts coupons and receipts into digital format and instantly transmits the data to store sales data management systems and inventory management systems. The system will have functions for taking images with a smartphone, converting them into text using a generative AI model, and automatically linking data.

[0412] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0413] Step 1:

[0414] A user takes a photo of a paper coupon or receipt with their smartphone camera. The user opens the camera app, frames the subject, and presses the shutter button. The input is the paper (coupon or receipt), and the output is digital image data.

[0415] Step 2:

[0416] The device compresses the captured image data and sends it to the server using an HTTP POST request. This reduces the size of the image data and improves communication speed. The input is digital image data, and the output is compressed image data (binary data).

[0417] Step 3:

[0418] The server takes the image data received via the HTTP POST request and decompresses it into the appropriate format. The server then decompresses the received binary data into image data. The input is the compressed image data, and the output is the original digital image data.

[0419] Step 4:

[0420] The server passes the extracted image data to a generative AI model, which extracts character information and converts it into text data. The generative AI model uses a machine learning algorithm to analyze the characters in the image. The input is digital image data, and the output is analyzed text data.

[0421] Step 5:

[0422] The server sends the generated text data to the sales data management system and the inventory management system. The server transfers the text data to each system via an API endpoint. The input is the parsed text data, and the output is the text data sent to each system.

[0423] Step 6:

[0424] The sales data management system and inventory management system use the received text data to update and manage data. This allows coupon usage information and inventory information to be updated in real time. The input is the received text data, and the output is the updated sales data and inventory data.

[0425] This processing step enables paper-based information in physical stores to be efficiently digitized and instantly linked to related systems.

[0426] 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.

[0427] System configuration and processing overview

[0428] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them into multiple systems as text data. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as the "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple systems. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0429] User operations

[0430] Users use their device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0431] Terminal handling

[0432] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the image data and determines the user's emotions.

[0433] Server Processing

[0434] The server receives the image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0435] The converted text data is adjusted based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff.

[0436] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0437] Specific examples

[0438] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0439] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0440] 2. The device sends the captured image data and the user's facial expression data to the server.

[0441] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0442] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0443] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0444] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0445] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0449] Step 2:

[0450] The user's facial expressions are also captured simultaneously: the application detects the user's face using the front or back camera and saves the facial expressions as image data.

[0451] Step 3:

[0452] The device sends the captured image data and the user's facial expression data to the server. The device then sends the saved image file and facial expression data to the server in the form of an HTTP POST request. At this time, the image data and facial expression data are compressed and, if necessary, encrypted before being sent.

[0453] Step 4:

[0454] The server receives the image data and facial expression data sent from the terminal. The server receives a request at a specific endpoint (e.g., / upload) and obtains the image data and facial expression data.

[0455] Step 5:

[0456] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0457] Step 6:

[0458] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0459] Step 7:

[0460] The server uses an emotion engine to analyze the emotion data. The server passes the facial expression data to the emotion engine to analyze the user's emotion. The emotion engine uses a facial expression analysis algorithm to determine the user's emotion.

[0461] Step 8:

[0462] The server adjusts the text data based on the results of the sentiment analysis. For example, if it determines that the user is feeling stressed, it adds a specific annotation to the text data and notifies the support staff.

[0463] Step 9:

[0464] The server sends the adjusted text data to multiple systems. The server makes HTTP POST requests to the API endpoints of the multiple systems to send the text data.

[0465] Step 10:

[0466] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0467] Step 11:

[0468] The user checks the processing results. Once processing is complete, the user can check the status of the document they sent and the results of the sentiment analysis through the application. They can check whether the text conversion and data storage were successful, and whether any actions were taken based on the sentiment analysis results.

[0469] These are the steps in a series of processes that digitize image data and emotion data and efficiently import them into multiple systems as text data. This system improves operational efficiency and significantly reduces the risk of input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0470] Example 2

[0471] 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."

[0472] Conventional image data to text data conversion systems are successful in extracting textual information from images, but they are unable to provide an optimal user experience because they are unable to consider the user's emotional state. Furthermore, the accuracy of the text data and the adjustment of the transmitted information are insufficient, resulting in input errors and inefficient data processing. To solve these issues, a system that simultaneously achieves high-precision text conversion and an improved user experience is required.

[0473] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring image information and user facial expression information, a means for analyzing the image information and using a generative model to convert it into text data, and a means for analyzing emotions based on the user facial expression information. This enables not only highly accurate text conversion but also appropriate adjustments based on the user's emotions, thereby improving the user experience and enabling efficient data processing.

[0474] "Image information" refers to visual data obtained using an input device such as a camera or scanner.

[0475] "User's facial expression information" refers to data of the user's facial expression captured using a camera or the like of the terminal.

[0476] A "generative model" is an AI model that uses machine learning algorithms to analyze image data and convert it into text data.

[0477] An "information processing device" is a computer system, such as a server or client system, that receives, processes, and stores various types of data.

[0478] "Central Processing Unit" means a central computer system that processes information, including a server.

[0479] An "emotion engine" is an algorithm or model that analyzes a user's facial expression data and recognizes and judges their emotional state.

[0480] "Text data" refers to character information extracted by analyzing image data using a generative model.

[0481] An "HTTP POST request" is a request method for sending data from a client to a server using the Internet protocol HTTP.

[0482] "OCR (Optical Character Recognition) technology" is a technology that reads character information from image data and converts it into text format.

[0483] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them as text data into multiple information processing devices. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple information processing devices. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0484] User operations

[0485] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0486] Terminal handling

[0487] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the facial expression data acquired by the device and determines the user's emotion.

[0488] Server Processing

[0489] The server receives image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0490] The converted text data is adjusted based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff. After the data is converted into text data, the server prepares it to be sent to various information processing devices. The server sequentially calls the API endpoints of multiple information processing devices and sends the generated text data. Each information processing device automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0491] Specific examples

[0492] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0493] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0494] 2. The device sends the captured image data and the user's facial expression data to the server.

[0495] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0496] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0497] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0498] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0499] Example prompt for a generative AI model:

[0500] The image below contains an expense receipt. Please convert this image to text format. At the same time, please analyze the user's facial expressions to determine their emotions and include the results.

[0501] In this way, with the system of the present invention, all a user has to do is take a photo of a document and send it; all processing is done automatically on the server side, realizing efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0502] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0503] Step 1:

[0504] The user takes an image of a paper document or application form using the device's camera. The input is the image information acquired through the camera, and the output is an image file stored inside the device. Specifically, the user takes the image by tapping the "take a photo" button in the dedicated application.

[0505] Step 2:

[0506] After taking a picture, the user sends the image data to the server via an application on the device. The input is the captured image file, and the output is the HTTP POST request data sent to the server. Specifically, the user taps the "Send" button in the application.

[0507] Step 3:

[0508] The device sends the captured image data and the user's facial expression data to the server via an HTTP POST request. The input is the image data and facial expression data, and the output is the HTTP request data sent to the server. Specifically, the device automatically analyzes the facial expression data captured by the camera and sends it together with the image data.

[0509] Step 4:

[0510] The server receives the HTTP POST request sent from the device and obtains the image data and facial expression data. The input is the HTTP POST request data, and the output is the storage of the image data and facial expression data within the server. Specifically, the server analyzes the request content and stores the data in an appropriate format.

[0511] Step 5:

[0512] The server uses a generative AI model to convert the received image data into text data. The input is the received image data, and the output is text data. The generative AI model uses a machine learning algorithm to extract text information from the image. Specifically, the server passes the image data to the generative AI model, which then uses OCR technology to convert it into text format.

[0513] Step 6:

[0514] The server uses an emotion engine to analyze emotions from the user's facial expression data. The input is facial expression data, and the output is analyzed emotional state data. Specifically, the server passes the facial expression data to the emotion engine, which then executes an algorithm to determine the user's emotion.

[0515] Step 7:

[0516] The server adjusts the text data generated by the generative AI model based on the analysis results of the emotion engine. The input is text data and emotional state data, and the output is the adjusted text data. Specifically, the server makes appropriate adjustments to the text data based on the analysis results. For example, if the user is feeling stressed, it adds an additional support message.

[0517] Step 8:

[0518] The adjusted text data is sequentially transmitted from the server to the API endpoints of the multiple information processing devices. The input is the adjusted text data, and the output is the data transmitted to each information processing device. Specifically, the server calls the API of each information processing device and transmits the data.

[0519] Step 9:

[0520] Each information processing device automatically processes the received text data, saving it in the required database or using it in a specific application. The input is the transmitted text data, and the output is saving the processed data or using it in an application. Specifically, each information processing device stores the data received via API in its internal system and automatically executes the business process.

[0521] (Application example 2)

[0522] 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."

[0523] In today's world, the digitization of paper documents and application forms requires rapid and accurate conversion. However, with conventional systems, this conversion process takes time and effort, and input errors and inaccuracies in data are particularly problematic. Furthermore, to improve the user experience, systems must be able to understand users' emotions and provide appropriate support, but there are few systems with such capabilities.

[0524] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image information, means for using a generative model to analyze the image information and convert it into text data, emotion recognition means for analyzing a user's emotion, means for adjusting the text data based on the emotion information analyzed by the emotion recognition means, and means for transmitting the text data to multiple systems. This enables users to easily convert paper documents and application forms into digital format and further receive appropriate support according to the user's emotion.

[0525] "Image information" is image data of paper documents or application forms photographed by a user.

[0526] A "generative model" is a model used to convert image information into text data using machine learning algorithms.

[0527] The "emotion recognition means" is a means for analyzing emotions from the user's facial expressions and actions and acquiring the results as data.

[0528] "Text data" is data that includes character information analyzed from image information.

[0529] "Central Processing Unit" refers to the central device or system that analyzes and transforms data and performs emotion recognition.

[0530] "Emotion information" is data obtained as a result of analyzing a user's emotions.

[0531] "Multiple systems" refers to multiple information processing systems that work together to receive and process text data.

[0532] System configuration and processing overview

[0533] This invention is a system that allows users to convert paper documents and application forms into digital formats and further improves the user experience by recognizing the user's emotions. The system acquires images using a smartphone or other mobile device, converts them into text using a generative model via a central processing unit (server), and then transmits the converted text data to multiple systems. It also includes emotion recognition means that analyzes emotions based on the user's facial expressions and operating status.

[0534] User operations

[0535] The user takes an image of a document or application form using the device's camera. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, emotion recognition is performed by the emotion recognition means based on the user's facial expressions and operational status. The user does not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0536] Terminal handling

[0537] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion recognition means incorporates an algorithm that analyzes the image data and determines the user's emotion.

[0538] Server Processing

[0539] The server receives image data and emotion data sent from the device. The received image data is processed by a generative model, and the character information in the image is converted into text data. The generative model uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0540] The converted text data is adjusted based on the user's emotions as recognized by the emotion recognition means. For example, if the user is feeling stressed, a corresponding message can be added to notify the support staff.

[0541] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0542] Specific examples

[0543] For example, when a user scans a receipt for electronic payment, the following process occurs:

[0544] 1. The user takes a photo of the receipt using the smartphone camera. At the same time, the user's facial expression is captured.

[0545] 2. The device sends the captured image data and the user's facial expression data to the server.

[0546] 3. The server passes the received image data to the generative model and converts it into text data. At the same time, the emotion recognition means analyzes the user's emotions.

[0547] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion recognition means. For example, if the user is feeling stressed, a message such as "The user may be feeling anxious about making a payment" is added.

[0548] 5. The adjusted text data is sent to the payment system.

[0549] 6. The payment system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis, enhancing user support.

[0550] Prompt Sentence Examples

[0551] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0552] This allows users to simply take a photo of a document and send it, with all processing performed automatically on the server side, enabling efficient data capture and processing. Furthermore, combining it with emotion recognition means can improve the user experience.

[0553] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0554] Step 1:

[0555] The user uses the device's camera to take a photo of a paper document or application form. When taking the photo, the user's facial expression is also captured. This allows the image data and facial expression data to be input into the device.

[0556] Step 2:

[0557] The device sends the captured image data and the user's facial expression data to the server using an HTTP POST request, and the server receives the data.

[0558] Step 3:

[0559] The server passes the received image data to a generative model, which analyzes the text information in the image and converts it into text data. This generative model uses a machine learning algorithm to perform advanced pattern recognition on the input image data and output the text data.

[0560] Step 4:

[0561] At the same time, the server uses emotion recognition means to analyze the received user facial expression data. The emotion recognition means determines the user's emotions based on the image data and outputs the results as emotional information. Specifically, it identifies whether the user is happy or stressed based on changes in facial expressions and feature points.

[0562] Step 5:

[0563] The server then adjusts the text data appropriately based on the text data converted by the generative model and the emotion information obtained by the emotion recognition means. For example, if the user is feeling stressed, the server may add a message saying, "The user may need additional support."

[0564] Step 6:

[0565] The server then sequentially sends the adjusted text data to the API endpoints of multiple systems. This allows each system to receive the necessary data and automatically process it internally, registering it in each system's database or using it in specific applications.

[0566] Step 7:

[0567] As a concrete example, a payment system can automatically process expense settlements and accounting based on received text data, and can also enhance user support based on emotional information. For example, if a user feels anxious, the system can display an additional support message.

[0568] Prompt Sentence Examples

[0569] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0570] 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.

[0571] 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.

[0572] 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.

[0573] [Third embodiment]

[0574] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0575] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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."

[0586] System configuration and processing overview

[0587] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. This system captures images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and then transmits the converted text data to multiple systems.

[0588] User operations

[0589] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0590] Terminal handling

[0591] The device performs operations to send the captured image to the server. Specifically, it sends the image data to the server using an HTTP POST request. At this time, the image data is compressed if necessary and converted into a format suitable for transmission.

[0592] Server Processing

[0593] The server receives the image data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion.

[0594] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0595] Specific examples

[0596] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0597] 1. The user takes a photo of the receipt using the smartphone camera.

[0598] 2. The device sends the captured image data to the server.

[0599] 3. The server passes the received image data to the generation AI and converts it into text data.

[0600] 4. The generated text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0601] 5. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0602] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data capture and processing. This system is expected to significantly reduce operation time and eliminate input errors.

[0603] The processing flow will be explained below.

[0604] Step 1:

[0605] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0606] Step 2:

[0607] The device sends the captured image data to the server. The device then sends the saved image file to the server in the form of an HTTP POST request. At this time, the image data is compressed and, if necessary, encrypted before being sent.

[0608] Step 3:

[0609] The server receives the image data sent from the device. The server receives a request at a specific endpoint (e.g., / upload) and retrieves the image data.

[0610] Step 4:

[0611] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0612] Step 5:

[0613] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0614] Step 6:

[0615] The server sends text data to multiple systems. The server sends an HTTP POST request to the API endpoint of each system to send the text data. The destination systems are expense reimbursement systems, accounting systems, etc.

[0616] Step 7:

[0617] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0618] Step 8:

[0619] The user checks the results. Once the process is complete, the user can check the status of the document they sent through the application. Check whether the text conversion and data saving were successful.

[0620] These are the steps required to digitize image data and efficiently import it into multiple systems as text data, improving operational efficiency and significantly reducing the risk of data entry errors.

[0621] Example 1

[0622] 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."

[0623] Digitizing traditional paper documents and application forms requires manual data entry, which wastes time and effort and introduces the risk of input errors. It is necessary to solve this problem and provide an efficient and accurate way to convert paper documents into digital form.

[0624] 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.

[0625] In this invention, the server includes means for acquiring image information on a terminal, means for transmitting the image information to the server using an HTTP POST request, means for converting the image information into text data using a generative AI model on the server, and means for transmitting the text data to API endpoints of multiple external systems. This allows a user to photograph a document, generate accurate digital data with simple operations, and automatically import it into various systems.

[0626] A "terminal" is a portable information terminal for acquiring images and transmitting data via communication.

[0627] "Image information" refers to digital data obtained by capturing paper documents or application forms using a photographing device such as a camera.

[0628] An "HTTP POST request" is a type of communication protocol for sending data from a client to a server over the Internet.

[0629] A "server" is a computing device that processes the received image information and converts it into text data using a generative AI model.

[0630] A "generative AI model" is an artificial intelligence technology that uses machine learning algorithms to analyze image information and convert character information into text data.

[0631] "Text data" is digital data containing text information extracted from image information by a generative AI model.

[0632] An "API endpoint" refers to an interface configured to communicate with another system, and is an access point for sending and receiving data.

[0633] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. Specifically, the system allows users to acquire image information using their devices, convert it into text using a generative AI model via a server, and then transmit the converted text data to multiple systems.

[0634] User operations

[0635] The user uses the device's camera to take a photo of a paper document or application form. Once the photo is taken, the image is saved on the device. The user then uses a specific application to send the saved image to the server. To do this, the user simply takes the photo and presses the send button as instructed by the application.

[0636] Terminal handling

[0637] The device uses an HTTP POST request to send the captured image information to the server. At this time, the image data is compressed if necessary and converted into a format suitable for transmission (e.g., JPEG or PNG). The device also has the function to compress image information and convert it into a format suitable for transmission.

[0638] Server Processing

[0639] The server receives the image data sent from the device. After receiving the data, the server uses a generative AI model to convert the image information into text data. The generative AI model uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion. An example of a prompt sent to the generative AI model could be, "Please convert the characters in this image into text data." The converted text data is returned to the server.

[0640] After receiving the converted text data, the server sends it to various systems. Specifically, the server sequentially calls the API endpoints of multiple systems and sends the generated text data. Each system automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0641] Specific examples

[0642] For example, when a user scans a receipt for expense reimbursement, the process goes something like this: The user takes a picture of the receipt using the camera on their smartphone and sends the image data to a server via a specific application. The server passes the received image data to a generative AI model and converts it into text data. The generated text data is then sent to multiple internal systems, such as expense reimbursement systems and accounting systems. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0643] With such a system, all a user has to do is take a photo of a document and send it, and all processing is done automatically, which is expected to significantly reduce operation time and eliminate input errors.

[0644] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0645] Step 1: The user takes a photo of the document on their device

[0646] The user takes a photo of a paper document or application form using the device's camera. The input is the paper document, and the output is digital image data. Once the photo is taken, the image data is saved in the device. Specifically, the user launches the camera app, positions the document within the camera's screen, and presses the shutter button.

[0647] Step 2: The device sends the image to the server

[0648] The device compresses the stored image data and converts it into a format suitable for transmission. The input is the stored image data, and the output is the compressed image data. Specifically, an HTTP POST request is created and a payload containing the image data is sent to the server. The user performs this operation using a specific application. Specifically, the user launches the application, selects an image, and presses the send button.

[0649] Step 3: The server receives the image data.

[0650] The server receives the HTTP POST request sent from the terminal and retrieves the image data. The input is the image data sent from the terminal, and the output is the image data stored on the server. After receiving the data, the server checks the integrity of the data and whether the image is corrupted. Specifically, the server listens for HTTP requests, extracts the image data, and temporarily stores it.

[0651] Step 4: The server uses the generative AI model to convert the image into text data.

[0652] The server inputs the saved image data into the generative AI model and sends it along with the prompt "Please convert the characters in this image into text data." The input is the image data and the prompt, and the output is the generated text data. The generative AI model uses a machine learning algorithm to analyze the image information and extract and convert the text information. Specifically, the server passes the image data to the generative AI model and obtains the analysis results.

[0653] Step 5: The server sends the text data to multiple systems

[0654] After receiving the generated text data, the server sends it sequentially to the API endpoints of various systems. The input is the generated text data, and the output is the text data sent to each system. Specifically, the API endpoints of multiple systems are called and the generated text data is sent. In concrete terms, the server creates an HTTP POST request to each endpoint and sends the data.

[0655] In this way, by adding detailed descriptions of the specific operations performed at each processing step and their inputs and outputs, the overall flow and operation of the system becomes clearer.

[0656] (Application example 1)

[0657] 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."

[0658] There is a need to efficiently digitize paper-based information such as coupons and receipts in physical stores and instantly link it to related systems to ensure fast and accurate data exchange between customers and stores. Another important issue is reducing the workload associated with the manual processing of coupons and receipts and improving the accuracy of data management.

[0659] 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.

[0660] In this invention, the server includes means for acquiring image information, means for analyzing the image information and using a generative model to convert it into text data, means for linking the converted text data to a sales data management system, and means for linking the text data to an inventory management system. This makes it possible to efficiently digitize information on paper media and instantly link it to related systems automatically.

[0661] "Means for acquiring image information" refers to a function for acquiring images of paper coupons and receipts using a photographing device such as a smartphone or camera.

[0662] "Means for using a generative model to analyze image information and convert it into text data" refers to a function for analyzing an acquired image using an AI model, in particular a generative AI model, and converting the text information in the image into digital text.

[0663] The "means for transmitting the converted text data to a plurality of systems" is a function for transmitting the generated text data to a plurality of systems, such as a sales data management system and an inventory management system, via a server.

[0664] The "means for linking the text data to a sales data management system" is a function for instantly linking the text data to a store's sales data management system, making it available as sales-related data.

[0665] The "means for linking the text data to an inventory management system" is a function for transmitting the converted text data to an inventory management system and managing and updating inventory in real time.

[0666] This invention provides a system that converts paper coupons and receipts from physical stores into digital format and instantly connects with related systems.

[0667] Program Generation

[0668] The system for realizing the present invention uses the following hardware and software.

[0669] Smartphone: A device that allows users to take pictures of paper coupons and receipts.

[0670] Server: A device that receives image data and performs analysis and text conversion.

[0671] Generative AI models are used to extract textual information from captured images and convert it into text data. Examples include Google Cloud Vision and AWS Rekognition.

[0672] Sales data management system and inventory management system: A system that receives converted text data and processes the data.

[0673] Processing Description

[0674] Smartphone

[0675] A user uses a smartphone to take a picture of a paper coupon or receipt, and the image data is compressed and sent to the server using an HTTP POST request.

[0676] server

[0677] The server receives the captured image data and passes it to the generative AI model for text conversion. The generative AI model uses a machine learning algorithm to extract text information from the image with high accuracy and convert it into text data. The converted text data is then sent to the sales data management system and inventory management system.

[0678] Sales data management system and inventory management system

[0679] These systems receive text data and update and manage the data in real time. For example, information on coupons used by customers is aggregated in a sales data management system, and inventory information is updated in an inventory management system.

[0680] Specific examples

[0681] For example, when a customer takes a photo of a coupon to be used at a store with their smartphone, the following process takes place.

[0682] 1. The user takes a photo of the coupon using their smartphone camera.

[0683] 2. The smartphone compresses the captured image and sends it to the server.

[0684] 3. The server passes the received image to the generative AI model and converts it into text data.

[0685] 4. The server sends the converted text data to the sales data management system and the inventory management system.

[0686] 5. The system uses the received data to record coupon redemptions and update inventory information.

[0687] Prompt Sentence Examples

[0688] The company will build a system that converts coupons and receipts into digital format and instantly transmits the data to store sales data management systems and inventory management systems. The system will have functions for taking images with a smartphone, converting them into text using a generative AI model, and automatically linking data.

[0689] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0690] Step 1:

[0691] A user takes a photo of a paper coupon or receipt with their smartphone camera. The user opens the camera app, frames the subject, and presses the shutter button. The input is the paper (coupon or receipt), and the output is digital image data.

[0692] Step 2:

[0693] The device compresses the captured image data and sends it to the server using an HTTP POST request. This reduces the size of the image data and improves communication speed. The input is digital image data, and the output is compressed image data (binary data).

[0694] Step 3:

[0695] The server takes the image data received via the HTTP POST request and decompresses it into the appropriate format. The server then decompresses the received binary data into image data. The input is the compressed image data, and the output is the original digital image data.

[0696] Step 4:

[0697] The server passes the extracted image data to a generative AI model, which extracts character information and converts it into text data. The generative AI model uses a machine learning algorithm to analyze the characters in the image. The input is digital image data, and the output is analyzed text data.

[0698] Step 5:

[0699] The server sends the generated text data to the sales data management system and the inventory management system. The server transfers the text data to each system via an API endpoint. The input is the parsed text data, and the output is the text data sent to each system.

[0700] Step 6:

[0701] The sales data management system and inventory management system use the received text data to update and manage data. This allows coupon usage information and inventory information to be updated in real time. The input is the received text data, and the output is the updated sales data and inventory data.

[0702] This processing step enables paper-based information in physical stores to be efficiently digitized and instantly linked to related systems.

[0703] 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.

[0704] System configuration and processing overview

[0705] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them into multiple systems as text data. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as the "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple systems. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0706] User operations

[0707] Users use their device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0708] Terminal handling

[0709] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the image data and determines the user's emotions.

[0710] Server Processing

[0711] The server receives the image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0712] The converted text data is adjusted based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff.

[0713] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0714] Specific examples

[0715] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0716] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0717] 2. The device sends the captured image data and the user's facial expression data to the server.

[0718] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0719] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0720] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0721] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0722] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0723] The processing flow will be explained below.

[0724] Step 1:

[0725] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0726] Step 2:

[0727] The user's facial expressions are also captured simultaneously: the application detects the user's face using the front or back camera and saves the facial expressions as image data.

[0728] Step 3:

[0729] The device sends the captured image data and the user's facial expression data to the server. The device then sends the saved image file and facial expression data to the server in the form of an HTTP POST request. At this time, the image data and facial expression data are compressed and, if necessary, encrypted before being sent.

[0730] Step 4:

[0731] The server receives the image data and facial expression data sent from the terminal. The server receives a request at a specific endpoint (e.g., / upload) and obtains the image data and facial expression data.

[0732] Step 5:

[0733] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0734] Step 6:

[0735] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0736] Step 7:

[0737] The server uses an emotion engine to analyze the emotion data. The server passes the facial expression data to the emotion engine to analyze the user's emotion. The emotion engine uses a facial expression analysis algorithm to determine the user's emotion.

[0738] Step 8:

[0739] The server adjusts the text data based on the results of the sentiment analysis. For example, if it determines that the user is feeling stressed, it adds a specific annotation to the text data and notifies the support staff.

[0740] Step 9:

[0741] The server sends the adjusted text data to multiple systems. The server makes HTTP POST requests to the API endpoints of the multiple systems to send the text data.

[0742] Step 10:

[0743] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0744] Step 11:

[0745] The user checks the processing results. Once processing is complete, the user can check the status of the document they sent and the results of the sentiment analysis through the application. They can check whether the text conversion and data storage were successful, and whether any actions were taken based on the sentiment analysis results.

[0746] These are the steps in a series of processes that digitize image data and emotion data and efficiently import them into multiple systems as text data. This system improves operational efficiency and significantly reduces the risk of input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0747] Example 2

[0748] 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."

[0749] Conventional image data to text data conversion systems are successful in extracting textual information from images, but they are unable to provide an optimal user experience because they are unable to consider the user's emotional state. Furthermore, the accuracy of the text data and the adjustment of the transmitted information are insufficient, resulting in input errors and inefficient data processing. To solve these issues, a system that simultaneously achieves high-precision text conversion and an improved user experience is required.

[0750] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring image information and user facial expression information, a means for analyzing the image information and using a generative model to convert it into text data, and a means for analyzing emotions based on the user facial expression information. This enables not only highly accurate text conversion but also appropriate adjustments based on the user's emotions, thereby improving the user experience and enabling efficient data processing.

[0751] "Image information" refers to visual data obtained using an input device such as a camera or scanner.

[0752] "User's facial expression information" refers to data of the user's facial expression captured using a camera or the like of the terminal.

[0753] A "generative model" is an AI model that uses machine learning algorithms to analyze image data and convert it into text data.

[0754] An "information processing device" is a computer system, such as a server or client system, that receives, processes, and stores various types of data.

[0755] "Central Processing Unit" means a central computer system that processes information, including a server.

[0756] An "emotion engine" is an algorithm or model that analyzes a user's facial expression data and recognizes and judges their emotional state.

[0757] "Text data" refers to character information extracted by analyzing image data using a generative model.

[0758] An "HTTP POST request" is a request method for sending data from a client to a server using the Internet protocol HTTP.

[0759] "OCR (Optical Character Recognition) technology" is a technology that reads character information from image data and converts it into text format.

[0760] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them as text data into multiple information processing devices. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple information processing devices. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0761] User operations

[0762] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0763] Terminal handling

[0764] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the facial expression data acquired by the device and determines the user's emotion.

[0765] Server Processing

[0766] The server receives image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0767] The converted text data is adjusted based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff. After the data is converted into text data, the server prepares it to be sent to various information processing devices. The server sequentially calls the API endpoints of multiple information processing devices and sends the generated text data. Each information processing device automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0768] Specific examples

[0769] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0770] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0771] 2. The device sends the captured image data and the user's facial expression data to the server.

[0772] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0773] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0774] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0775] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[0776] Example prompt for a generative AI model:

[0777] The image below contains an expense receipt. Please convert this image to text format. At the same time, please analyze the user's facial expressions to determine their emotions and include the results.

[0778] In this way, with the system of the present invention, all a user has to do is take a photo of a document and send it; all processing is done automatically on the server side, realizing efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[0779] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0780] Step 1:

[0781] The user takes an image of a paper document or application form using the device's camera. The input is the image information acquired through the camera, and the output is an image file stored inside the device. Specifically, the user takes the image by tapping the "take a photo" button in the dedicated application.

[0782] Step 2:

[0783] After taking a picture, the user sends the image data to the server via an application on the device. The input is the captured image file, and the output is the HTTP POST request data sent to the server. Specifically, the user taps the "Send" button in the application.

[0784] Step 3:

[0785] The device sends the captured image data and the user's facial expression data to the server via an HTTP POST request. The input is the image data and facial expression data, and the output is the HTTP request data sent to the server. Specifically, the device automatically analyzes the facial expression data captured by the camera and sends it together with the image data.

[0786] Step 4:

[0787] The server receives the HTTP POST request sent from the device and obtains the image data and facial expression data. The input is the HTTP POST request data, and the output is the storage of the image data and facial expression data within the server. Specifically, the server analyzes the request content and stores the data in an appropriate format.

[0788] Step 5:

[0789] The server uses a generative AI model to convert the received image data into text data. The input is the received image data, and the output is text data. The generative AI model uses a machine learning algorithm to extract text information from the image. Specifically, the server passes the image data to the generative AI model, which then uses OCR technology to convert it into text format.

[0790] Step 6:

[0791] The server uses an emotion engine to analyze emotions from the user's facial expression data. The input is facial expression data, and the output is analyzed emotional state data. Specifically, the server passes the facial expression data to the emotion engine, which then executes an algorithm to determine the user's emotion.

[0792] Step 7:

[0793] The server adjusts the text data generated by the generative AI model based on the analysis results of the emotion engine. The input is text data and emotional state data, and the output is the adjusted text data. Specifically, the server makes appropriate adjustments to the text data based on the analysis results. For example, if the user is feeling stressed, it adds an additional support message.

[0794] Step 8:

[0795] The adjusted text data is sequentially transmitted from the server to the API endpoints of the multiple information processing devices. The input is the adjusted text data, and the output is the data transmitted to each information processing device. Specifically, the server calls the API of each information processing device and transmits the data.

[0796] Step 9:

[0797] Each information processing device automatically processes the received text data, saving it in the required database or using it in a specific application. The input is the transmitted text data, and the output is saving the processed data or using it in an application. Specifically, each information processing device stores the data received via API in its internal system and automatically executes the business process.

[0798] (Application example 2)

[0799] 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."

[0800] In today's world, the digitization of paper documents and application forms requires rapid and accurate conversion. However, with conventional systems, this conversion process takes time and effort, and input errors and inaccuracies in data are particularly problematic. Furthermore, to improve the user experience, systems must be able to understand users' emotions and provide appropriate support, but there are few systems with such capabilities.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image information, means for using a generative model to analyze the image information and convert it into text data, emotion recognition means for analyzing a user's emotion, means for adjusting the text data based on the emotion information analyzed by the emotion recognition means, and means for transmitting the text data to multiple systems. This enables users to easily convert paper documents and application forms into digital format and further receive appropriate support according to the user's emotion.

[0802] "Image information" is image data of paper documents or application forms photographed by a user.

[0803] A "generative model" is a model used to convert image information into text data using machine learning algorithms.

[0804] The "emotion recognition means" is a means for analyzing emotions from the user's facial expressions and actions and acquiring the results as data.

[0805] "Text data" is data that includes character information analyzed from image information.

[0806] "Central Processing Unit" refers to the central device or system that analyzes and transforms data and performs emotion recognition.

[0807] "Emotion information" is data obtained as a result of analyzing a user's emotions.

[0808] "Multiple systems" refers to multiple information processing systems that work together to receive and process text data.

[0809] System configuration and processing overview

[0810] This invention is a system that allows users to convert paper documents and application forms into digital formats and further improves the user experience by recognizing the user's emotions. The system acquires images using a smartphone or other mobile device, converts them into text using a generative model via a central processing unit (server), and then transmits the converted text data to multiple systems. It also includes emotion recognition means that analyzes emotions based on the user's facial expressions and operating status.

[0811] User operations

[0812] The user takes an image of a document or application form using the device's camera. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, emotion recognition is performed by the emotion recognition means based on the user's facial expressions and operational status. The user does not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0813] Terminal handling

[0814] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion recognition means incorporates an algorithm that analyzes the image data and determines the user's emotion.

[0815] Server Processing

[0816] The server receives image data and emotion data sent from the device. The received image data is processed by a generative model, and the character information in the image is converted into text data. The generative model uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0817] The converted text data is adjusted based on the user's emotions as recognized by the emotion recognition means. For example, if the user is feeling stressed, a corresponding message can be added to notify the support staff.

[0818] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0819] Specific examples

[0820] For example, when a user scans a receipt for electronic payment, the following process occurs:

[0821] 1. The user takes a photo of the receipt using the smartphone camera. At the same time, the user's facial expression is captured.

[0822] 2. The device sends the captured image data and the user's facial expression data to the server.

[0823] 3. The server passes the received image data to the generative model and converts it into text data. At the same time, the emotion recognition means analyzes the user's emotions.

[0824] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion recognition means. For example, if the user is feeling stressed, a message such as "The user may be feeling anxious about making a payment" is added.

[0825] 5. The adjusted text data is sent to the payment system.

[0826] 6. The payment system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis, enhancing user support.

[0827] Prompt Sentence Examples

[0828] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0829] This allows users to simply take a photo of a document and send it, with all processing performed automatically on the server side, enabling efficient data capture and processing. Furthermore, combining it with emotion recognition means can improve the user experience.

[0830] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0831] Step 1:

[0832] The user uses the device's camera to take a photo of a paper document or application form. When taking the photo, the user's facial expression is also captured. This allows the image data and facial expression data to be input into the device.

[0833] Step 2:

[0834] The device sends the captured image data and the user's facial expression data to the server using an HTTP POST request, and the server receives the data.

[0835] Step 3:

[0836] The server passes the received image data to a generative model, which analyzes the text information in the image and converts it into text data. This generative model uses a machine learning algorithm to perform advanced pattern recognition on the input image data and output the text data.

[0837] Step 4:

[0838] At the same time, the server uses emotion recognition means to analyze the received user facial expression data. The emotion recognition means determines the user's emotions based on the image data and outputs the results as emotional information. Specifically, it identifies whether the user is happy or stressed based on changes in facial expressions and feature points.

[0839] Step 5:

[0840] The server then adjusts the text data appropriately based on the text data converted by the generative model and the emotion information obtained by the emotion recognition means. For example, if the user is feeling stressed, the server may add a message saying, "The user may need additional support."

[0841] Step 6:

[0842] The server then sequentially sends the adjusted text data to the API endpoints of multiple systems. This allows each system to receive the necessary data and automatically process it internally, registering it in each system's database or using it in specific applications.

[0843] Step 7:

[0844] As a concrete example, a payment system can automatically process expense settlements and accounting based on received text data, and can also enhance user support based on emotional information. For example, if a user feels anxious, the system can display an additional support message.

[0845] Prompt Sentence Examples

[0846] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Fourth embodiment]

[0851] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0852] 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.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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."

[0864] System configuration and processing overview

[0865] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. This system captures images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and then transmits the converted text data to multiple systems.

[0866] User operations

[0867] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0868] Terminal handling

[0869] The device performs operations to send the captured image to the server. Specifically, it sends the image data to the server using an HTTP POST request. At this time, the image data is compressed if necessary and converted into a format suitable for transmission.

[0870] Server Processing

[0871] The server receives the image data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion.

[0872] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0873] Specific examples

[0874] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0875] 1. The user takes a photo of the receipt using the smartphone camera.

[0876] 2. The device sends the captured image data to the server.

[0877] 3. The server passes the received image data to the generation AI and converts it into text data.

[0878] 4. The generated text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0879] 5. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0880] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data capture and processing. This system is expected to significantly reduce operation time and eliminate input errors.

[0881] The processing flow will be explained below.

[0882] Step 1:

[0883] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[0884] Step 2:

[0885] The device sends the captured image data to the server. The device then sends the saved image file to the server in the form of an HTTP POST request. At this time, the image data is compressed and, if necessary, encrypted before being sent.

[0886] Step 3:

[0887] The server receives the image data sent from the device. The server receives a request at a specific endpoint (e.g., / upload) and retrieves the image data.

[0888] Step 4:

[0889] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[0890] Step 5:

[0891] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[0892] Step 6:

[0893] The server sends text data to multiple systems. The server sends an HTTP POST request to the API endpoint of each system to send the text data. The destination systems are expense reimbursement systems, accounting systems, etc.

[0894] Step 7:

[0895] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[0896] Step 8:

[0897] The user checks the results. Once the process is complete, the user can check the status of the document they sent through the application. Check whether the text conversion and data saving were successful.

[0898] These are the steps required to digitize image data and efficiently import it into multiple systems as text data, improving operational efficiency and significantly reducing the risk of data entry errors.

[0899] Example 1

[0900] 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."

[0901] Digitizing traditional paper documents and application forms requires manual data entry, which wastes time and effort and introduces the risk of input errors. It is necessary to solve this problem and provide an efficient and accurate way to convert paper documents into digital form.

[0902] 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.

[0903] In this invention, the server includes means for acquiring image information on a terminal, means for transmitting the image information to the server using an HTTP POST request, means for converting the image information into text data using a generative AI model on the server, and means for transmitting the text data to API endpoints of multiple external systems. This allows a user to photograph a document, generate accurate digital data with simple operations, and automatically import it into various systems.

[0904] A "terminal" is a portable information terminal for acquiring images and transmitting data via communication.

[0905] "Image information" refers to digital data obtained by capturing paper documents or application forms using a photographing device such as a camera.

[0906] An "HTTP POST request" is a type of communication protocol for sending data from a client to a server over the Internet.

[0907] A "server" is a computing device that processes the received image information and converts it into text data using a generative AI model.

[0908] A "generative AI model" is an artificial intelligence technology that uses machine learning algorithms to analyze image information and convert character information into text data.

[0909] "Text data" is digital data containing text information extracted from image information by a generative AI model.

[0910] An "API endpoint" refers to an interface configured to communicate with another system, and is an access point for sending and receiving data.

[0911] This invention is a system that converts paper documents and application forms into digital format and imports them into multiple systems as text data. Specifically, the system allows users to acquire image information using their devices, convert it into text using a generative AI model via a server, and then transmit the converted text data to multiple systems.

[0912] User operations

[0913] The user uses the device's camera to take a photo of a paper document or application form. Once the photo is taken, the image is saved on the device. The user then uses a specific application to send the saved image to the server. To do this, the user simply takes the photo and presses the send button as instructed by the application.

[0914] Terminal handling

[0915] The device uses an HTTP POST request to send the captured image information to the server. At this time, the image data is compressed if necessary and converted into a format suitable for transmission (e.g., JPEG or PNG). The device also has the function to compress image information and convert it into a format suitable for transmission.

[0916] Server Processing

[0917] The server receives the image data sent from the device. After receiving the data, the server uses a generative AI model to convert the image information into text data. The generative AI model uses a machine learning algorithm to analyze the image information and perform highly accurate text conversion. An example of a prompt sent to the generative AI model could be, "Please convert the characters in this image into text data." The converted text data is returned to the server.

[0918] After receiving the converted text data, the server sends it to various systems. Specifically, the server sequentially calls the API endpoints of multiple systems and sends the generated text data. Each system automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[0919] Specific examples

[0920] For example, when a user scans a receipt for expense reimbursement, the process goes something like this: The user takes a picture of the receipt using the camera on their smartphone and sends the image data to a server via a specific application. The server passes the received image data to a generative AI model and converts it into text data. The generated text data is then sent to multiple internal systems, such as expense reimbursement systems and accounting systems. Each system automatically processes the received text data and stores it in the necessary documents or databases.

[0921] With such a system, all a user has to do is take a photo of a document and send it, and all processing is done automatically, which is expected to significantly reduce operation time and eliminate input errors.

[0922] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0923] Step 1: The user takes a photo of the document on their device

[0924] The user takes a photo of a paper document or application form using the device's camera. The input is the paper document, and the output is digital image data. Once the photo is taken, the image data is saved in the device. Specifically, the user launches the camera app, positions the document within the camera's screen, and presses the shutter button.

[0925] Step 2: The device sends the image to the server

[0926] The device compresses the stored image data and converts it into a format suitable for transmission. The input is the stored image data, and the output is the compressed image data. Specifically, an HTTP POST request is created and a payload containing the image data is sent to the server. The user performs this operation using a specific application. Specifically, the user launches the application, selects an image, and presses the send button.

[0927] Step 3: The server receives the image data.

[0928] The server receives the HTTP POST request sent from the terminal and retrieves the image data. The input is the image data sent from the terminal, and the output is the image data stored on the server. After receiving the data, the server checks the integrity of the data and whether the image is corrupted. Specifically, the server listens for HTTP requests, extracts the image data, and temporarily stores it.

[0929] Step 4: The server uses the generative AI model to convert the image into text data.

[0930] The server inputs the saved image data into the generative AI model and sends it along with the prompt "Please convert the characters in this image into text data." The input is the image data and the prompt, and the output is the generated text data. The generative AI model uses a machine learning algorithm to analyze the image information and extract and convert the text information. Specifically, the server passes the image data to the generative AI model and obtains the analysis results.

[0931] Step 5: The server sends the text data to multiple systems

[0932] After receiving the generated text data, the server sends it sequentially to the API endpoints of various systems. The input is the generated text data, and the output is the text data sent to each system. Specifically, the API endpoints of multiple systems are called and the generated text data is sent. In concrete terms, the server creates an HTTP POST request to each endpoint and sends the data.

[0933] In this way, by adding detailed descriptions of the specific operations performed at each processing step and their inputs and outputs, the overall flow and operation of the system becomes clearer.

[0934] (Application example 1)

[0935] 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."

[0936] There is a need to efficiently digitize paper-based information such as coupons and receipts in physical stores and instantly link it to related systems to ensure fast and accurate data exchange between customers and stores. Another important issue is reducing the workload associated with the manual processing of coupons and receipts and improving the accuracy of data management.

[0937] 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.

[0938] In this invention, the server includes means for acquiring image information, means for analyzing the image information and using a generative model to convert it into text data, means for linking the converted text data to a sales data management system, and means for linking the text data to an inventory management system. This makes it possible to efficiently digitize information on paper media and instantly link it to related systems automatically.

[0939] "Means for acquiring image information" refers to a function for acquiring images of paper coupons and receipts using a photographing device such as a smartphone or camera.

[0940] "Means for using a generative model to analyze image information and convert it into text data" refers to a function for analyzing an acquired image using an AI model, in particular a generative AI model, and converting the text information in the image into digital text.

[0941] The "means for transmitting the converted text data to a plurality of systems" is a function for transmitting the generated text data to a plurality of systems, such as a sales data management system and an inventory management system, via a server.

[0942] The "means for linking the text data to a sales data management system" is a function for instantly linking the text data to a store's sales data management system, making it available as sales-related data.

[0943] The "means for linking the text data to an inventory management system" is a function for transmitting the converted text data to an inventory management system and managing and updating inventory in real time.

[0944] This invention provides a system that converts paper coupons and receipts from physical stores into digital format and instantly connects with related systems.

[0945] Generating a Program

[0946] The system for realizing the present invention uses the following hardware and software.

[0947] Smartphone: A device that allows users to take pictures of paper coupons and receipts.

[0948] Server: A device that receives image data and performs analysis and text conversion.

[0949] Generative AI models are used to extract textual information from captured images and convert it into text data. Examples include Google Cloud Vision and AWS Rekognition.

[0950] Sales data management system and inventory management system: A system that receives converted text data and processes the data.

[0951] Processing Description

[0952] Smartphone

[0953] A user uses a smartphone to take a picture of a paper coupon or receipt, and the image data is compressed and sent to the server using an HTTP POST request.

[0954] server

[0955] The server receives the captured image data and passes it to the generative AI model for text conversion. The generative AI model uses a machine learning algorithm to extract text information from the image with high accuracy and convert it into text data. The converted text data is then sent to the sales data management system and inventory management system.

[0956] Sales data management system and inventory management system

[0957] These systems receive text data and update and manage the data in real time. For example, information on coupons used by customers is aggregated in a sales data management system, and inventory information is updated in an inventory management system.

[0958] Specific examples

[0959] For example, when a customer takes a photo of a coupon to be used at a store with their smartphone, the following process takes place.

[0960] 1. The user takes a photo of the coupon using their smartphone camera.

[0961] 2. The smartphone compresses the captured image and sends it to the server.

[0962] 3. The server passes the received image to the generative AI model and converts it into text data.

[0963] 4. The server sends the converted text data to the sales data management system and the inventory management system.

[0964] 5. The system uses the received data to record the coupon redemption and update inventory information.

[0965] Prompt Sentence Examples

[0966] The company will build a system that converts coupons and receipts into digital format and instantly transmits the data to store sales data management systems and inventory management systems. The system will have functions for taking images with a smartphone, converting them into text using a generative AI model, and automatically linking data.

[0967] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0968] Step 1:

[0969] A user takes a photo of a paper coupon or receipt with their smartphone camera. The user opens the camera app, frames the subject, and presses the shutter button. The input is the paper (coupon or receipt), and the output is digital image data.

[0970] Step 2:

[0971] The device compresses the captured image data and sends it to the server using an HTTP POST request. This reduces the size of the image data and improves communication speed. The input is digital image data, and the output is compressed image data (binary data).

[0972] Step 3:

[0973] The server takes the image data received via the HTTP POST request and decompresses it into the appropriate format. The server then decompresses the received binary data into image data. The input is the compressed image data, and the output is the original digital image data.

[0974] Step 4:

[0975] The server passes the extracted image data to a generative AI model, which extracts character information and converts it into text data. The generative AI model uses a machine learning algorithm to analyze the characters in the image. The input is digital image data, and the output is analyzed text data.

[0976] Step 5:

[0977] The server sends the generated text data to the sales data management system and the inventory management system. The server transfers the text data to each system via an API endpoint. The input is the parsed text data, and the output is the text data sent to each system.

[0978] Step 6:

[0979] The sales data management system and inventory management system use the received text data to update and manage data. This allows coupon usage information and inventory information to be updated in real time. The input is the received text data, and the output is the updated sales data and inventory data.

[0980] This processing step enables paper-based information in physical stores to be efficiently digitized and instantly linked to related systems.

[0981] 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.

[0982] System configuration and processing overview

[0983] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them into multiple systems as text data. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as the "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple systems. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[0984] User operations

[0985] Users use their device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[0986] Terminal handling

[0987] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the image data and determines the user's emotions.

[0988] Server Processing

[0989] The server receives the image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[0990] The converted text data is adjusted based on the user's emotions as recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff.

[0991] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[0992] Specific examples

[0993] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[0994] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[0995] 2. The device sends the captured image data and the user's facial expression data to the server.

[0996] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[0997] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[0998] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[0999] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[1000] In this way, all a user has to do is take a photo of a document and send it, and all processing is done automatically on the server side, achieving efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[1001] The processing flow will be explained below.

[1002] Step 1:

[1003] The user takes a photo of a document or application form with their smartphone camera. They then launch a dedicated application and tap the capture button to capture the image of the document. The application then saves the image at the appropriate resolution.

[1004] Step 2:

[1005] The user's facial expressions are also captured simultaneously: the application detects the user's face using the front or back camera and saves the facial expressions as image data.

[1006] Step 3:

[1007] The device sends the captured image data and the user's facial expression data to the server. The device then sends the saved image file and facial expression data to the server in the form of an HTTP POST request. At this time, the image data and facial expression data are compressed and, if necessary, encrypted before being sent.

[1008] Step 4:

[1009] The server receives the image data and facial expression data sent from the terminal. The server receives a request at a specific endpoint (e.g., / upload) and obtains the image data and facial expression data.

[1010] Step 5:

[1011] The server passes the image data to the generation AI, which converts it into text data. The received image data is processed through the generation AI's interface, and the text information in the image is extracted and converted into text data.

[1012] Step 6:

[1013] The server receives the generated text data. The server temporarily stores the text data returned from the generation AI and prepares it for the next process.

[1014] Step 7:

[1015] The server uses an emotion engine to analyze the emotion data. The server passes the facial expression data to the emotion engine to analyze the user's emotion. The emotion engine uses a facial expression analysis algorithm to determine the user's emotion.

[1016] Step 8:

[1017] The server adjusts the text data based on the results of the sentiment analysis. For example, if it determines that the user is feeling stressed, it adds a specific annotation to the text data and notifies the support staff.

[1018] Step 9:

[1019] The server sends the adjusted text data to multiple systems. The server makes HTTP POST requests to the API endpoints of the multiple systems to send the text data.

[1020] Step 10:

[1021] Each system processes the text data it receives. Multiple systems automatically process the text data sent from the server, storing it in their respective databases or using it for specific business processes.

[1022] Step 11:

[1023] The user checks the processing results. Once processing is complete, the user can check the status of the document they sent and the results of the sentiment analysis through the application. They can check whether the text conversion and data storage were successful, and whether any actions were taken based on the sentiment analysis results.

[1024] These are the steps in a series of processes that digitize image data and emotion data and efficiently import them into multiple systems as text data. This system improves operational efficiency and significantly reduces the risk of input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[1025] Example 2

[1026] 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."

[1027] Conventional image data to text data conversion systems are successful in extracting textual information from images, but they are unable to provide an optimal user experience because they are unable to consider the user's emotional state. Furthermore, the accuracy of the text data and the adjustment of the transmitted information are insufficient, resulting in input errors and inefficient data processing. To solve these issues, a system that simultaneously achieves high-precision text conversion and an improved user experience is required.

[1028] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for acquiring image information and user facial expression information, a means for analyzing the image information and using a generative model to convert it into text data, and a means for analyzing emotions based on the user facial expression information. This enables not only highly accurate text conversion but also appropriate adjustments based on the user's emotions, thereby improving the user experience and enabling efficient data processing.

[1029] "Image information" refers to visual data obtained using an input device such as a camera or scanner.

[1030] "User's facial expression information" refers to data of the user's facial expression captured using a camera or the like of the terminal.

[1031] A "generative model" is an AI model that uses machine learning algorithms to analyze image data and convert it into text data.

[1032] An "information processing device" is a computer system, such as a server or client system, that receives, processes, and stores various types of data.

[1033] "Central Processing Unit" means a central computer system that processes information, including a server.

[1034] An "emotion engine" is an algorithm or model that analyzes a user's facial expression data and recognizes and judges their emotional state.

[1035] "Text data" refers to character information extracted by analyzing image data using a generative model.

[1036] An "HTTP POST request" is a request method for sending data from a client to a server using the Internet protocol HTTP.

[1037] "OCR (Optical Character Recognition) technology" is a technology that reads character information from image data and converts it into text format.

[1038] The present invention is a system that allows users to convert paper documents and application forms into digital format and import them as text data into multiple information processing devices. Furthermore, it is a mechanism for improving the user experience by combining an emotion engine that recognizes the user's emotions. This system acquires images using a smartphone or other mobile device (hereinafter referred to as "device"), converts them into text using generative AI via a server, and transmits the converted text data to multiple information processing devices. Additionally, it includes an emotion engine that analyzes the user's emotions based on image data and other input data.

[1039] User operations

[1040] Users use the device's camera to take images of documents or application forms. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, an emotion engine recognizes emotions based on the user's facial expressions and operational status. Users do not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[1041] Terminal handling

[1042] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion engine contains an algorithm that analyzes the facial expression data acquired by the device and determines the user's emotion.

[1043] Server Processing

[1044] The server receives image data and emotion data sent from the device. The received image data is processed by the generation AI, and the character information in the image is converted into text data. The generation AI uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[1045] The converted text data is adjusted based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, a corresponding message can be added to notify support staff. After the data is converted into text data, the server prepares it to be sent to various information processing devices. The server sequentially calls the API endpoints of multiple information processing devices and sends the generated text data. Each information processing device automatically processes the received text data, saving it in the necessary database or using it in a specific application.

[1046] Specific examples

[1047] For example, when a user scans a receipt for expense reimbursement, the following process occurs:

[1048] 1. The user takes a photo of the receipt using the smartphone camera, and the user's facial expression is captured at the same time.

[1049] 2. The device sends the captured image data and the user's facial expression data to the server.

[1050] 3. The server passes the received image data to the generation AI and converts it into text data. At the same time, the emotion engine analyzes the user's emotions.

[1051] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion engine.

[1052] 5. The adjusted text data is sent to multiple internal systems, such as expense reimbursement systems and accounting systems.

[1053] 6. Each system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis to enhance user support.

[1054] Example prompt for a generative AI model:

[1055] The image below contains an expense receipt. Please convert this image to text format. At the same time, please analyze the user's facial expressions to determine their emotions and include the results.

[1056] In this way, with the system of the present invention, all a user has to do is take a photo of a document and send it; all processing is done automatically on the server side, realizing efficient data import and processing. This system is expected to significantly reduce operation time and eliminate input errors. Furthermore, by combining it with an emotion engine, the user experience can be improved.

[1057] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1058] Step 1:

[1059] The user takes an image of a paper document or application form using the device's camera. The input is the image information acquired through the camera, and the output is an image file stored inside the device. Specifically, the user takes the image by tapping the "take a photo" button in the dedicated application.

[1060] Step 2:

[1061] After taking a picture, the user sends the image data to the server via an application on the device. The input is the captured image file, and the output is the HTTP POST request data sent to the server. Specifically, the user taps the "Send" button in the application.

[1062] Step 3:

[1063] The device sends the captured image data and the user's facial expression data to the server via an HTTP POST request. The input is the image data and facial expression data, and the output is the HTTP request data sent to the server. Specifically, the device automatically analyzes the facial expression data captured by the camera and sends it together with the image data.

[1064] Step 4:

[1065] The server receives the HTTP POST request sent from the device and obtains the image data and facial expression data. The input is the HTTP POST request data, and the output is the storage of the image data and facial expression data within the server. Specifically, the server analyzes the request content and stores the data in an appropriate format.

[1066] Step 5:

[1067] The server uses a generative AI model to convert the received image data into text data. The input is the received image data, and the output is text data. The generative AI model uses a machine learning algorithm to extract text information from the image. Specifically, the server passes the image data to the generative AI model, which then uses OCR technology to convert it into text format.

[1068] Step 6:

[1069] The server uses an emotion engine to analyze emotions from the user's facial expression data. The input is facial expression data, and the output is analyzed emotional state data. Specifically, the server passes the facial expression data to the emotion engine, which then executes an algorithm to determine the user's emotion.

[1070] Step 7:

[1071] The server adjusts the text data generated by the generative AI model based on the analysis results of the emotion engine. The input is text data and emotional state data, and the output is the adjusted text data. Specifically, the server makes appropriate adjustments to the text data based on the analysis results. For example, if the user is feeling stressed, it adds an additional support message.

[1072] Step 8:

[1073] The adjusted text data is sequentially transmitted from the server to the API endpoints of the multiple information processing devices. The input is the adjusted text data, and the output is the data transmitted to each information processing device. Specifically, the server calls the API of each information processing device and transmits the data.

[1074] Step 9:

[1075] Each information processing device automatically processes the received text data, saving it in the required database or using it in a specific application. The input is the transmitted text data, and the output is saving the processed data or using it in an application. Specifically, each information processing device stores the data received via API in its internal system and automatically executes the business process.

[1076] (Application example 2)

[1077] 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."

[1078] In today's world, the digitization of paper documents and application forms requires rapid and accurate conversion. However, with conventional systems, this conversion process takes time and effort, and input errors and inaccuracies in data are particularly problematic. Furthermore, to improve the user experience, systems must be able to understand users' emotions and provide appropriate support, but there are few systems with such capabilities.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring image information, means for using a generative model to analyze the image information and convert it into text data, emotion recognition means for analyzing a user's emotion, means for adjusting the text data based on the emotion information analyzed by the emotion recognition means, and means for transmitting the text data to multiple systems. This enables users to easily convert paper documents and application forms into digital format and further receive appropriate support according to the user's emotion.

[1080] "Image information" is image data of paper documents or application forms photographed by a user.

[1081] A "generative model" is a model used to convert image information into text data using machine learning algorithms.

[1082] The "emotion recognition means" is a means for analyzing the emotions of a user from their facial expressions and actions, and acquiring the results as data.

[1083] "Text data" is data that includes character information analyzed from image information.

[1084] "Central processing unit" refers to the central device or system that analyzes and transforms data and performs emotion recognition.

[1085] "Emotion information" is data obtained as a result of analyzing a user's emotions.

[1086] "Multiple systems" refers to multiple information processing systems that work together to receive and process text data.

[1087] System configuration and processing overview

[1088] This invention is a system that allows users to convert paper documents and application forms into digital formats and further improves the user experience by recognizing the user's emotions. The system acquires images using a smartphone or other mobile device, converts them into text using a generative model via a central processing unit (server), and then transmits the converted text data to multiple systems. It also includes emotion recognition means that analyzes emotions based on the user's facial expressions and operating status.

[1089] User operations

[1090] The user uses the device's camera to take an image of a document or application form. After taking the image, the image is saved on the device and sent to a server via a specific application. At the same time, emotion recognition is performed by the emotion recognition means based on the user's facial expressions and operational status. The user does not need to perform any particularly complicated operations; they simply take the image according to the application's instructions and press the send button.

[1091] Terminal handling

[1092] The device sends the captured image and data including the user's facial expression to the server. Specifically, the image data and the user's facial expression data are sent to the server using an HTTP POST request. The emotion recognition means incorporates an algorithm that analyzes the image data and determines the user's emotion.

[1093] Server Processing

[1094] The server receives image data and emotion data sent from the device. The received image data is processed by a generative model, and the character information in the image is converted into text data. The generative model uses machine learning algorithms to analyze the image information and perform highly accurate text conversion.

[1095] The converted text data is adjusted based on the user's emotions as recognized by the emotion recognition means. For example, if the user is feeling stressed, a corresponding message can be added to notify the support staff.

[1096] After the data is converted into text data, the server prepares it for transmission to various systems. The server sequentially calls the API endpoints of multiple systems and transmits the generated text data. Each system automatically processes the received text data, storing it in the necessary database or using it in a specific application.

[1097] Specific examples

[1098] For example, when a user scans a receipt for electronic payment, the following process occurs:

[1099] 1. The user takes a photo of the receipt using the smartphone camera. At the same time, the user's facial expression is captured.

[1100] 2. The device sends the captured image data and the user's facial expression data to the server.

[1101] 3. The server passes the received image data to the generative model and converts it into text data. At the same time, the emotion recognition means analyzes the user's emotions.

[1102] 4. The generated text data is adjusted as necessary based on the analysis results of the emotion recognition means. For example, if the user is feeling stressed, a message such as "The user may be feeling anxious about making a payment" is added.

[1103] 5. The adjusted text data is sent to the payment system.

[1104] 6. The payment system automatically processes the received text data and stores it in the necessary documents and databases, while also taking into account the results of sentiment analysis, enhancing user support.

[1105] Prompt Sentence Examples

[1106] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[1107] This allows users to simply take a photo of a document and send it, with all processing performed automatically on the server side, enabling efficient data capture and processing. Furthermore, combining it with emotion recognition means can improve the user experience.

[1108] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1109] Step 1:

[1110] The user uses the device's camera to take a photo of a paper document or application form. When taking the photo, the user's facial expression is also captured. This allows the image data and facial expression data to be input into the device.

[1111] Step 2:

[1112] The device sends the captured image data and the user's facial expression data to the server using an HTTP POST request, and the server receives the data.

[1113] Step 3:

[1114] The server passes the received image data to a generative model, which analyzes the text information in the image and converts it into text data. This generative model uses a machine learning algorithm to perform advanced pattern recognition on the input image data and output the text data.

[1115] Step 4:

[1116] At the same time, the server uses emotion recognition means to analyze the received user facial expression data. The emotion recognition means determines the user's emotions based on the image data and outputs the results as emotional information. Specifically, it identifies whether the user is happy or stressed based on changes in facial expressions and feature points.

[1117] Step 5:

[1118] The server then adjusts the text data appropriately based on the text data converted by the generative model and the emotion information obtained by the emotion recognition means. For example, if the user is feeling stressed, the server adds a message saying, "The user may need additional support."

[1119] Step 6:

[1120] The server then sequentially sends the adjusted text data to the API endpoints of multiple systems. This allows each system to receive the necessary data and automatically process it internally, registering it in each system's database or using it in specific applications.

[1121] Step 7:

[1122] As a concrete example, a payment system can automatically process expense settlements and accounting based on received text data, and can also enhance user support based on emotional information. For example, if a user feels anxious, the system can display an additional support message.

[1123] Prompt Sentence Examples

[1124] "A user took a photo of a convenience store receipt and sent it to the server. The user's facial expression appears to be a little stressed. Based on what you can read from the image, convert the necessary data into text and add an appropriate message."

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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).

[1132] 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.

[1133] 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."

[1134] 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.

[1135] 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).

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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.

[1145] 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.

[1146] The following is further disclosed regarding the above embodiment.

[1147] (Claim 1)

[1148] means for acquiring image information;

[1149] means for analyzing the image information and converting it into text data using a generative model;

[1150] means for transmitting the text data to a plurality of systems;

[1151] A system including:

[1152] (Claim 2)

[1153] 10. The system of claim 1, further comprising means for transmitting captured image information to a central processing unit.

[1154] (Claim 3)

[1155] The system of claim 1 , wherein the generative model is constructed using a machine learning algorithm.

[1156] "Example 1"

[1157] (Claim 1)

[1158] a means for acquiring image information at the terminal;

[1159] means for transmitting the image information to a server using an HTTP POST request;

[1160] means for converting the image information into text data using a generative AI model in the server;

[1161] means for transmitting the text data to API endpoints of a plurality of external systems;

[1162] A system including:

[1163] (Claim 2)

[1164] 2. The system of claim 1, wherein said terminal includes means for compressing and converting said image information into a format suitable for transmission.

[1165] (Claim 3)

[1166] The system of claim 1, wherein the generative AI model includes means for parsing textual information from the image information using a prompt sentence.

[1167] "Application Example 1"

[1168] (Claim 1)

[1169] means for acquiring image information;

[1170] means for analyzing the image information and converting it into text data using a generative model;

[1171] means for transmitting the converted text data to a plurality of systems;

[1172] means for linking the text data to a sales data management system;

[1173] means for linking the text data to an inventory management system;

[1174] A system including:

[1175] (Claim 2)

[1176] 10. The system of claim 1, further comprising means for transmitting captured image information to a central processing unit.

[1177] (Claim 3)

[1178] The system of claim 1 , wherein the generative model is constructed using a machine learning algorithm.

[1179] "Example 2: Combining Emotion Engines"

[1180] (Claim 1)

[1181] means for acquiring image information;

[1182] means for analyzing the image information and converting it into text data using a generative model;

[1183] means for transmitting the text data to a plurality of information processing devices;

[1184] means for acquiring the image information and facial expression information of a user;

[1185] means for analyzing emotions based on facial expression information of the user;

[1186] means for adjusting the text data including the analysis results;

[1187] A system including:

[1188] (Claim 2)

[1189] 10. The system of claim 1, further comprising means for transmitting captured image information to a central processing unit.

[1190] (Claim 3)

[1191] The system of claim 1 , wherein the generative model is constructed using a machine learning algorithm.

[1192] "Application example 2 when combining emotion engines"

[1193] (Claim 1)

[1194] means for acquiring image information;

[1195] means for analyzing the image information and converting it into text data using a generative model;

[1196] emotion recognition means for analyzing the emotion of a user;

[1197] means for adjusting the text data based on the emotion information analyzed by the emotion recognition means;

[1198] means for transmitting the text data to a plurality of systems;

[1199] A system including:

[1200] (Claim 2)

[1201] 10. The system of claim 1, further comprising means for transmitting the captured image information and emotion information to a central processing unit.

[1202] (Claim 3)

[1203] The system of claim 1 , wherein the generative model is constructed using a machine learning algorithm. [Explanation of symbols]

[1204] 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 acquiring image information; means for analyzing the image information and converting it into text data using a generative model; means for transmitting the text data to a plurality of systems; A system including:

2. 2. The system of claim 1, further comprising means for transmitting captured image information to a central processing unit.

3. The system of claim 1 , wherein the generative model is constructed using a machine learning algorithm.

Images