System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing an image of a print media with an imaging device; means for transmitting the captured image to a server via a network; means for extracting text from the image using an speech synthesis device; means for converting the extracted text to audio; means for transmitting the converted audio back to the client via the network; and means for playing the transmitted audio at the client.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] For the visually impaired and busy people, there are many limitations to accessing text information in print media. Visually impaired people have difficulty reading printed materials, making it difficult for them to receive and understand information. In addition, people commuting or traveling have limited time to read text, making it difficult for them to digest information efficiently. This invention solves these problems by converting text information in print media into speech, allowing visually impaired and busy people to easily access information. [Means for solving the problem]

[0005] The present invention provides the following means. First, a means for capturing an image of a print medium using a photographing device is provided. Next, a means for transmitting the captured image data to a server via a network is provided. The server is provided with a means for extracting text from the image data using an optical character recognition device. Furthermore, a speech synthesizer is provided for converting the extracted text into speech. By providing a means for returning the converted speech data to a terminal via the network and a means for playing the returned speech data on the terminal, a user can obtain text information by speech. Furthermore, the speech synthesizer supports multiple languages ​​and accents, making it possible to accommodate a wider range of users. Furthermore, by including a means for saving the received speech data on the terminal and making it possible to play it later, the user can easily check the speech information again when necessary.

[0006] An "imaging device" is a device for capturing an image of a print medium.

[0007] A "network" is a communication means for sending and receiving data between a terminal and a server.

[0008] A "server" is a device that processes image data received from a terminal via a network and generates text and voice data.

[0009] A "terminal" is a device that is operated by a user and has a photographing device and an audio playback function.

[0010] An "optical character recognition device" is a device that applies technology to extract character information from image data.

[0011] A "voice synthesizer" is a device for converting text data into voice data.

[0012] "Voice data" refers to digital data of voice information generated by a voice synthesizer.

[0013] "Text data" refers to digital data of character information extracted by an optical character recognition device.

[0014] The "storage means" is a mechanism for storing received audio data in the terminal so that it can be played back later.

[0015] The "playback means" is a mechanism for playing back audio data stored in the terminal so that the user can listen to the audio. [Brief explanation of the drawings]

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

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system for converting text information on a print medium into speech for the visually impaired and busy people. Specific embodiments of this system will be described below.

[0038] System Overview

[0039] The system of the present invention is mainly composed of a terminal, a network, and a server.

[0040] 1. Device:

[0041] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet device can be used.

[0042] It has the function of sending the acquired images to a server via a network.

[0043] It has a reproducing means for reproducing the audio data returned from the server.

[0044] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[0045] 2. Network:

[0046] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[0047] 3. Server:

[0048] A device that processes image data received from a terminal.

[0049] An optical character recognizer is used to extract text from images.

[0050] A speech synthesizer is used to convert the extracted text into speech data, which is then sent back to the terminal via the network.

[0051] Program processing explanation

[0052] The specific program processing of this system will be explained below in order.

[0053] Image acquisition and transmission

[0054] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[0055] Extracting text from images

[0056] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[0057] Text-to-speech

[0058] The server converts the extracted text into voice data using a speech synthesizer. At this time, the language and accent of the voice can be adjusted according to the user's settings. This allows users to receive text information in a voice that suits them best.

[0059] Sending and playing audio data

[0060] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[0061] Specific examples

[0062] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0063] 1. The user takes a photo of a page in a book using their smartphone camera.

[0064] 2. The application on the smartphone sends this image data to the server.

[0065] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0066] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0067] 5. The server sends the generated voice data to the smartphone.

[0068] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0069] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to visually impaired people and busy people.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] The user takes a photo of the printed text using the device's camera function. The device acquires the image data through the camera and stores the image in memory.

[0073] Step 2:

[0074] The device sends the stored image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[0075] Step 3:

[0076] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[0077] Step 4:

[0078] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information within the image, where an OCR engine analyzes the image and generates a string of characters.

[0079] Step 5:

[0080] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[0081] Step 6:

[0082] The server converts the generated audio data into a file format and saves it. A path for the saved audio file is generated.

[0083] Step 7:

[0084] The server returns the path of the saved audio file to the device, which uses this path to download the audio file from the server.

[0085] Step 8:

[0086] The terminal stores the downloaded audio file in the terminal for playback, and uses the audio playback function of the terminal to play the audio data to the user.

[0087] Step 9:

[0088] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[0089] In this way, users can easily convert printed text information into speech and retrieve it efficiently, greatly improving information access for the visually impaired and busy people.

[0090] Example 1

[0091] 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."

[0092] Visually impaired people and busy people face challenges in easily and efficiently obtaining text information from printed materials through audio. Conventional systems require a complex process of converting image data to text and then converting that text to audio, making operation cumbersome. Furthermore, the lack of a means to play or save audio data limits the user experience.

[0093] 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.

[0094] In this invention, the server includes means for extracting text from the image data using an optical character recognition device, a speech synthesis device for converting the extracted text into speech, and means for returning the converted speech data to the terminal via the network. This allows users to easily obtain text information from printed materials by speech and save and play the speech data, improving convenience for visually impaired people and busy people.

[0095] An "imaging device" is a device for capturing an image of a print medium, and includes, for example, a camera or the camera function of a smartphone.

[0096] "Image data" is digital data of an image of a print medium captured by a photographing device.

[0097] "Network" refers to the means of communication for sending and receiving data between a terminal and a server, including the Internet and wireless communication.

[0098] The "server" is a device that analyzes received image data using an optical character recognition device, extracts text information, and converts it into voice data.

[0099] An "optical character recognition device" is a technical device that extracts character information from image data and uses OCR technology.

[0100] "Text" is character information extracted from image data by an optical character recognition device.

[0101] A "speech synthesizer" is a technical device that converts extracted text into speech data, and uses speech synthesis technology.

[0102] "Voice data" refers to digital data that is generated by a voice synthesizer and can be reproduced as voice.

[0103] A "terminal" is a device used by a user, which has the function of playing or saving audio data.

[0104] "Internal storage" refers to a storage device installed within a terminal for storing digital data.

[0105] An "audio player" is software or hardware installed on a terminal for playing audio data.

[0106] The present invention relates to a system for converting text information from print media into speech, aimed at visually impaired people and busy people. This system is mainly composed of a terminal, a network, and a server.

[0107] Hardware and software used

[0108] Terminal

[0109] The terminals used are smartphones or tablet devices. The terminals are equipped with a camera function so that users can take pictures of the printed materials. The terminals also have a communication means for sending the acquired image data to a server via a network.

[0110] network

[0111] The network uses the Internet or wireless communication, which allows data to be sent and received efficiently between the terminal and the server.

[0112] server

[0113] The server is equipped with the following hardware and software:

[0114] Optical character recognition (OCR) devices: For example, using Tesseract OCR or Google Cloud Vision API to extract text information from image data.

[0115] Speech synthesizer: For example, use Google Text-to-Speech or Amazon Polly to convert the extracted text into audio data.

[0116] Program processing

[0117] Image acquisition and transmission

[0118] The user takes a picture of the printed text using the camera function of the device, and the device sends the image data to a server via the Internet or wireless communication.

[0119] Extracting text from images

[0120] The server analyzes the received image data using an optical character recognition device to extract text information from the image. For example, the server receives the image data and calls Tesseract OCR or Google Cloud Vision API to scan the text information in the image and convert it into digital text.

[0121] Text-to-speech

[0122] The server then converts the extracted text into audio data using a speech synthesizer, such as Google Text-to-Speech or Amazon Polly, and saves the resulting audio data in a specified format (e.g., MP3).

[0123] Sending and playing audio data

[0124] The server transmits the generated audio data to the device via the network. The device that receives the data stores the audio data in its internal storage and plays it back using its built-in audio player.

[0125] Specific examples

[0126] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0127] 1. The user takes a photo of a page in a book using their smartphone camera.

[0128] 2. The application on the smartphone sends this image data to the server.

[0129] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0130] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0131] 5. The server sends the generated voice data to the smartphone.

[0132] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0133] Examples of prompt statements

[0134] Below are some examples of prompts for generative AI models:

[0135] Example prompt sentence:

[0136] "Hello, Model. I'm developing a system to allow the visually impaired to hear printed book pages aloud. Could you please walk me through the steps a user takes a photo of a book page with their smartphone camera and then converts the text into speech and plays it back?"

[0137] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to the visually impaired and busy people.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Image acquisition

[0140] The user takes a picture of the printed media using the device's camera function. When the user presses the capture button, the smartphone's camera app starts up and the captured image is saved in the device's internal storage.

[0141] Input: Print media (books, newspapers, etc.)

[0142] Output: Acquired image data

[0143] Specific operation: The user opens the camera app, frames the target print, and takes a photo. The image data is temporarily saved on the device.

[0144] Step 2: Send image data

[0145] The device sends the acquired image data to the server via the network, and an application on the smartphone automatically generates an HTTP POST request to upload the image data to the server.

[0146] Input: Acquired image data

[0147] Output: Image data sent to the server

[0148] Specific operation: The application on the device selects the image data and sends it to the server via the Internet.

[0149] Step 3: Extract text from images

[0150] The server analyzes the received image data using an optical character recognition device to extract the text information in the image, then calls OCR software (such as Tesseract OCR or Google Cloud Vision API) to scan the text information in the image and convert it into digital text.

[0151] Input: Image data sent to the server

[0152] Output: Extracted text data

[0153] What happens: The server stores the received data and runs an OCR process to extract text information from the image data.

[0154] Step 4: Convert text to speech

[0155] The server converts the extracted text into voice data using a speech synthesizer. The server uses Google Text-to-Speech or Amazon Polly to convert the text into voice data. It is also possible to adjust the language and accent of the voice according to the user's settings.

[0156] Input: Extracted text data

[0157] Output: Converted audio data

[0158] Specific operation: The server passes the text data to the speech synthesis system to generate audio data. The generated audio data is saved in the specified format (e.g. MP3).

[0159] Step 5: Sending audio data

[0160] The server sends the generated voice data to the terminal via the network, and returns the voice data to the terminal as an HTTP response.

[0161] Input: Converted audio data

[0162] Output: Audio data sent to the device

[0163] Specific operation: The server returns the audio data as an HTTP response, and the device receives it.

[0164] Step 6: Play and save the audio data

[0165] The device stores the received audio data in its internal storage and plays it using the built-in audio player, allowing the user to play the received audio at any time.

[0166] Input: Audio data sent to the device

[0167] Output: Played audio, stored audio data

[0168] Specific operation: The device saves the audio data to the internal storage, and the user operates the audio player to play the audio.

[0169] By performing the above steps, the system of the present invention can provide text information from printed material simply and efficiently by voice.

[0170] (Application example 1)

[0171] 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."

[0172] Conventional systems that convert text information from print media into speech are only useful for the visually impaired and busy people, but they lack the ability to provide audio guidance of product labels and descriptions in physical stores, which causes inconvenience when shopping in physical stores. Visually impaired people in particular often have difficulty selecting and purchasing products. Even for busy people, the inefficiency of gathering information in stores has been an issue.

[0173] 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.

[0174] In this invention, the server includes means for capturing an image of an actual product using a photographing device, means for transmitting the captured image data to an information processing device via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to a terminal via the network, means for playing the returned speech data on the terminal, and means for providing audio guidance of product labels and descriptions in a store, thereby enabling visually impaired people and busy people to easily shop in a physical store.

[0175] An "imaging device" is a hardware device for capturing images of real objects.

[0176] "Image data" refers to image information of an actual object captured by a photographing device.

[0177] A "network" is a communication means for sending and receiving data between a terminal and a server.

[0178] An "information processing device" is a device that functions as a server and processes data.

[0179] An "optical character recognition device" is a device for extracting text from image data.

[0180] A "speech synthesizer" is a device for converting extracted text into speech data.

[0181] A "terminal" is a device that plays back the audio data returned from the server, and includes smartphones and tablets.

[0182] "Product label" refers to the information label affixed to a product in a physical store.

[0183] "Description" refers to the text information that describes a product or service in a physical store.

[0184] "Voice guidance means" is a function that informs the user of information on product labels and descriptions through voice.

[0185] System Overview

[0186] The system of this invention aims to make shopping in brick-and-mortar stores easier for visually impaired people and busy people. The system consists of the following elements:

[0187] Hardware and software used

[0188] Smartphone cameras as photographic devices

[0189] Internet connection as a network

[0190] Server as an information processing device

[0191] Tesseract OCR as an optical character recognizer

[0192] Google Cloud Text-to-Speech API as a speech synthesizer

[0193] Smartphones as devices

[0194] System Operation

[0195] The operation of the system involves the following steps:

[0196] 1. Image capture: The user uses the smartphone camera to take an image of the product label or description.

[0197] 2. Image transmission: The smartphone transmits the captured image data to a server via the Internet.

[0198] 3. Character Recognition: The server uses Tesseract OCR to extract character information from the received image data.

[0199] 4. Speech conversion: The extracted text data is converted to audio data using the Google Cloud Text-to-Speech API.

[0200] 5. Voice data transmission: The converted voice data is sent back to the smartphone via the network.

[0201] 6. Audio playback: The smartphone plays the received audio data, allowing the user to check product information and descriptions by voice.

[0202] Specific examples

[0203] As a concrete example, consider the following scenario:

[0204] Imagine a user standing in front of a product shelf in a physical store, taking a picture of the label with their smartphone camera, and the application automatically sends the image to the server.

[0205] The server uses Tesseract OCR to extract text information from the image data, such as "Milk 1L 200 yen." This information is input into the Google Cloud Text-to-Speech API and generated as audio data.

[0206] The voice data is sent to the user's smartphone, and the user can hear the voice guidance, "Milk 1 liter, 200 yen." This example enables visually impaired people and busy people to quickly obtain necessary product information by voice, making shopping in physical stores more convenient.

[0207] Prompt Sentence Examples

[0208] An example prompt is:

[0209] "Please convert the following product information into audio: Milk 1L 200 yen"

[0210] Such a system can obtain product information without relying on vision by obtaining information from product labels and descriptions and providing audio guidance.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] A user takes a picture of a product label or description using a smartphone camera. The input is the actual product label or description, and the output is the captured image data. Specific operations include the user launching the application, switching to camera mode, and pressing the capture button.

[0214] Step 2:

[0215] The device sends the captured image data to the server via the Internet. The input here is the image data acquired in step 1, and the output is the image data sent to the server. Specific operations include the device automatically acquiring the image data and uploading it to the server using an HTTP request.

[0216] Step 3:

[0217] The server uses Tesseract OCR to extract text information from image data received by the server. The input is the image data sent to the server, and the output is the extracted text data. Specific operations include the server processing the received data and calling the OCR engine to perform character recognition.

[0218] Step 4:

[0219] The server converts the extracted text data into speech data using the Google Cloud Text-to-Speech API. The input here is the text data extracted in step 3, and the output is the generated speech data. Specific operations include the server calling the Text-to-Speech API to input the text data and perform speech synthesis.

[0220] Step 5:

[0221] The server sends the audio data to the terminal via the network. The input here is the audio data generated in step 4, and the output is the audio data sent to the terminal. Specific operations include the server returning the generated audio data to the terminal in an HTTP response.

[0222] Step 6:

[0223] The terminal plays the received audio data. The input is the audio data sent from the server, and the output is the audio information played back to the user. Specific operations include the terminal's audio player decoding the audio data and playing it through the speaker.

[0224] In this way, by explaining the specific operations and inputs / outputs of each step, you can gain a detailed understanding of the overall system and how it operates.

[0225] 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.

[0226] The present invention relates to a system for converting text information from print media into speech for visually impaired people and busy people, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system will be described below.

[0227] System Overview

[0228] The system of the present invention comprises a terminal, a network, a server, and an emotion engine.

[0229] 1. Device:

[0230] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet is used.

[0231] It has the function of sending the acquired image data to a server via a network.

[0232] It has a playback means for playing back the voice data returned from the server, and is also equipped with an emotion engine that has the function of recognizing emotions from the user's facial expressions and voice.

[0233] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[0234] 2. Network:

[0235] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[0236] 3. Server:

[0237] A device that processes image data received from a terminal.

[0238] An optical character recognizer is used to extract text from images.

[0239] It is equipped with a speech synthesizer that converts the extracted text into speech data.

[0240] When synthesizing speech, it has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[0241] 4. Emotion Engine:

[0242] It is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice.

[0243] The emotion engine can transmit the acquired emotion data to the server and reflect it in the generation of voice data.

[0244] Program processing explanation

[0245] The specific program processing of this system will be explained below in order.

[0246] Image acquisition and transmission

[0247] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[0248] Extracting text from images

[0249] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[0250] Text-to-speech

[0251] The server converts the extracted text into voice data using a speech synthesizer, and can adjust the language and accent of the voice according to the user's settings. Furthermore, the server can adjust the voice tone and speed based on the user's emotional data transmitted from the device.

[0252] Sending and playing audio data

[0253] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[0254] Functions and Use of Emotion Engine

[0255] The emotion engine is installed on the device and analyzes the user's facial expressions and voice in real time. The emotion data is sent to the server and reflected in the voice synthesis. For example, if the user is tired, a calm tone of voice is generated. On the other hand, if the user is happy, a bright tone of voice is generated.

[0256] Specific examples

[0257] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0258] 1. The user takes a photo of a page in a book using their smartphone camera.

[0259] 2. The application on the smartphone sends this image data to the server.

[0260] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0261] 4. The server uses speech synthesis technology to convert this text into speech, adjusting the tone and speed of the speech based on data from the emotion engine.

[0262] 5. The server sends the generated voice data to the smartphone.

[0263] 6. The smartphone plays the received audio data, and the user hears the audio saying "Hello, world." At this time, an audio tone is played that corresponds to the user's emotional state.

[0264] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] The user uses the device's camera to take a picture of the printed text, and the device stores the captured image data in its memory.

[0268] Step 2:

[0269] The device sends the saved image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[0270] Step 3:

[0271] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[0272] Step 4:

[0273] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information from the image. The OCR engine analyzes the image and generates a string of characters.

[0274] Step 5:

[0275] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[0276] Step 6:

[0277] The server adjusts the voice tone and speed based on the user's emotional data sent from the device, so that the voice data is appropriate for the user's emotional state.

[0278] Step 7:

[0279] The server saves the generated audio data, generates a path for the saved audio file, and returns the path to the device.

[0280] Step 8:

[0281] The terminal receives the path of the audio file returned from the server, and uses this path to download the audio file from the server.

[0282] Step 9:

[0283] After the download is complete, the terminal uses the playback means to play the received audio file, and the terminal uses the audio playback function to play the audio data to the user.

[0284] Step 10:

[0285] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[0286] Step 11:

[0287] The emotion engine analyzes the user's facial expressions and voice in real time to obtain emotional data, which is then sent to the server and reflected in the next speech synthesis.

[0288] In this way, the system provides a more personalized audio experience by providing voice data that reflects the user's emotions, and it can significantly improve information access for the visually impaired and busy people.

[0289] Example 2

[0290] 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."

[0291] In modern society, visually impaired people and busy people need efficient and intuitive ways to obtain information from print media. However, conventional systems cannot generate speech that takes the user's emotions into account, making it difficult to improve the user experience. Furthermore, the process of information acquisition and speech generation is limited to a single function, resulting in a lack of flexibility. To solve these problems, a technology that synthesizes speech based on the user's emotions is needed.

[0292] 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 means for capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, means for playing the returned speech data on the terminal, and an emotion engine for recognizing the user's emotion and adjusting the speech data based on the emotion. This allows visually impaired people and busy people to efficiently obtain information obtained from print media by speech, and the tone and speed of the speech reflect the user's emotion, enabling a more intuitive and comfortable user experience.

[0293] An "imaging device" is a device for capturing an image of a print medium, and examples include smartphones and tablets.

[0294] A "network" is a communication means for sending and receiving data between a terminal and a server, and may be an internet line or a wireless network.

[0295] An "optical character recognition device" is a technology for extracting text information from image data, and OCR technology is one such example.

[0296] A "speech synthesizer" is a technology for converting extracted text into audio data, and includes text-to-speech systems and speech synthesis engines.

[0297] A "server" is a device that processes received image data and performs text extraction and voice synthesis.

[0298] A "terminal" is a device that includes a photographing device, transmits image data to a server, and plays back received audio data.

[0299] An "emotion engine" is a technology that analyzes a user's facial expressions and voice to recognize their emotions and reflects that data in speech synthesis.

[0300] This invention relates to a system that converts text information from print media into speech for visually impaired people and busy people, and also combines it with an emotion engine that recognizes the user's emotions. Details of how to specifically implement this system are described below.

[0301] System configuration

[0302] This system consists of terminals, a network, a server, and an emotion engine.

[0303] Device:

[0304] The terminal is a device that captures images of print media using a photographing device. Specific examples include smartphones and tablets. The terminal has the function of sending the captured image data to a server via a network and has a playback means for playing back the voice data returned from the server. It also has an emotion engine and the function of recognizing emotions from the user's facial expressions and voice. It also has a storage means for saving the voice data as needed so that it can be played back later.

[0305] network:

[0306] A network is a communication means for sending and receiving data between a terminal and a server, and can be an internet line or a wireless network.

[0307] server:

[0308] The server processes image data received from the device. It uses optical character recognition (OCR) to extract text from the image and then includes a speech synthesizer that converts the text into speech data. During speech synthesis, the server also has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[0309] Emotion Engine:

[0310] The emotion engine is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice. The emotion engine sends the acquired emotion data to the server, which can then be reflected in the generated voice data.

[0311] Specific examples

[0312] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0313] 1. The user takes a photo of a page in a book using their smartphone camera.

[0314] 2. The application on the smartphone sends this image data to the server.

[0315] 3. The server extracts text information from the image using OCR technology (e.g., Tesseract), e.g., the text "Hello, World" is extracted.

[0316] 4. The server converts this text into voice data using speech synthesis technology (e.g., Google Text-to-Speech or OpenAI's speech synthesis library), and adjusts the voice tone and speed based on the emotion data sent from the device.

[0317] 5. The server sends the generated voice data to the smartphone.

[0318] 6. The smartphone plays the received audio data, and the user hears the message "Hello, world" in a voice that corresponds to the user's emotional state.

[0319] Examples of prompt statements

[0320] Below are some example prompts for a generative AI model:

[0321] "Write a program to design a system that generates speech based on the user's emotional data. The system should be able to adjust the tone and speed of the speech depending on the user's emotion. Explain how the user can use their device to send images of printed media to a server, which will then extract text from the images and convert it into speech."

[0322] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] The user acquires an image of the print medium using a terminal.

[0326] The user launches the camera app on their device (such as a smartphone) and takes a picture of the page of the book or document they want to read. Specifically, they capture the image by framing the image appropriately and pressing the shutter button. The input is an image of the printed media, and the output is the captured image data.

[0327] Step 2:

[0328] The terminal transmits the image data to the server.

[0329] The device sends the captured image data to a server in the background. An application in the smartphone processes the image data and sends it to a specified server address via an Internet connection (Wi-Fi or mobile data). Specifically, this involves the user tapping the "Send" button. The input is the captured image data, and the output is the image data sent to the server.

[0330] Step 3:

[0331] The server extracts the text from the image data.

[0332] The server analyzes the received image data and extracts text using optical character recognition (OCR) technology. Character recognition is performed using an OCR library such as Tesseract to obtain text information from the image data. For example, the text "Hello, world" is extracted from the image data. The input is the image data sent to the server, and the output is the extracted text data.

[0333] Step 4:

[0334] The server converts the text into audio data.

[0335] The server converts the extracted text into voice data using a speech synthesizer. It uses Google Text-to-Speech or OpenAI's speech synthesis library to convert text to voice. Furthermore, it adjusts the voice tone and speed based on the user's emotional data sent from the device. Specifically, the server calls the speech synthesis API to brighten or calm the tone based on the user's emotional state. The input is the extracted text data and emotional data, and the output is the adjusted voice data.

[0336] Step 5:

[0337] The server sends the audio data to the terminal.

[0338] The server sends the generated voice data to the terminal via the network. Specifically, the server creates the generated voice file, assembles the file into data packets for transmission to the terminal, and transmits them via the network. The input is the adjusted voice data, and the output is the voice data transmitted to the terminal.

[0339] Step 6:

[0340] The device plays the audio data.

[0341] The terminal plays the received audio data using a playback means (speaker or headphones). The user can listen to the audio by pressing the play button in the application. It is also possible to save the audio data via a storage means and play it later. Specifically, this includes operations for the terminal to load the received audio data and issue a play command. The input is the audio data sent to the terminal, and the output is the played audio.

[0342] Step 7:

[0343] The emotion engine recognizes and reflects the user's emotions.

[0344] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates the data. The device sends this emotion data to the server, which then reflects this data when synthesizing speech. Specifically, when the user faces the smartphone camera, the device performs facial recognition and voice analysis, generates emotion data, and sends it to the server. The input is the user's facial expressions and voice data, and the output is emotion data.

[0345] (Application example 2)

[0346] 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."

[0347] Visually impaired people and busy people have difficulty reading restaurant and food delivery menus. Furthermore, if the audio information provided is not tailored to the user's emotional state, it can be stressful to understand the information and experience it is used. Therefore, there is a need for a system that delivers printed text information in audio that adapts to the user's emotional state.

[0348] The identification process by the identification 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 capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, an emotion analysis engine for analyzing a user's emotion and adjusting the tone and speed of speech synthesis based on the analysis results, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, and means for playing the returned speech data on the terminal. This makes it possible to provide text information on a print medium in a voice that corresponds to the user's emotion.

[0349] A "photography device" is a device for capturing an image of a print medium, such as a camera mounted on a smartphone or tablet.

[0350] "Image data" refers to image information of a print medium captured by a photographing device.

[0351] A "network" is a communication means for sending and receiving data between a terminal and a server, and includes the Internet and wireless networks.

[0352] A "server" is a device that analyzes image data received from a terminal and performs the necessary processing.

[0353] "Optical character recognition device" is a technology for extracting text information from image data, and generally refers to OCR (Optical Character Recognition) technology.

[0354] "Text" is written information in digital form that has been extracted by an optical character recognition device.

[0355] A "speech synthesizer" is a device equipped with technology for converting text information into voice data. For example, it includes text-to-speech technology.

[0356] "Voice data" refers to digital data in a voice format generated by a voice synthesizer.

[0357] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state and output the results.

[0358] A "terminal" is a device that has a camera, audio playback function, and network communication function, and includes smartphones and tablets.

[0359] The "playback means" is hardware or software for playing back audio data received by the terminal.

[0360] System Overview

[0361] This invention is a system for converting text information from print media into speech for visually impaired people and busy people. The system also combines an emotion analysis engine that recognizes the user's emotions and adjusts the tone and speed of the speech accordingly. Specific embodiments of the system are described below.

[0362] Hardware and Software Configuration

[0363] Terminal

[0364] A device is a device that includes a camera, such as a smartphone or tablet. A device has the following functions:

[0365] A function to capture images of print media using a photographic device

[0366] A function to send acquired image data to a server via a network

[0367] A function to play back audio data returned from the server

[0368] Equipped with an emotion analysis engine that analyzes emotions from the user's facial expressions and voice

[0369] A storage method that allows audio data to be saved and played back later if necessary

[0370] server

[0371] The server has the following capabilities:

[0372] A function that analyzes image data received from a device using optical character recognition (OCR) technology and extracts text information.

[0373] A speech synthesizer that converts extracted text into speech data

[0374] Ability to adjust voice tone and speed based on user emotion data

[0375] network

[0376] A communication method for sending and receiving data between a terminal and a server, including the Internet and wireless networks.

[0377] Program processing overview

[0378] The device first captures an image of the print media using the smartphone's camera. The image data is then sent to a server via a network. The server uses OCR technology to extract text information from the received image data. The extracted text is then converted into voice data using a voice synthesizer. When synthesizing the voice, the tone and speed of the voice are adjusted based on the user's emotional data sent from the device. The generated voice data is sent to the device via a network, where it is played back.

[0379] Specific examples

[0380] We will explain the series of processes that occur when a user takes a photo of a restaurant menu with their smartphone camera and listens to the menu contents aloud.

[0381] 1. The user takes a photo of a restaurant menu using their smartphone camera.

[0382] 2. The application on the smartphone sends this image data to the server.

[0383] 3. The server uses OCR technology to extract text information from the image, such as "We have sushi, tempura, and eel."

[0384] 4. The server converts this text to speech using speech synthesis technology, adjusting the tone and speed of the speech based on data from the sentiment analysis engine.

[0385] 5. The server sends the generated voice data to the smartphone.

[0386] 6. The smartphone plays the received audio data, and the user can hear the menu contents aloud. For example, if the user is happy, the audio will be played in a bright tone.

[0387] Prompt Sentence Examples

[0388] Create an audio file that reads the following text aloud, assuming the user's emotion is "joy."

[0389] Text: "We have sushi, tempura, and eel. Which would you like to eat?"

[0390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0391] Step 1:

[0392] A user uses the smartphone camera to take an image of a printed medium (e.g., a restaurant menu).

[0393] Input: User-taken image of printed material

[0394] Output: Captured image data file

[0395] Specific operation: The user opens the camera app on their smartphone, points it at the target print medium, and presses the shutter button to take a picture.

[0396] Step 2:

[0397] The terminal transmits the acquired image data to the server.

[0398] Input: Captured image data

[0399] Output: Image data sent to the server

[0400] Specific operation: An application on the smartphone automatically selects the captured image files and sends them to a specified server address via the Internet.

[0401] Step 3:

[0402] The server extracts text information from the received image data using an optical character recognition device.

[0403] Input: Image data sent to the server

[0404] Output: Extracted text information

[0405] What it does: OCR software on the server analyzes the image data and extracts the characters in the print media as digital text, for example, "We have sushi, tempura, and eel."

[0406] Step 4:

[0407] The server converts the extracted text information into audio data.

[0408] Input: Extracted text information

[0409] Output: Audio data file

[0410] What it does: Speech synthesis software on the server analyzes the text information and converts it into spoken audio, adjusting for the language and accent of the audio, if any.

[0411] Step 5:

[0412] The device uses an emotion analysis engine to analyze the user's emotions and sends the data to the server.

[0413] Input: User facial and voice data

[0414] Output: Sentiment analysis data

[0415] Specific operation: The emotion analysis engine analyzes the user's facial expressions and tone of voice in real time, generates emotion data (e.g., "happiness," "sadness," etc.) based on that, and sends it to the server.

[0416] Step 6:

[0417] The server adjusts the tone and speed of the voice based on the emotion analysis data.

[0418] Input: Audio data file, emotion analysis data

[0419] Output: Adjusted audio data file

[0420] What it does: The server's speech synthesis software uses the emotion analysis data to appropriately adjust the tone and speed of the speech. For example, if the user is "happy," a brighter tone will be generated.

[0421] Step 7:

[0422] The server transmits the generated voice data to the terminal.

[0423] Input: Adjusted audio data file

[0424] Output: Audio data sent to the device

[0425] Specific operation: The server sends an audio data file to the terminal via the network.

[0426] Step 8:

[0427] The terminal plays the concluded audio data.

[0428] Input: Audio data sent to the device

[0429] Output: Played audio

[0430] Specific operation: The smartphone's audio playback function analyzes the received audio data and plays it back through the speaker, allowing the user to hear the menu contents aloud.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] [Second embodiment]

[0435] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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."

[0447] The present invention relates to a system for converting text information on a print medium into speech for the visually impaired and busy people. Specific embodiments of this system will be described below.

[0448] System Overview

[0449] The system of the present invention is mainly composed of a terminal, a network, and a server.

[0450] 1. Device:

[0451] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet device can be used.

[0452] It has the function of sending the acquired images to a server via a network.

[0453] It has a reproducing means for reproducing the audio data returned from the server.

[0454] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[0455] 2. Network:

[0456] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[0457] 3. Server:

[0458] A device that processes image data received from a terminal.

[0459] An optical character recognizer is used to extract text from images.

[0460] A speech synthesizer is used to convert the extracted text into speech data, which is then sent back to the terminal via the network.

[0461] Program processing explanation

[0462] The specific program processing of this system will be explained below in order.

[0463] Image acquisition and transmission

[0464] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[0465] Extracting text from images

[0466] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[0467] Text-to-speech

[0468] The server converts the extracted text into voice data using a speech synthesizer. At this time, the language and accent of the voice can be adjusted according to the user's settings. This allows users to receive text information in a voice that suits them best.

[0469] Sending and playing audio data

[0470] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[0471] Specific examples

[0472] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0473] 1. The user takes a photo of a page in a book using their smartphone camera.

[0474] 2. The application on the smartphone sends this image data to the server.

[0475] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0476] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0477] 5. The server sends the generated voice data to the smartphone.

[0478] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0479] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to visually impaired people and busy people.

[0480] The processing flow will be explained below.

[0481] Step 1:

[0482] The user takes a photo of the printed text using the device's camera function. The device acquires the image data through the camera and stores the image in memory.

[0483] Step 2:

[0484] The device sends the stored image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[0485] Step 3:

[0486] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[0487] Step 4:

[0488] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information within the image, where an OCR engine analyzes the image and generates a string of characters.

[0489] Step 5:

[0490] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[0491] Step 6:

[0492] The server converts the generated audio data into a file format and saves it. A path for the saved audio file is generated.

[0493] Step 7:

[0494] The server returns the path of the saved audio file to the device, which uses this path to download the audio file from the server.

[0495] Step 8:

[0496] The terminal stores the downloaded audio file in the terminal for playback, and uses the audio playback function of the terminal to play the audio data to the user.

[0497] Step 9:

[0498] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[0499] In this way, users can easily convert printed text information into speech and retrieve it efficiently, greatly improving information access for the visually impaired and busy people.

[0500] Example 1

[0501] 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."

[0502] Visually impaired people and busy people face challenges in easily and efficiently obtaining text information from printed materials through audio. Conventional systems require a complex process of converting image data to text and then converting that text to audio, making operation cumbersome. Furthermore, the lack of a means to play or save audio data limits the user experience.

[0503] 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.

[0504] In this invention, the server includes means for extracting text from the image data using an optical character recognition device, a speech synthesis device for converting the extracted text into speech, and means for returning the converted speech data to the terminal via the network. This allows users to easily obtain text information from printed materials by speech and save and play the speech data, improving convenience for visually impaired people and busy people.

[0505] An "imaging device" is a device for capturing an image of a print medium, and includes, for example, a camera or the camera function of a smartphone.

[0506] "Image data" is digital data of an image of a print medium captured by a photographing device.

[0507] "Network" refers to the means of communication for sending and receiving data between a terminal and a server, including the Internet and wireless communication.

[0508] The "server" is a device that analyzes received image data using an optical character recognition device, extracts text information, and converts it into voice data.

[0509] An "optical character recognition device" is a technical device that extracts character information from image data and uses OCR technology.

[0510] "Text" is character information extracted from image data by an optical character recognition device.

[0511] A "speech synthesizer" is a technical device that converts extracted text into speech data, and uses speech synthesis technology.

[0512] "Voice data" refers to digital data that is generated by a voice synthesizer and can be reproduced as voice.

[0513] A "terminal" is a device used by a user, which has the function of playing or saving audio data.

[0514] "Internal storage" refers to a storage device installed within a terminal for storing digital data.

[0515] An "audio player" is software or hardware installed on a terminal for playing audio data.

[0516] The present invention relates to a system for converting text information from print media into speech, aimed at visually impaired people and busy people. This system is mainly composed of a terminal, a network, and a server.

[0517] Hardware and software used

[0518] Terminal

[0519] The terminals used are smartphones or tablet devices. The terminals are equipped with a camera function so that users can take pictures of the printed materials. The terminals also have a communication means for sending the acquired image data to a server via a network.

[0520] network

[0521] The network uses the Internet or wireless communication, which allows data to be sent and received efficiently between the terminal and the server.

[0522] server

[0523] The server is equipped with the following hardware and software:

[0524] Optical character recognition (OCR) devices: For example, using Tesseract OCR or Google Cloud Vision API to extract text information from image data.

[0525] Speech synthesizer: For example, use Google Text-to-Speech or Amazon Polly to convert the extracted text into audio data.

[0526] Program processing

[0527] Image acquisition and transmission

[0528] The user takes a picture of the printed text using the camera function of the device, and the device sends the image data to a server via the Internet or wireless communication.

[0529] Extracting text from images

[0530] The server analyzes the received image data using an optical character recognition device to extract text information from the image. For example, the server receives the image data and calls Tesseract OCR or Google Cloud Vision API to scan the text information in the image and convert it into digital text.

[0531] Text-to-speech

[0532] The server then converts the extracted text into audio data using a speech synthesizer, such as Google Text-to-Speech or Amazon Polly, and saves the resulting audio data in a specified format (e.g., MP3).

[0533] Sending and playing audio data

[0534] The server transmits the generated audio data to the device via the network. The device that receives the data stores the audio data in its internal storage and plays it back using its built-in audio player.

[0535] Specific examples

[0536] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0537] 1. The user takes a photo of a page in a book using their smartphone camera.

[0538] 2. The application on the smartphone sends this image data to the server.

[0539] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0540] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0541] 5. The server sends the generated voice data to the smartphone.

[0542] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0543] Examples of prompt statements

[0544] Below are some examples of prompts for generative AI models:

[0545] Example prompt sentence:

[0546] "Hello, Model. I'm developing a system to allow the visually impaired to hear printed book pages aloud. Could you please walk me through the steps a user takes a photo of a book page with their smartphone camera and then converts the text into speech and plays it back?"

[0547] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to the visually impaired and busy people.

[0548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0549] Step 1: Image acquisition

[0550] The user takes a picture of the printed media using the device's camera function. When the user presses the capture button, the smartphone's camera app starts up and the captured image is saved in the device's internal storage.

[0551] Input: Print media (books, newspapers, etc.)

[0552] Output: Acquired image data

[0553] Specific operation: The user opens the camera app, frames the target print, and takes a photo. The image data is temporarily saved on the device.

[0554] Step 2: Send image data

[0555] The device sends the acquired image data to the server via the network, and an application on the smartphone automatically generates an HTTP POST request to upload the image data to the server.

[0556] Input: Acquired image data

[0557] Output: Image data sent to the server

[0558] Specific operation: The application on the device selects the image data and sends it to the server via the Internet.

[0559] Step 3: Extract text from images

[0560] The server analyzes the received image data using an optical character recognition device to extract the text information in the image, then calls OCR software (such as Tesseract OCR or Google Cloud Vision API) to scan the text information in the image and convert it into digital text.

[0561] Input: Image data sent to the server

[0562] Output: Extracted text data

[0563] What happens: The server stores the received data and runs an OCR process to extract text information from the image data.

[0564] Step 4: Convert text to speech

[0565] The server converts the extracted text into voice data using a speech synthesizer. The server uses Google Text-to-Speech or Amazon Polly to convert the text into voice data. It is also possible to adjust the language and accent of the voice according to the user's settings.

[0566] Input: Extracted text data

[0567] Output: Converted audio data

[0568] Specific operation: The server passes the text data to the speech synthesis system to generate audio data. The generated audio data is saved in the specified format (e.g. MP3).

[0569] Step 5: Sending audio data

[0570] The server sends the generated voice data to the terminal via the network, and returns the voice data to the terminal as an HTTP response.

[0571] Input: Converted audio data

[0572] Output: Audio data sent to the device

[0573] Specific operation: The server returns the audio data as an HTTP response, and the device receives it.

[0574] Step 6: Play and save the audio data

[0575] The device stores the received audio data in its internal storage and plays it using the built-in audio player, allowing the user to play the received audio at any time.

[0576] Input: Audio data sent to the device

[0577] Output: Played audio, stored audio data

[0578] Specific operation: The device saves the audio data to the internal storage, and the user operates the audio player to play the audio.

[0579] By performing the above steps, the system of the present invention can provide text information from printed material simply and efficiently by voice.

[0580] (Application example 1)

[0581] 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."

[0582] Conventional systems that convert text information from print media into speech are only useful for the visually impaired and busy people, but they lack the ability to provide audio guidance of product labels and descriptions in physical stores, which causes inconvenience when shopping in physical stores. Visually impaired people in particular often have difficulty selecting and purchasing products. Even for busy people, the inefficiency of gathering information in stores has been an issue.

[0583] 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.

[0584] In this invention, the server includes means for capturing an image of an actual product using a photographing device, means for transmitting the captured image data to an information processing device via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to a terminal via the network, means for playing the returned speech data on the terminal, and means for providing audio guidance of product labels and descriptions in a store, thereby enabling visually impaired people and busy people to easily shop in a physical store.

[0585] An "imaging device" is a hardware device for capturing images of real objects.

[0586] "Image data" refers to image information of an actual object captured by a photographing device.

[0587] A "network" is a communication means for sending and receiving data between a terminal and a server.

[0588] An "information processing device" is a device that functions as a server and processes data.

[0589] An "optical character recognition device" is a device for extracting text from image data.

[0590] A "speech synthesizer" is a device for converting extracted text into speech data.

[0591] A "terminal" is a device that plays back the audio data returned from the server, and includes smartphones and tablets.

[0592] "Product label" refers to the information label affixed to a product in a physical store.

[0593] "Description" refers to the text information that describes a product or service in a physical store.

[0594] "Voice guidance means" is a function that informs the user of information on product labels and descriptions through voice.

[0595] System Overview

[0596] The system of this invention aims to make shopping in brick-and-mortar stores easier for visually impaired people and busy people. The system consists of the following elements:

[0597] Hardware and software used

[0598] Smartphone cameras as photographic devices

[0599] Internet connection as a network

[0600] Server as an information processing device

[0601] Tesseract OCR as an optical character recognizer

[0602] Google Cloud Text-to-Speech API as a speech synthesizer

[0603] Smartphones as devices

[0604] System Operation

[0605] The operation of the system involves the following steps:

[0606] 1. Image capture: The user uses the smartphone camera to take an image of the product label or description.

[0607] 2. Image transmission: The smartphone transmits the captured image data to a server via the Internet.

[0608] 3. Character Recognition: The server uses Tesseract OCR to extract character information from the received image data.

[0609] 4. Speech conversion: The extracted text data is converted to audio data using the Google Cloud Text-to-Speech API.

[0610] 5. Voice data transmission: The converted voice data is sent back to the smartphone via the network.

[0611] 6. Audio playback: The smartphone plays the received audio data, allowing the user to check product information and descriptions by voice.

[0612] Specific examples

[0613] As a concrete example, consider the following scenario:

[0614] Imagine a user standing in front of a product shelf in a physical store, taking a picture of the label with their smartphone camera, and the application automatically sends the image to the server.

[0615] The server uses Tesseract OCR to extract text information from the image data, such as "Milk 1L 200 yen." This information is input into the Google Cloud Text-to-Speech API and generated as audio data.

[0616] The voice data is sent to the user's smartphone, and the user can hear the voice guidance, "Milk 1 liter, 200 yen." This example enables visually impaired people and busy people to quickly obtain necessary product information by voice, making shopping in physical stores more convenient.

[0617] Prompt Sentence Examples

[0618] An example prompt is:

[0619] "Please convert the following product information into audio: Milk 1L 200 yen"

[0620] Such a system can obtain product information without relying on vision by obtaining information from product labels and descriptions and providing audio guidance.

[0621] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0622] Step 1:

[0623] A user takes a picture of a product label or description using a smartphone camera. The input is the actual product label or description, and the output is the captured image data. Specific operations include the user launching the application, switching to camera mode, and pressing the capture button.

[0624] Step 2:

[0625] The device sends the captured image data to the server via the Internet. The input here is the image data acquired in step 1, and the output is the image data sent to the server. Specific operations include the device automatically acquiring the image data and uploading it to the server using an HTTP request.

[0626] Step 3:

[0627] The server uses Tesseract OCR to extract text information from image data received by the server. The input is the image data sent to the server, and the output is the extracted text data. Specific operations include the server processing the received data and calling the OCR engine to perform character recognition.

[0628] Step 4:

[0629] The server converts the extracted text data into speech data using the Google Cloud Text-to-Speech API. The input here is the text data extracted in step 3, and the output is the generated speech data. Specific operations include the server calling the Text-to-Speech API to input the text data and perform speech synthesis.

[0630] Step 5:

[0631] The server sends the audio data to the terminal via the network. The input here is the audio data generated in step 4, and the output is the audio data sent to the terminal. Specific operations include the server returning the generated audio data to the terminal in an HTTP response.

[0632] Step 6:

[0633] The terminal plays the received audio data. The input is the audio data sent from the server, and the output is the audio information played back to the user. Specific operations include the terminal's audio player decoding the audio data and playing it through the speaker.

[0634] In this way, by explaining the specific operations and inputs / outputs of each step, you can gain a detailed understanding of the overall system and how it operates.

[0635] 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.

[0636] The present invention relates to a system for converting text information from print media into speech for visually impaired people and busy people, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system will be described below.

[0637] System Overview

[0638] The system of the present invention comprises a terminal, a network, a server, and an emotion engine.

[0639] 1. Device:

[0640] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet is used.

[0641] It has the function of sending the acquired image data to a server via a network.

[0642] It has a playback means for playing back the voice data returned from the server, and is also equipped with an emotion engine that has the function of recognizing emotions from the user's facial expressions and voice.

[0643] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[0644] 2. Network:

[0645] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[0646] 3. Server:

[0647] A device that processes image data received from a terminal.

[0648] An optical character recognizer is used to extract text from images.

[0649] It is equipped with a speech synthesizer that converts the extracted text into speech data.

[0650] When synthesizing speech, it has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[0651] 4. Emotion Engine:

[0652] It is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice.

[0653] The emotion engine can transmit the acquired emotion data to the server and reflect it in the generation of voice data.

[0654] Program processing explanation

[0655] The specific program processing of this system will be explained below in order.

[0656] Image acquisition and transmission

[0657] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[0658] Extracting text from images

[0659] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[0660] Text-to-speech

[0661] The server converts the extracted text into voice data using a speech synthesizer, and can adjust the language and accent of the voice according to the user's settings. Furthermore, the server can adjust the voice tone and speed based on the user's emotional data transmitted from the device.

[0662] Sending and playing audio data

[0663] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[0664] Functions and Use of Emotion Engine

[0665] The emotion engine is installed on the device and analyzes the user's facial expressions and voice in real time. The emotion data is sent to the server and reflected in the voice synthesis. For example, if the user is tired, a calm tone of voice is generated. On the other hand, if the user is happy, a bright tone of voice is generated.

[0666] Specific examples

[0667] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0668] 1. The user takes a photo of a page in a book using their smartphone camera.

[0669] 2. The application on the smartphone sends this image data to the server.

[0670] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0671] 4. The server uses speech synthesis technology to convert this text into speech, adjusting the tone and speed of the speech based on data from the emotion engine.

[0672] 5. The server sends the generated voice data to the smartphone.

[0673] 6. The smartphone plays the received audio data, and the user hears the audio saying "Hello, world." At this time, an audio tone is played that corresponds to the user's emotional state.

[0674] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] The user uses the device's camera to take a picture of the printed text, and the device stores the captured image data in its memory.

[0678] Step 2:

[0679] The device sends the saved image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[0680] Step 3:

[0681] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[0682] Step 4:

[0683] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information from the image. The OCR engine analyzes the image and generates a string of characters.

[0684] Step 5:

[0685] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[0686] Step 6:

[0687] The server adjusts the voice tone and speed based on the user's emotional data sent from the device, so that the voice data is appropriate for the user's emotional state.

[0688] Step 7:

[0689] The server saves the generated audio data, generates a path for the saved audio file, and returns the path to the device.

[0690] Step 8:

[0691] The terminal receives the path of the audio file returned from the server, and uses this path to download the audio file from the server.

[0692] Step 9:

[0693] After the download is complete, the terminal uses the playback means to play the received audio file, and the terminal uses the audio playback function to play the audio data to the user.

[0694] Step 10:

[0695] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[0696] Step 11:

[0697] The emotion engine analyzes the user's facial expressions and voice in real time to obtain emotional data, which is then sent to the server and reflected in the next speech synthesis.

[0698] In this way, the system provides a more personalized audio experience by providing voice data that reflects the user's emotions, and it can significantly improve information access for the visually impaired and busy people.

[0699] Example 2

[0700] 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."

[0701] In modern society, visually impaired people and busy people need efficient and intuitive ways to obtain information from print media. However, conventional systems cannot generate speech that takes the user's emotions into account, making it difficult to improve the user experience. Furthermore, the process of information acquisition and speech generation is limited to a single function, resulting in a lack of flexibility. To solve these problems, a technology that synthesizes speech based on the user's emotions is needed.

[0702] 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 means for capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, means for playing the returned speech data on the terminal, and an emotion engine for recognizing the user's emotion and adjusting the speech data based on the emotion. This allows visually impaired people and busy people to efficiently obtain information obtained from print media by speech, and the tone and speed of the speech reflect the user's emotion, enabling a more intuitive and comfortable user experience.

[0703] An "imaging device" is a device for capturing an image of a print medium, and examples include smartphones and tablets.

[0704] A "network" is a communication means for sending and receiving data between a terminal and a server, and may be an internet line or a wireless network.

[0705] An "optical character recognition device" is a technology for extracting text information from image data, and OCR technology is one such example.

[0706] A "speech synthesizer" is a technology for converting extracted text into audio data, and includes text-to-speech systems and speech synthesis engines.

[0707] A "server" is a device that processes received image data and performs text extraction and voice synthesis.

[0708] A "terminal" is a device that includes a photographing device, transmits image data to a server, and plays back received audio data.

[0709] An "emotion engine" is a technology that analyzes a user's facial expressions and voice to recognize their emotions and reflects that data in speech synthesis.

[0710] This invention relates to a system that converts text information from print media into speech for visually impaired people and busy people, and also combines it with an emotion engine that recognizes the user's emotions. Details of how to specifically implement this system are described below.

[0711] System configuration

[0712] This system consists of terminals, a network, a server, and an emotion engine.

[0713] Device:

[0714] The terminal is a device that captures images of print media using a photographing device. Specific examples include smartphones and tablets. The terminal has the function of sending the captured image data to a server via a network and has a playback means for playing back the voice data returned from the server. It also has an emotion engine and the function of recognizing emotions from the user's facial expressions and voice. It also has a storage means for saving the voice data as needed so that it can be played back later.

[0715] network:

[0716] A network is a communication means for sending and receiving data between a terminal and a server, and can be an internet line or a wireless network.

[0717] server:

[0718] The server processes image data received from the device. It uses optical character recognition (OCR) to extract text from the image and then includes a speech synthesizer that converts the text into speech data. During speech synthesis, the server also has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[0719] Emotion Engine:

[0720] The emotion engine is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice. The emotion engine sends the acquired emotion data to the server, which can then be reflected in the generated voice data.

[0721] Specific examples

[0722] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0723] 1. The user takes a photo of a page in a book using their smartphone camera.

[0724] 2. The application on the smartphone sends this image data to the server.

[0725] 3. The server extracts text information from the image using OCR technology (e.g., Tesseract), e.g., the text "Hello, World" is extracted.

[0726] 4. The server converts this text into voice data using speech synthesis technology (e.g., Google Text-to-Speech or OpenAI's speech synthesis library), and adjusts the voice tone and speed based on the emotion data sent from the device.

[0727] 5. The server sends the generated voice data to the smartphone.

[0728] 6. The smartphone plays the received audio data, and the user hears the message "Hello, world" in a voice that corresponds to the user's emotional state.

[0729] Examples of prompt statements

[0730] Below are some example prompts for a generative AI model:

[0731] "Write a program to design a system that generates speech based on the user's emotional data. The system should be able to adjust the tone and speed of the speech depending on the user's emotion. Explain how the user can use their device to send images of printed media to a server, which will then extract text from the images and convert it into speech."

[0732] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[0733] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0734] Step 1:

[0735] The user acquires an image of the print medium using a terminal.

[0736] The user launches the camera app on their device (such as a smartphone) and takes a picture of the page of the book or document they want to read. Specifically, they capture the image by framing the image appropriately and pressing the shutter button. The input is an image of the printed media, and the output is the captured image data.

[0737] Step 2:

[0738] The terminal transmits the image data to the server.

[0739] The device sends the captured image data to a server in the background. An application in the smartphone processes the image data and sends it to a specified server address via an Internet connection (Wi-Fi or mobile data). Specifically, this involves the user tapping the "Send" button. The input is the captured image data, and the output is the image data sent to the server.

[0740] Step 3:

[0741] The server extracts the text from the image data.

[0742] The server analyzes the received image data and extracts text using optical character recognition (OCR) technology. Character recognition is performed using an OCR library such as Tesseract to obtain text information from the image data. For example, the text "Hello, world" is extracted from the image data. The input is the image data sent to the server, and the output is the extracted text data.

[0743] Step 4:

[0744] The server converts the text into audio data.

[0745] The server converts the extracted text into voice data using a speech synthesizer. It uses Google Text-to-Speech or OpenAI's speech synthesis library to convert text to voice. Furthermore, it adjusts the voice tone and speed based on the user's emotional data sent from the device. Specifically, the server calls the speech synthesis API to brighten or calm the tone based on the user's emotional state. The input is the extracted text data and emotional data, and the output is the adjusted voice data.

[0746] Step 5:

[0747] The server sends the audio data to the terminal.

[0748] The server sends the generated voice data to the terminal via the network. Specifically, the server creates the generated voice file, assembles the file into data packets for transmission to the terminal, and transmits them via the network. The input is the adjusted voice data, and the output is the voice data transmitted to the terminal.

[0749] Step 6:

[0750] The device plays the audio data.

[0751] The terminal plays the received audio data using a playback means (speaker or headphones). The user can listen to the audio by pressing the play button in the application. It is also possible to save the audio data via a storage means and play it later. Specifically, this includes operations for the terminal to load the received audio data and issue a play command. The input is the audio data sent to the terminal, and the output is the played audio.

[0752] Step 7:

[0753] The emotion engine recognizes and reflects the user's emotions.

[0754] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates the data. The device sends this emotion data to the server, which then reflects this data when synthesizing speech. Specifically, when the user faces the smartphone camera, the device performs facial recognition and voice analysis, generates emotion data, and sends it to the server. The input is the user's facial expressions and voice data, and the output is emotion data.

[0755] (Application example 2)

[0756] 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."

[0757] Visually impaired people and busy people have difficulty reading restaurant and food delivery menus. Furthermore, if the audio information provided is not tailored to the user's emotional state, it can be stressful to understand the information and experience it is used. Therefore, there is a need for a system that delivers printed text information in audio that adapts to the user's emotional state.

[0758] The identification process by the identification 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 capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, an emotion analysis engine for analyzing a user's emotion and adjusting the tone and speed of speech synthesis based on the analysis results, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, and means for playing the returned speech data on the terminal. This makes it possible to provide text information on a print medium in a voice that corresponds to the user's emotion.

[0759] A "photography device" is a device for capturing an image of a print medium, such as a camera mounted on a smartphone or tablet.

[0760] "Image data" refers to image information of a print medium captured by a photographing device.

[0761] A "network" is a communication means for sending and receiving data between a terminal and a server, and includes the Internet and wireless networks.

[0762] A "server" is a device that analyzes image data received from a terminal and performs the necessary processing.

[0763] "Optical character recognition device" is a technology for extracting text information from image data, and generally refers to OCR (Optical Character Recognition) technology.

[0764] "Text" is written information in digital form that has been extracted by an optical character recognition device.

[0765] A "speech synthesizer" is a device equipped with technology for converting text information into voice data. For example, it includes text-to-speech technology.

[0766] "Voice data" refers to digital data in a voice format generated by a voice synthesizer.

[0767] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state and output the results.

[0768] A "terminal" is a device that has a camera, audio playback function, and network communication function, and includes smartphones and tablets.

[0769] The "playback means" is hardware or software for playing back audio data received by the terminal.

[0770] System Overview

[0771] This invention is a system for converting text information from print media into speech for visually impaired people and busy people. The system also combines an emotion analysis engine that recognizes the user's emotions and adjusts the tone and speed of the speech accordingly. Specific embodiments of the system are described below.

[0772] Hardware and Software Configuration

[0773] Terminal

[0774] A device is a device that includes a camera, such as a smartphone or tablet. A device has the following functions:

[0775] A function to capture images of print media using a photographic device

[0776] A function to send acquired image data to a server via a network

[0777] A function to play back audio data returned from the server

[0778] Equipped with an emotion analysis engine that analyzes emotions from the user's facial expressions and voice

[0779] A storage method that allows audio data to be saved and played back later if necessary

[0780] server

[0781] The server has the following capabilities:

[0782] A function that analyzes image data received from a device using optical character recognition (OCR) technology and extracts text information.

[0783] A speech synthesizer that converts extracted text into speech data

[0784] Ability to adjust voice tone and speed based on user emotion data

[0785] network

[0786] A communication method for sending and receiving data between a terminal and a server, including the Internet and wireless networks.

[0787] Program processing overview

[0788] The device first captures an image of the print media using the smartphone's camera. The image data is then sent to a server via a network. The server uses OCR technology to extract text information from the received image data. The extracted text is then converted into voice data using a voice synthesizer. When synthesizing the voice, the tone and speed of the voice are adjusted based on the user's emotional data sent from the device. The generated voice data is sent to the device via a network, where it is played back.

[0789] Specific examples

[0790] We will explain the series of processes that occur when a user takes a photo of a restaurant menu with their smartphone camera and listens to the menu contents aloud.

[0791] 1. The user takes a photo of a restaurant menu using their smartphone camera.

[0792] 2. The application on the smartphone sends this image data to the server.

[0793] 3. The server uses OCR technology to extract text information from the image, such as "We have sushi, tempura, and eel."

[0794] 4. The server converts this text to speech using speech synthesis technology, adjusting the tone and speed of the speech based on data from the sentiment analysis engine.

[0795] 5. The server sends the generated voice data to the smartphone.

[0796] 6. The smartphone plays the received audio data, and the user can hear the menu contents aloud. For example, if the user is happy, the audio will be played in a bright tone.

[0797] Prompt Sentence Examples

[0798] Create an audio file that reads the following text aloud, assuming the user's emotion is "joy."

[0799] Text: "We have sushi, tempura, and eel. Which would you like to eat?"

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

[0801] Step 1:

[0802] A user uses the smartphone camera to take an image of a printed medium (e.g., a restaurant menu).

[0803] Input: User-taken image of printed material

[0804] Output: Captured image data file

[0805] Specific operation: The user opens the camera app on their smartphone, points it at the target print medium, and presses the shutter button to take a picture.

[0806] Step 2:

[0807] The terminal transmits the acquired image data to the server.

[0808] Input: Captured image data

[0809] Output: Image data sent to the server

[0810] Specific operation: An application on the smartphone automatically selects the captured image files and sends them to a specified server address via the Internet.

[0811] Step 3:

[0812] The server extracts text information from the received image data using an optical character recognition device.

[0813] Input: Image data sent to the server

[0814] Output: Extracted text information

[0815] What it does: OCR software on the server analyzes the image data and extracts the characters in the print media as digital text, for example, "We have sushi, tempura, and eel."

[0816] Step 4:

[0817] The server converts the extracted text information into audio data.

[0818] Input: Extracted text information

[0819] Output: Audio data file

[0820] What it does: Speech synthesis software on the server analyzes the text information and converts it into spoken audio, adjusting for the language and accent of the audio, if any.

[0821] Step 5:

[0822] The device uses an emotion analysis engine to analyze the user's emotions and sends the data to the server.

[0823] Input: User facial and voice data

[0824] Output: Sentiment analysis data

[0825] Specific operation: The emotion analysis engine analyzes the user's facial expressions and tone of voice in real time, generates emotion data (e.g., "happiness," "sadness," etc.) based on that, and sends it to the server.

[0826] Step 6:

[0827] The server adjusts the tone and speed of the voice based on the emotion analysis data.

[0828] Input: Audio data file, emotion analysis data

[0829] Output: Adjusted audio data file

[0830] What it does: The server's speech synthesis software uses the emotion analysis data to appropriately adjust the tone and speed of the speech. For example, if the user is "happy," a brighter tone will be generated.

[0831] Step 7:

[0832] The server transmits the generated voice data to the terminal.

[0833] Input: Adjusted audio data file

[0834] Output: Audio data sent to the device

[0835] Specific operation: The server sends an audio data file to the terminal via the network.

[0836] Step 8:

[0837] The terminal plays the concluded audio data.

[0838] Input: Audio data sent to the device

[0839] Output: Played audio

[0840] Specific operation: The smartphone's audio playback function analyzes the received audio data and plays it back through the speaker, allowing the user to hear the menu contents aloud.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] [Third embodiment]

[0845] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0846] 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.

[0847] 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).

[0848] 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.

[0849] 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.

[0850] 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).

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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."

[0857] The present invention relates to a system for converting text information on a print medium into speech for the visually impaired and busy people. Specific embodiments of this system will be described below.

[0858] System Overview

[0859] The system of the present invention is mainly composed of a terminal, a network, and a server.

[0860] 1. Device:

[0861] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet device can be used.

[0862] It has the function of sending the acquired images to a server via a network.

[0863] It has a reproducing means for reproducing the audio data returned from the server.

[0864] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[0865] 2. Network:

[0866] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[0867] 3. Server:

[0868] A device that processes image data received from a terminal.

[0869] An optical character recognizer is used to extract text from images.

[0870] A speech synthesizer is used to convert the extracted text into speech data, which is then sent back to the terminal via the network.

[0871] Program processing explanation

[0872] The specific program processing of this system will be explained below in order.

[0873] Image acquisition and transmission

[0874] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[0875] Extracting text from images

[0876] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[0877] Text-to-speech

[0878] The server converts the extracted text into voice data using a speech synthesizer. At this time, the language and accent of the voice can be adjusted according to the user's settings. This allows users to receive text information in a voice that suits them best.

[0879] Sending and playing audio data

[0880] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[0881] Specific examples

[0882] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0883] 1. The user takes a photo of a page in a book using their smartphone camera.

[0884] 2. The application on the smartphone sends this image data to the server.

[0885] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0886] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0887] 5. The server sends the generated voice data to the smartphone.

[0888] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0889] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to visually impaired people and busy people.

[0890] The processing flow will be explained below.

[0891] Step 1:

[0892] The user takes a photo of the printed text using the device's camera function. The device acquires the image data through the camera and stores the image in memory.

[0893] Step 2:

[0894] The device sends the stored image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[0895] Step 3:

[0896] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[0897] Step 4:

[0898] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information within the image, where an OCR engine analyzes the image and generates a string of characters.

[0899] Step 5:

[0900] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[0901] Step 6:

[0902] The server converts the generated audio data into a file format and saves it. A path for the saved audio file is generated.

[0903] Step 7:

[0904] The server returns the path of the saved audio file to the device, which uses this path to download the audio file from the server.

[0905] Step 8:

[0906] The terminal stores the downloaded audio file in the terminal for playback, and uses the audio playback function of the terminal to play the audio data to the user.

[0907] Step 9:

[0908] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[0909] In this way, users can easily convert printed text information into speech and retrieve it efficiently, greatly improving information access for the visually impaired and busy people.

[0910] Example 1

[0911] 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."

[0912] Visually impaired people and busy people face challenges in easily and efficiently obtaining text information from printed materials through audio. Conventional systems require a complex process of converting image data to text and then converting that text to audio, making operation cumbersome. Furthermore, the lack of a means to play or save audio data limits the user experience.

[0913] 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.

[0914] In this invention, the server includes means for extracting text from the image data using an optical character recognition device, a speech synthesis device for converting the extracted text into speech, and means for returning the converted speech data to the terminal via the network. This allows users to easily obtain text information from printed materials by speech and save and play the speech data, improving convenience for visually impaired people and busy people.

[0915] An "imaging device" is a device for capturing an image of a print medium, and includes, for example, a camera or the camera function of a smartphone.

[0916] "Image data" is digital data of an image of a print medium captured by a photographing device.

[0917] "Network" refers to the means of communication for sending and receiving data between a terminal and a server, including the Internet and wireless communication.

[0918] The "server" is a device that analyzes received image data using an optical character recognition device, extracts text information, and converts it into voice data.

[0919] An "optical character recognition device" is a technical device that extracts character information from image data and uses OCR technology.

[0920] "Text" is character information extracted from image data by an optical character recognition device.

[0921] A "speech synthesizer" is a technical device that converts extracted text into speech data, and uses speech synthesis technology.

[0922] "Voice data" refers to digital data that is generated by a voice synthesizer and can be reproduced as voice.

[0923] A "terminal" is a device used by a user, which has the function of playing or saving audio data.

[0924] "Internal storage" refers to a storage device installed within a terminal for storing digital data.

[0925] An "audio player" is software or hardware installed on a terminal for playing audio data.

[0926] The present invention relates to a system for converting text information from print media into speech, aimed at visually impaired people and busy people. This system is mainly composed of a terminal, a network, and a server.

[0927] Hardware and software used

[0928] Terminal

[0929] The terminals used are smartphones or tablet devices. The terminals are equipped with a camera function so that users can take pictures of the printed materials. The terminals also have a communication means for sending the acquired image data to a server via a network.

[0930] network

[0931] The network uses the Internet or wireless communication, which allows data to be sent and received efficiently between the terminal and the server.

[0932] server

[0933] The server is equipped with the following hardware and software:

[0934] Optical character recognition (OCR) devices: For example, using Tesseract OCR or Google Cloud Vision API to extract text information from image data.

[0935] Speech synthesizer: For example, use Google Text-to-Speech or Amazon Polly to convert the extracted text into audio data.

[0936] Program processing

[0937] Image acquisition and transmission

[0938] The user takes a picture of the printed text using the camera function of the device, and the device sends the image data to a server via the Internet or wireless communication.

[0939] Extracting text from images

[0940] The server analyzes the received image data using an optical character recognition device to extract text information from the image. For example, the server receives the image data and calls Tesseract OCR or Google Cloud Vision API to scan the text information in the image and convert it into digital text.

[0941] Text-to-speech

[0942] The server then converts the extracted text into audio data using a speech synthesizer, such as Google Text-to-Speech or Amazon Polly, and saves the resulting audio data in a specified format (e.g., MP3).

[0943] Sending and playing audio data

[0944] The server transmits the generated audio data to the device via the network. The device that receives the data stores the audio data in its internal storage and plays it back using its built-in audio player.

[0945] Specific examples

[0946] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[0947] 1. The user takes a photo of a page in a book using their smartphone camera.

[0948] 2. The application on the smartphone sends this image data to the server.

[0949] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[0950] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[0951] 5. The server sends the generated voice data to the smartphone.

[0952] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[0953] Examples of prompt statements

[0954] Below are some examples of prompts for generative AI models:

[0955] Example prompt sentence:

[0956] "Hello, Model. I'm developing a system to allow the visually impaired to hear printed book pages aloud. Could you please walk me through the steps a user takes a photo of a book page with their smartphone camera and then converts the text into speech and plays it back?"

[0957] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to the visually impaired and busy people.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1: Image acquisition

[0960] The user takes a picture of the printed media using the device's camera function. When the user presses the capture button, the smartphone's camera app starts up and the captured image is saved in the device's internal storage.

[0961] Input: Print media (books, newspapers, etc.)

[0962] Output: Acquired image data

[0963] Specific operation: The user opens the camera app, frames the target print, and takes a photo. The image data is temporarily saved on the device.

[0964] Step 2: Send image data

[0965] The device sends the acquired image data to the server via the network, and an application on the smartphone automatically generates an HTTP POST request to upload the image data to the server.

[0966] Input: Acquired image data

[0967] Output: Image data sent to the server

[0968] Specific operation: The application on the device selects the image data and sends it to the server via the Internet.

[0969] Step 3: Extract text from images

[0970] The server analyzes the received image data using an optical character recognition device to extract the text information in the image, then calls OCR software (such as Tesseract OCR or Google Cloud Vision API) to scan the text information in the image and convert it into digital text.

[0971] Input: Image data sent to the server

[0972] Output: Extracted text data

[0973] What happens: The server stores the received data and runs an OCR process to extract text information from the image data.

[0974] Step 4: Convert text to speech

[0975] The server converts the extracted text into voice data using a speech synthesizer. The server uses Google Text-to-Speech or Amazon Polly to convert the text into voice data. It is also possible to adjust the language and accent of the voice according to the user's settings.

[0976] Input: Extracted text data

[0977] Output: Converted audio data

[0978] Specific operation: The server passes the text data to the speech synthesis system to generate audio data. The generated audio data is saved in the specified format (e.g. MP3).

[0979] Step 5: Sending audio data

[0980] The server sends the generated voice data to the terminal via the network, and returns the voice data to the terminal as an HTTP response.

[0981] Input: Converted audio data

[0982] Output: Audio data sent to the device

[0983] Specific operation: The server returns the audio data as an HTTP response, and the device receives it.

[0984] Step 6: Play and save the audio data

[0985] The device stores the received audio data in its internal storage and plays it using the built-in audio player, allowing the user to play the received audio at any time.

[0986] Input: Audio data sent to the device

[0987] Output: Played audio, stored audio data

[0988] Specific operation: The device saves the audio data to the internal storage, and the user operates the audio player to play the audio.

[0989] By performing the above steps, the system of the present invention can provide text information from printed material simply and efficiently by voice.

[0990] (Application example 1)

[0991] 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."

[0992] Conventional systems that convert text information from print media into speech are only useful for the visually impaired and busy people, but they lack the ability to provide audio guidance of product labels and descriptions in physical stores, which causes inconvenience when shopping in physical stores. Visually impaired people in particular often have difficulty selecting and purchasing products. Even for busy people, the inefficiency of gathering information in stores has been an issue.

[0993] 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.

[0994] In this invention, the server includes means for capturing an image of an actual product using a photographing device, means for transmitting the captured image data to an information processing device via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to a terminal via the network, means for playing the returned speech data on the terminal, and means for providing audio guidance of product labels and descriptions in a store, thereby enabling visually impaired people and busy people to easily shop in a physical store.

[0995] An "imaging device" is a hardware device for capturing images of real objects.

[0996] "Image data" refers to image information of an actual object captured by a photographing device.

[0997] A "network" is a communication means for sending and receiving data between a terminal and a server.

[0998] An "information processing device" is a device that functions as a server and processes data.

[0999] An "optical character recognition device" is a device for extracting text from image data.

[1000] A "speech synthesizer" is a device for converting extracted text into speech data.

[1001] A "terminal" is a device that plays back the audio data returned from the server, and includes smartphones and tablets.

[1002] "Product label" refers to the information label affixed to a product in a physical store.

[1003] "Description" refers to the text information that describes a product or service in a physical store.

[1004] "Voice guidance means" is a function that informs the user of information on product labels and descriptions through voice.

[1005] System Overview

[1006] The system of this invention aims to make shopping in brick-and-mortar stores easier for visually impaired people and busy people. The system consists of the following elements:

[1007] Hardware and software used

[1008] Smartphone cameras as photographic devices

[1009] Internet connection as a network

[1010] Server as an information processing device

[1011] Tesseract OCR as an optical character recognizer

[1012] Google Cloud Text-to-Speech API as a speech synthesizer

[1013] Smartphones as devices

[1014] System Operation

[1015] The operation of the system involves the following steps:

[1016] 1. Image capture: The user uses the smartphone camera to take an image of the product label or description.

[1017] 2. Image transmission: The smartphone transmits the captured image data to a server via the Internet.

[1018] 3. Character Recognition: The server uses Tesseract OCR to extract character information from the received image data.

[1019] 4. Speech conversion: The extracted text data is converted to audio data using the Google Cloud Text-to-Speech API.

[1020] 5. Voice data transmission: The converted voice data is sent back to the smartphone via the network.

[1021] 6. Audio playback: The smartphone plays the received audio data, allowing the user to check product information and descriptions by voice.

[1022] Specific examples

[1023] As a concrete example, consider the following scenario:

[1024] Imagine a user standing in front of a product shelf in a physical store, taking a picture of the label with their smartphone camera, and the application automatically sends the image to the server.

[1025] The server uses Tesseract OCR to extract text information from the image data, such as "Milk 1L 200 yen." This information is input into the Google Cloud Text-to-Speech API and generated as audio data.

[1026] The voice data is sent to the user's smartphone, and the user can hear the voice guidance, "Milk 1 liter, 200 yen." This example enables visually impaired people and busy people to quickly obtain necessary product information by voice, making shopping in physical stores more convenient.

[1027] Prompt Sentence Examples

[1028] An example prompt is:

[1029] "Please convert the following product information into audio: Milk 1L 200 yen"

[1030] Such a system can obtain product information without relying on vision by obtaining information from product labels and descriptions and providing audio guidance.

[1031] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1032] Step 1:

[1033] A user takes a picture of a product label or description using a smartphone camera. The input is the actual product label or description, and the output is the captured image data. Specific operations include the user launching the application, switching to camera mode, and pressing the capture button.

[1034] Step 2:

[1035] The device sends the captured image data to the server via the Internet. The input here is the image data acquired in step 1, and the output is the image data sent to the server. Specific operations include the device automatically acquiring the image data and uploading it to the server using an HTTP request.

[1036] Step 3:

[1037] The server uses Tesseract OCR to extract text information from image data received by the server. The input is the image data sent to the server, and the output is the extracted text data. Specific operations include the server processing the received data and calling the OCR engine to perform character recognition.

[1038] Step 4:

[1039] The server converts the extracted text data into speech data using the Google Cloud Text-to-Speech API. The input here is the text data extracted in step 3, and the output is the generated speech data. Specific operations include the server calling the Text-to-Speech API to input the text data and perform speech synthesis.

[1040] Step 5:

[1041] The server sends the audio data to the terminal via the network. The input here is the audio data generated in step 4, and the output is the audio data sent to the terminal. Specific operations include the server returning the generated audio data to the terminal in an HTTP response.

[1042] Step 6:

[1043] The terminal plays the received audio data. The input is the audio data sent from the server, and the output is the audio information played back to the user. Specific operations include the terminal's audio player decoding the audio data and playing it through the speaker.

[1044] In this way, by explaining the specific operations and inputs / outputs of each step, you can gain a detailed understanding of the overall system and how it operates.

[1045] 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.

[1046] The present invention relates to a system for converting text information from print media into speech for visually impaired people and busy people, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system will be described below.

[1047] System Overview

[1048] The system of the present invention comprises a terminal, a network, a server, and an emotion engine.

[1049] 1. Device:

[1050] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet is used.

[1051] It has the function of sending the acquired image data to a server via a network.

[1052] It has a playback means for playing back the voice data returned from the server, and is also equipped with an emotion engine that has the function of recognizing emotions from the user's facial expressions and voice.

[1053] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[1054] 2. Network:

[1055] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[1056] 3. Server:

[1057] A device that processes image data received from a terminal.

[1058] An optical character recognizer is used to extract text from images.

[1059] It is equipped with a speech synthesizer that converts the extracted text into speech data.

[1060] When synthesizing speech, it has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[1061] 4. Emotion Engine:

[1062] It is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice.

[1063] The emotion engine can transmit the acquired emotion data to the server and reflect it in the generation of voice data.

[1064] Program processing explanation

[1065] The specific program processing of this system will be explained below in order.

[1066] Image acquisition and transmission

[1067] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[1068] Extracting text from images

[1069] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[1070] Text-to-speech

[1071] The server converts the extracted text into voice data using a speech synthesizer, and can adjust the language and accent of the voice according to the user's settings. Furthermore, the server can adjust the voice tone and speed based on the user's emotional data transmitted from the device.

[1072] Sending and playing audio data

[1073] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[1074] Functions and Use of Emotion Engine

[1075] The emotion engine is installed on the device and analyzes the user's facial expressions and voice in real time. The emotion data is sent to the server and reflected in the voice synthesis. For example, if the user is tired, a calm tone of voice is generated. On the other hand, if the user is happy, a bright tone of voice is generated.

[1076] Specific examples

[1077] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1078] 1. The user takes a photo of a page in a book using their smartphone camera.

[1079] 2. The application on the smartphone sends this image data to the server.

[1080] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[1081] 4. The server uses speech synthesis technology to convert this text into speech, adjusting the tone and speed of the speech based on data from the emotion engine.

[1082] 5. The server sends the generated voice data to the smartphone.

[1083] 6. The smartphone plays the received audio data, and the user hears the audio saying "Hello, world." At this time, an audio tone is played that corresponds to the user's emotional state.

[1084] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[1085] The processing flow will be explained below.

[1086] Step 1:

[1087] The user uses the device's camera to take a picture of the printed text, and the device stores the captured image data in its memory.

[1088] Step 2:

[1089] The device sends the saved image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[1090] Step 3:

[1091] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[1092] Step 4:

[1093] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information from the image. The OCR engine analyzes the image and generates a string of characters.

[1094] Step 5:

[1095] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[1096] Step 6:

[1097] The server adjusts the voice tone and speed based on the user's emotional data sent from the device, so that the voice data is appropriate for the user's emotional state.

[1098] Step 7:

[1099] The server saves the generated audio data, generates a path for the saved audio file, and returns the path to the device.

[1100] Step 8:

[1101] The terminal receives the path of the audio file returned from the server, and uses this path to download the audio file from the server.

[1102] Step 9:

[1103] After the download is complete, the terminal uses the playback means to play the received audio file, and the terminal uses the audio playback function to play the audio data to the user.

[1104] Step 10:

[1105] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[1106] Step 11:

[1107] The emotion engine analyzes the user's facial expressions and voice in real time to obtain emotional data, which is then sent to the server and reflected in the next speech synthesis.

[1108] In this way, the system provides a more personalized audio experience by providing voice data that reflects the user's emotions, and it can significantly improve information access for the visually impaired and busy people.

[1109] Example 2

[1110] 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."

[1111] In modern society, visually impaired people and busy people need efficient and intuitive ways to obtain information from print media. However, conventional systems cannot generate speech that takes the user's emotions into account, making it difficult to improve the user experience. Furthermore, the process of information acquisition and speech generation is limited to a single function, resulting in a lack of flexibility. To solve these problems, a technology that synthesizes speech based on the user's emotions is needed.

[1112] 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 means for capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, means for playing the returned speech data on the terminal, and an emotion engine for recognizing the user's emotion and adjusting the speech data based on the emotion. This allows visually impaired people and busy people to efficiently obtain information obtained from print media by speech, and the tone and speed of the speech reflect the user's emotion, enabling a more intuitive and comfortable user experience.

[1113] An "imaging device" is a device for capturing an image of a print medium, and examples include smartphones and tablets.

[1114] A "network" is a communication means for sending and receiving data between a terminal and a server, and may be an internet line or a wireless network.

[1115] An "optical character recognition device" is a technology for extracting text information from image data, and OCR technology is one such example.

[1116] A "speech synthesizer" is a technology for converting extracted text into audio data, and includes text-to-speech systems and speech synthesis engines.

[1117] A "server" is a device that processes received image data and performs text extraction and voice synthesis.

[1118] A "terminal" is a device that includes a photographing device, transmits image data to a server, and plays back received audio data.

[1119] An "emotion engine" is a technology that analyzes a user's facial expressions and voice to recognize their emotions and reflects that data in speech synthesis.

[1120] This invention relates to a system that converts text information from print media into speech for visually impaired people and busy people, and also combines it with an emotion engine that recognizes the user's emotions. Details of how to specifically implement this system are described below.

[1121] System configuration

[1122] This system consists of terminals, a network, a server, and an emotion engine.

[1123] Device:

[1124] The terminal is a device that captures images of print media using a photographing device. Specific examples include smartphones and tablets. The terminal has the function of sending the captured image data to a server via a network and has a playback means for playing back the voice data returned from the server. It also has an emotion engine and the function of recognizing emotions from the user's facial expressions and voice. It also has a storage means for saving the voice data as needed so that it can be played back later.

[1125] network:

[1126] A network is a communication means for sending and receiving data between a terminal and a server, and can be an internet line or a wireless network.

[1127] server:

[1128] The server processes image data received from the device. It uses optical character recognition (OCR) to extract text from the image and then includes a speech synthesizer that converts the text into speech data. During speech synthesis, the server also has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[1129] Emotion Engine:

[1130] The emotion engine is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice. The emotion engine sends the acquired emotion data to the server, which can then be reflected in the generated voice data.

[1131] Specific examples

[1132] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1133] 1. The user takes a photo of a page in a book using their smartphone camera.

[1134] 2. The application on the smartphone sends this image data to the server.

[1135] 3. The server extracts text information from the image using OCR technology (e.g., Tesseract), e.g., the text "Hello, World" is extracted.

[1136] 4. The server converts this text into voice data using speech synthesis technology (e.g., Google Text-to-Speech or OpenAI's speech synthesis library), and adjusts the voice tone and speed based on the emotion data sent from the device.

[1137] 5. The server sends the generated voice data to the smartphone.

[1138] 6. The smartphone plays the received audio data, and the user hears the message "Hello, world" in a voice that corresponds to the user's emotional state.

[1139] Examples of prompt statements

[1140] Below are some example prompts for a generative AI model:

[1141] "Write a program to design a system that generates speech based on the user's emotional data. The system should be able to adjust the tone and speed of the speech depending on the user's emotion. Explain how the user can use their device to send images of printed media to a server, which will then extract text from the images and convert it into speech."

[1142] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[1143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1144] Step 1:

[1145] The user acquires an image of the print medium using a terminal.

[1146] The user launches the camera app on their device (such as a smartphone) and takes a picture of the page of the book or document they want to read. Specifically, they capture the image by framing the image appropriately and pressing the shutter button. The input is an image of the printed media, and the output is the captured image data.

[1147] Step 2:

[1148] The terminal transmits the image data to the server.

[1149] The device sends the captured image data to a server in the background. An application in the smartphone processes the image data and sends it to a specified server address via an Internet connection (Wi-Fi or mobile data). Specifically, this involves the user tapping the "Send" button. The input is the captured image data, and the output is the image data sent to the server.

[1150] Step 3:

[1151] The server extracts the text from the image data.

[1152] The server analyzes the received image data and extracts text using optical character recognition (OCR) technology. Character recognition is performed using an OCR library such as Tesseract to obtain text information from the image data. For example, the text "Hello, world" is extracted from the image data. The input is the image data sent to the server, and the output is the extracted text data.

[1153] Step 4:

[1154] The server converts the text into audio data.

[1155] The server converts the extracted text into voice data using a speech synthesizer. It uses Google Text-to-Speech or OpenAI's speech synthesis library to convert text to voice. Furthermore, it adjusts the voice tone and speed based on the user's emotional data sent from the device. Specifically, the server calls the speech synthesis API to brighten or calm the tone based on the user's emotional state. The input is the extracted text data and emotional data, and the output is the adjusted voice data.

[1156] Step 5:

[1157] The server sends the audio data to the terminal.

[1158] The server sends the generated voice data to the terminal via the network. Specifically, the server creates the generated voice file, assembles the file into data packets for transmission to the terminal, and transmits them via the network. The input is the adjusted voice data, and the output is the voice data transmitted to the terminal.

[1159] Step 6:

[1160] The device plays the audio data.

[1161] The terminal plays the received audio data using a playback means (speaker or headphones). The user can listen to the audio by pressing the play button in the application. It is also possible to save the audio data via a storage means and play it later. Specifically, this includes operations for the terminal to load the received audio data and issue a play command. The input is the audio data sent to the terminal, and the output is the played audio.

[1162] Step 7:

[1163] The emotion engine recognizes and reflects the user's emotions.

[1164] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates the data. The device sends this emotion data to the server, which then reflects this data when synthesizing speech. Specifically, when the user faces the smartphone camera, the device performs facial recognition and voice analysis, generates emotion data, and sends it to the server. The input is the user's facial expressions and voice data, and the output is emotion data.

[1165] (Application example 2)

[1166] 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."

[1167] Visually impaired people and busy people have difficulty reading restaurant and food delivery menus. Furthermore, if the audio information provided is not tailored to the user's emotional state, it can be stressful to understand the information and experience it is used. Therefore, there is a need for a system that delivers printed text information in audio that adapts to the user's emotional state.

[1168] The identification process by the identification 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 capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, an emotion analysis engine for analyzing a user's emotion and adjusting the tone and speed of speech synthesis based on the analysis results, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, and means for playing the returned speech data on the terminal. This makes it possible to provide text information on a print medium in a voice that corresponds to the user's emotion.

[1169] A "photography device" is a device for capturing an image of a print medium, such as a camera mounted on a smartphone or tablet.

[1170] "Image data" refers to image information of a print medium captured by a photographing device.

[1171] A "network" is a communication means for sending and receiving data between a terminal and a server, and includes the Internet and wireless networks.

[1172] A "server" is a device that analyzes image data received from a terminal and performs the necessary processing.

[1173] "Optical character recognition device" is a technology for extracting text information from image data, and generally refers to OCR (Optical Character Recognition) technology.

[1174] "Text" is written information in digital form that has been extracted by an optical character recognition device.

[1175] A "speech synthesizer" is a device equipped with technology for converting text information into voice data. For example, it includes text-to-speech technology.

[1176] "Voice data" refers to digital data in a voice format generated by a voice synthesizer.

[1177] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state and output the results.

[1178] A "terminal" is a device that has a camera, audio playback function, and network communication function, and includes smartphones and tablets.

[1179] The "playback means" is hardware or software for playing back audio data received by the terminal.

[1180] System Overview

[1181] This invention is a system for converting text information from print media into speech for visually impaired people and busy people. The system also combines an emotion analysis engine that recognizes the user's emotions and adjusts the tone and speed of the speech accordingly. Specific embodiments of the system are described below.

[1182] Hardware and Software Configuration

[1183] Terminal

[1184] A device is a device that includes a camera, such as a smartphone or tablet. A device has the following functions:

[1185] A function to capture images of print media using a photographic device

[1186] A function to send acquired image data to a server via a network

[1187] A function to play back audio data returned from the server

[1188] Equipped with an emotion analysis engine that analyzes emotions from the user's facial expressions and voice

[1189] A storage method that allows audio data to be saved and played back later if necessary

[1190] server

[1191] The server has the following capabilities:

[1192] A function that analyzes image data received from a device using optical character recognition (OCR) technology and extracts text information.

[1193] A speech synthesizer that converts extracted text into speech data

[1194] Ability to adjust voice tone and speed based on user emotion data

[1195] network

[1196] A communication method for sending and receiving data between a terminal and a server, including the Internet and wireless networks.

[1197] Program processing overview

[1198] The device first captures an image of the print media using the smartphone's camera. The image data is then sent to a server via a network. The server uses OCR technology to extract text information from the received image data. The extracted text is then converted into voice data using a voice synthesizer. When synthesizing the voice, the tone and speed of the voice are adjusted based on the user's emotional data sent from the device. The generated voice data is sent to the device via a network, where it is played back.

[1199] Specific examples

[1200] We will explain the series of processes that occur when a user takes a photo of a restaurant menu with their smartphone camera and listens to the menu contents aloud.

[1201] 1. The user takes a photo of a restaurant menu using their smartphone camera.

[1202] 2. The application on the smartphone sends this image data to the server.

[1203] 3. The server uses OCR technology to extract text information from the image, such as "We have sushi, tempura, and eel."

[1204] 4. The server converts this text to speech using speech synthesis technology, adjusting the tone and speed of the speech based on data from the sentiment analysis engine.

[1205] 5. The server sends the generated voice data to the smartphone.

[1206] 6. The smartphone plays the received audio data, and the user can hear the menu contents aloud. For example, if the user is happy, the audio will be played in a bright tone.

[1207] Prompt Sentence Examples

[1208] Create an audio file that reads the following text aloud, assuming the user's emotion is "joy."

[1209] Text: "We have sushi, tempura, and eel. Which would you like to eat?"

[1210] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1211] Step 1:

[1212] A user uses the smartphone camera to take an image of a printed medium (e.g., a restaurant menu).

[1213] Input: User-taken image of printed material

[1214] Output: Captured image data file

[1215] Specific operation: The user opens the camera app on their smartphone, points it at the target print medium, and presses the shutter button to take a picture.

[1216] Step 2:

[1217] The terminal transmits the acquired image data to the server.

[1218] Input: Captured image data

[1219] Output: Image data sent to the server

[1220] Specific operation: An application on the smartphone automatically selects the captured image files and sends them to a specified server address via the Internet.

[1221] Step 3:

[1222] The server extracts text information from the received image data using an optical character recognition device.

[1223] Input: Image data sent to the server

[1224] Output: Extracted text information

[1225] What it does: OCR software on the server analyzes the image data and extracts the characters in the print media as digital text, for example, "We have sushi, tempura, and eel."

[1226] Step 4:

[1227] The server converts the extracted text information into audio data.

[1228] Input: Extracted text information

[1229] Output: Audio data file

[1230] What it does: Speech synthesis software on the server analyzes the text information and converts it into spoken audio, adjusting for the language and accent of the audio, if any.

[1231] Step 5:

[1232] The device uses an emotion analysis engine to analyze the user's emotions and sends the data to the server.

[1233] Input: User facial and voice data

[1234] Output: Sentiment analysis data

[1235] Specific operation: The emotion analysis engine analyzes the user's facial expressions and tone of voice in real time, generates emotion data (e.g., "happiness," "sadness," etc.) based on that, and sends it to the server.

[1236] Step 6:

[1237] The server adjusts the tone and speed of the voice based on the emotion analysis data.

[1238] Input: Audio data file, emotion analysis data

[1239] Output: Adjusted audio data file

[1240] What it does: The server's speech synthesis software uses the emotion analysis data to appropriately adjust the tone and speed of the speech. For example, if the user is "happy," a brighter tone will be generated.

[1241] Step 7:

[1242] The server transmits the generated voice data to the terminal.

[1243] Input: Adjusted audio data file

[1244] Output: Audio data sent to the device

[1245] Specific operation: The server sends an audio data file to the terminal via the network.

[1246] Step 8:

[1247] The terminal plays the concluded audio data.

[1248] Input: Audio data sent to the device

[1249] Output: Played audio

[1250] Specific operation: The smartphone's audio playback function analyzes the received audio data and plays it back through the speaker, allowing the user to hear the menu contents aloud.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] [Fourth embodiment]

[1255] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1256] 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.

[1257] 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).

[1258] 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.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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."

[1268] The present invention relates to a system for converting text information on a print medium into speech for the visually impaired and busy people. Specific embodiments of this system will be described below.

[1269] System Overview

[1270] The system of the present invention is mainly composed of a terminal, a network, and a server.

[1271] 1. Device:

[1272] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet device can be used.

[1273] It has the function of sending the acquired images to a server via a network.

[1274] It has a reproducing means for reproducing the audio data returned from the server.

[1275] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[1276] 2. Network:

[1277] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[1278] 3. Server:

[1279] A device that processes image data received from a terminal.

[1280] An optical character recognizer is used to extract text from images.

[1281] A speech synthesizer is used to convert the extracted text into speech data, which is then sent back to the terminal via the network.

[1282] Program processing explanation

[1283] The specific program processing of this system will be explained below in order.

[1284] Image acquisition and transmission

[1285] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[1286] Extracting text from images

[1287] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[1288] Text-to-speech

[1289] The server converts the extracted text into voice data using a speech synthesizer. At this time, the language and accent of the voice can be adjusted according to the user's settings. This allows users to receive text information in a voice that suits them best.

[1290] Sending and playing audio data

[1291] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[1292] Specific examples

[1293] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1294] 1. The user takes a photo of a page in a book using their smartphone camera.

[1295] 2. The application on the smartphone sends this image data to the server.

[1296] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[1297] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[1298] 5. The server sends the generated voice data to the smartphone.

[1299] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[1300] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to visually impaired people and busy people.

[1301] The processing flow will be explained below.

[1302] Step 1:

[1303] The user takes a photo of the printed text using the device's camera function. The device acquires the image data through the camera and stores the image in memory.

[1304] Step 2:

[1305] The device sends the stored image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[1306] Step 3:

[1307] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[1308] Step 4:

[1309] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information within the image, where an OCR engine analyzes the image and generates a string of characters.

[1310] Step 5:

[1311] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[1312] Step 6:

[1313] The server converts the generated audio data into a file format and saves it. A path for the saved audio file is generated.

[1314] Step 7:

[1315] The server returns the path of the saved audio file to the device, which uses this path to download the audio file from the server.

[1316] Step 8:

[1317] The terminal stores the downloaded audio file in the terminal for playback, and uses the audio playback function of the terminal to play the audio data to the user.

[1318] Step 9:

[1319] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[1320] In this way, users can easily convert printed text information into speech and retrieve it efficiently, greatly improving information access for the visually impaired and busy people.

[1321] Example 1

[1322] 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."

[1323] Visually impaired people and busy people face challenges in easily and efficiently obtaining text information from printed materials through audio. Conventional systems require a complex process of converting image data to text and then converting that text to audio, making operation cumbersome. Furthermore, the lack of a means to play or save audio data limits the user experience.

[1324] 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.

[1325] In this invention, the server includes means for extracting text from the image data using an optical character recognition device, a speech synthesis device for converting the extracted text into speech, and means for returning the converted speech data to the terminal via the network. This allows users to easily obtain text information from printed materials by speech and save and play the speech data, improving convenience for visually impaired people and busy people.

[1326] An "imaging device" is a device for capturing an image of a print medium, and includes, for example, a camera or the camera function of a smartphone.

[1327] "Image data" is digital data of an image of a print medium captured by a photographing device.

[1328] "Network" refers to the means of communication for sending and receiving data between a terminal and a server, including the Internet and wireless communication.

[1329] The "server" is a device that analyzes received image data using an optical character recognition device, extracts text information, and converts it into voice data.

[1330] An "optical character recognition device" is a technical device that extracts character information from image data and uses OCR technology.

[1331] "Text" is character information extracted from image data by an optical character recognition device.

[1332] A "speech synthesizer" is a technical device that converts extracted text into speech data, and uses speech synthesis technology.

[1333] "Voice data" refers to digital data that is generated by a voice synthesizer and can be reproduced as voice.

[1334] A "terminal" is a device used by a user, which has the function of playing or saving audio data.

[1335] "Internal storage" refers to a storage device installed within a terminal for storing digital data.

[1336] An "audio player" is software or hardware installed on a terminal for playing audio data.

[1337] The present invention relates to a system for converting text information from print media into speech, aimed at visually impaired people and busy people. This system is mainly composed of a terminal, a network, and a server.

[1338] Hardware and software used

[1339] Terminal

[1340] The terminals used are smartphones or tablet devices. The terminals are equipped with a camera function so that users can take pictures of the printed materials. The terminals also have a communication means for sending the acquired image data to a server via a network.

[1341] network

[1342] The network uses the Internet or wireless communication, which allows data to be sent and received efficiently between the terminal and the server.

[1343] server

[1344] The server is equipped with the following hardware and software:

[1345] Optical character recognition (OCR) devices: For example, using Tesseract OCR or Google Cloud Vision API to extract text information from image data.

[1346] Speech synthesizer: For example, use Google Text-to-Speech or Amazon Polly to convert the extracted text into audio data.

[1347] Program processing

[1348] Image acquisition and transmission

[1349] The user takes a picture of the printed text using the camera function of the device, and the device sends the image data to a server via the Internet or wireless communication.

[1350] Extracting text from images

[1351] The server analyzes the received image data using an optical character recognition device to extract text information from the image. For example, the server receives the image data and calls Tesseract OCR or Google Cloud Vision API to scan the text information in the image and convert it into digital text.

[1352] Text-to-speech

[1353] The server then converts the extracted text into audio data using a speech synthesizer, such as Google Text-to-Speech or Amazon Polly, and saves the resulting audio data in a specified format (e.g., MP3).

[1354] Sending and playing audio data

[1355] The server transmits the generated audio data to the device via the network. The device that receives the data stores the audio data in its internal storage and plays it back using its built-in audio player.

[1356] Specific examples

[1357] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1358] 1. The user takes a photo of a page in a book using their smartphone camera.

[1359] 2. The application on the smartphone sends this image data to the server.

[1360] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[1361] 4. The server uses speech synthesis technology to convert this text into voice data, for example, "Hello, world."

[1362] 5. The server sends the generated voice data to the smartphone.

[1363] 6. The smartphone plays the received audio data, and the user can hear the audio saying "Hello, world."

[1364] Examples of prompt statements

[1365] Below are some examples of prompts for generative AI models:

[1366] Example prompt sentence:

[1367] "Hello, Model. I'm developing a system to allow the visually impaired to hear printed book pages aloud. Could you please walk me through the steps a user takes a photo of a book page with their smartphone camera and then converts the text into speech and plays it back?"

[1368] As described above, the system of the present invention can provide printed text information by voice simply and efficiently to the visually impaired and busy people.

[1369] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1370] Step 1: Image acquisition

[1371] The user takes a picture of the printed media using the device's camera function. When the user presses the capture button, the smartphone's camera app starts up and the captured image is saved in the device's internal storage.

[1372] Input: Print media (books, newspapers, etc.)

[1373] Output: Acquired image data

[1374] Specific operation: The user opens the camera app, frames the target print, and takes a photo. The image data is temporarily saved on the device.

[1375] Step 2: Send image data

[1376] The device sends the acquired image data to the server via the network, and an application on the smartphone automatically generates an HTTP POST request to upload the image data to the server.

[1377] Input: Acquired image data

[1378] Output: Image data sent to the server

[1379] Specific operation: The application on the device selects the image data and sends it to the server via the Internet.

[1380] Step 3: Extract text from images

[1381] The server analyzes the received image data using an optical character recognition device to extract the text information in the image, then calls OCR software (such as Tesseract OCR or Google Cloud Vision API) to scan the text information in the image and convert it into digital text.

[1382] Input: Image data sent to the server

[1383] Output: Extracted text data

[1384] What happens: The server stores the received data and runs an OCR process to extract text information from the image data.

[1385] Step 4: Convert text to speech

[1386] The server converts the extracted text into voice data using a speech synthesizer. The server uses Google Text-to-Speech or Amazon Polly to convert the text into voice data. It is also possible to adjust the language and accent of the voice according to the user's settings.

[1387] Input: Extracted text data

[1388] Output: Converted audio data

[1389] Specific operation: The server passes the text data to the speech synthesis system to generate audio data. The generated audio data is saved in the specified format (e.g. MP3).

[1390] Step 5: Sending audio data

[1391] The server sends the generated voice data to the terminal via the network, and returns the voice data to the terminal as an HTTP response.

[1392] Input: Converted audio data

[1393] Output: Audio data sent to the device

[1394] Specific operation: The server returns the audio data as an HTTP response, and the device receives it.

[1395] Step 6: Play and save the audio data

[1396] The device stores the received audio data in its internal storage and plays it using the built-in audio player, allowing the user to play the received audio at any time.

[1397] Input: Audio data sent to the device

[1398] Output: Played audio, stored audio data

[1399] Specific operation: The device saves the audio data to the internal storage, and the user operates the audio player to play the audio.

[1400] By performing the above steps, the system of the present invention can provide text information from printed material simply and efficiently by voice.

[1401] (Application example 1)

[1402] 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."

[1403] Conventional systems that convert text information from print media into speech are only useful for the visually impaired and busy people, but they lack the ability to provide audio guidance of product labels and descriptions in physical stores, which causes inconvenience when shopping in physical stores. Visually impaired people in particular often have difficulty selecting and purchasing products. Even for busy people, the inefficiency of gathering information in stores has been an issue.

[1404] 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.

[1405] In this invention, the server includes means for capturing an image of an actual product using a photographing device, means for transmitting the captured image data to an information processing device via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to a terminal via the network, means for playing the returned speech data on the terminal, and means for providing audio guidance of product labels and descriptions in a store, thereby enabling visually impaired people and busy people to easily shop in a physical store.

[1406] An "imaging device" is a hardware device for capturing images of real objects.

[1407] "Image data" refers to image information of an actual object captured by a photographing device.

[1408] A "network" is a communication means for sending and receiving data between a terminal and a server.

[1409] An "information processing device" is a device that functions as a server and processes data.

[1410] An "optical character recognition device" is a device for extracting text from image data.

[1411] A "speech synthesizer" is a device for converting extracted text into speech data.

[1412] A "terminal" is a device that plays back the audio data returned from the server, and includes smartphones and tablets.

[1413] "Product label" refers to the information label affixed to a product in a physical store.

[1414] "Description" refers to the text information that describes a product or service in a physical store.

[1415] "Voice guidance means" is a function that informs the user of information on product labels and descriptions through voice.

[1416] System Overview

[1417] The system of this invention aims to make shopping in brick-and-mortar stores easier for visually impaired people and busy people. The system consists of the following elements:

[1418] Hardware and software used

[1419] Smartphone cameras as photographic devices

[1420] Internet connection as a network

[1421] Server as an information processing device

[1422] Tesseract OCR as an optical character recognizer

[1423] Google Cloud Text-to-Speech API as a speech synthesizer

[1424] Smartphones as devices

[1425] System Operation

[1426] The operation of the system involves the following steps:

[1427] 1. Image capture: The user uses the smartphone camera to take an image of the product label or description.

[1428] 2. Image transmission: The smartphone transmits the captured image data to a server via the Internet.

[1429] 3. Character Recognition: The server uses Tesseract OCR to extract character information from the received image data.

[1430] 4. Speech conversion: The extracted text data is converted to audio data using the Google Cloud Text-to-Speech API.

[1431] 5. Voice data transmission: The converted voice data is sent back to the smartphone via the network.

[1432] 6. Audio playback: The smartphone plays the received audio data, allowing the user to check product information and descriptions by voice.

[1433] Specific examples

[1434] As a concrete example, consider the following scenario:

[1435] Imagine a user standing in front of a product shelf in a physical store, taking a picture of the label with their smartphone camera, and the application automatically sends the image to the server.

[1436] The server uses Tesseract OCR to extract text information from the image data, such as "Milk 1L 200 yen." This information is input into the Google Cloud Text-to-Speech API and generated as audio data.

[1437] The voice data is sent to the user's smartphone, and the user can hear the voice guidance, "Milk 1 liter, 200 yen." This example enables visually impaired people and busy people to quickly obtain necessary product information by voice, making shopping in physical stores more convenient.

[1438] Prompt Sentence Examples

[1439] An example prompt is:

[1440] "Please convert the following product information into audio: Milk 1L 200 yen"

[1441] Such a system can obtain product information without relying on vision by obtaining information from product labels and descriptions and providing audio guidance.

[1442] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1443] Step 1:

[1444] A user takes a picture of a product label or description using a smartphone camera. The input is the actual product label or description, and the output is the captured image data. Specific operations include the user launching the application, switching to camera mode, and pressing the capture button.

[1445] Step 2:

[1446] The device sends the captured image data to the server via the Internet. The input here is the image data acquired in step 1, and the output is the image data sent to the server. Specific operations include the device automatically acquiring the image data and uploading it to the server using an HTTP request.

[1447] Step 3:

[1448] The server uses Tesseract OCR to extract text information from image data received by the server. The input is the image data sent to the server, and the output is the extracted text data. Specific operations include the server processing the received data and calling the OCR engine to perform character recognition.

[1449] Step 4:

[1450] The server converts the extracted text data into speech data using the Google Cloud Text-to-Speech API. The input here is the text data extracted in step 3, and the output is the generated speech data. Specific operations include the server calling the Text-to-Speech API to input the text data and perform speech synthesis.

[1451] Step 5:

[1452] The server sends the audio data to the terminal via the network. The input here is the audio data generated in step 4, and the output is the audio data sent to the terminal. Specific operations include the server returning the generated audio data to the terminal in an HTTP response.

[1453] Step 6:

[1454] The terminal plays the received audio data. The input is the audio data sent from the server, and the output is the audio information played back to the user. Specific operations include the terminal's audio player decoding the audio data and playing it through the speaker.

[1455] In this way, by explaining the specific operations and inputs / outputs of each step, you can gain a detailed understanding of the overall system and how it operates.

[1456] 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.

[1457] The present invention relates to a system for converting text information from print media into speech for visually impaired people and busy people, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system will be described below.

[1458] System Overview

[1459] The system of the present invention comprises a terminal, a network, a server, and an emotion engine.

[1460] 1. Device:

[1461] This is a device for capturing images of print media using a photographic device. For example, a smartphone or tablet is used.

[1462] It has the function of sending the acquired image data to a server via a network.

[1463] It has a playback means for playing back the voice data returned from the server, and is also equipped with an emotion engine that has the function of recognizing emotions from the user's facial expressions and voice.

[1464] If necessary, a storage means is provided for storing the audio data so that it can be played back later.

[1465] 2. Network:

[1466] A communication method for sending and receiving data between a terminal and a server, using an internet connection or a wireless network.

[1467] 3. Server:

[1468] A device that processes image data received from a terminal.

[1469] An optical character recognizer is used to extract text from images.

[1470] It is equipped with a speech synthesizer that converts the extracted text into speech data.

[1471] When synthesizing speech, it has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[1472] 4. Emotion Engine:

[1473] It is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice.

[1474] The emotion engine can transmit the acquired emotion data to the server and reflect it in the generation of voice data.

[1475] Program processing explanation

[1476] The specific program processing of this system will be explained below in order.

[1477] Image acquisition and transmission

[1478] The user takes a picture of the printed text using the camera function of the device. The device then sends the image data to the server via the network. This process allows the user to easily capture an image of the printed material and send it to the server.

[1479] Extracting text from images

[1480] The server analyzes the received image data using an optical character recognition device to extract text information from the image, for example, using OCR technology to obtain character information from the image, thereby converting the printed text into digital text.

[1481] Text-to-speech

[1482] The server converts the extracted text into voice data using a speech synthesizer, and can adjust the language and accent of the voice according to the user's settings. Furthermore, the server can adjust the voice tone and speed based on the user's emotional data transmitted from the device.

[1483] Sending and playing audio data

[1484] The server transmits the generated voice data to the terminal via the network. The terminal then plays the received voice data using a playback means, allowing the user to listen to the text information aloud. If the terminal has a storage means, it is also possible to save the received voice data and play it back later.

[1485] Functions and Use of Emotion Engine

[1486] The emotion engine is installed on the device and analyzes the user's facial expressions and voice in real time. The emotion data is sent to the server and reflected in the voice synthesis. For example, if the user is tired, a calm tone of voice is generated. On the other hand, if the user is happy, a bright tone of voice is generated.

[1487] Specific examples

[1488] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1489] 1. The user takes a photo of a page in a book using their smartphone camera.

[1490] 2. The application on the smartphone sends this image data to the server.

[1491] 3. The server uses OCR technology to extract text information from the image, for example, "Hello, World."

[1492] 4. The server uses speech synthesis technology to convert this text into speech, adjusting the tone and speed of the speech based on data from the emotion engine.

[1493] 5. The server sends the generated voice data to the smartphone.

[1494] 6. The smartphone plays the received audio data, and the user hears the audio saying "Hello, world." At this time, an audio tone is played that corresponds to the user's emotional state.

[1495] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[1496] The processing flow will be explained below.

[1497] Step 1:

[1498] The user uses the device's camera to take a picture of the printed text, and the device stores the captured image data in its memory.

[1499] Step 2:

[1500] The device sends the saved image data to the server via the network using an HTTP POST request, and the image data is sent to the server in binary format.

[1501] Step 3:

[1502] The server analyzes the image data received from the terminal. First, the server converts the received binary data into an image object.

[1503] Step 4:

[1504] The server processes the image object using OCR (Optical Character Recognition) technology to extract text information from the image. The OCR engine analyzes the image and generates a string of characters.

[1505] Step 5:

[1506] The server uses speech synthesis technology to convert the extracted text data into speech data. The text data is input to a speech synthesis engine, which generates speech data in the specified language and accent.

[1507] Step 6:

[1508] The server adjusts the voice tone and speed based on the user's emotional data sent from the device, so that the voice data is appropriate for the user's emotional state.

[1509] Step 7:

[1510] The server saves the generated audio data, generates a path for the saved audio file, and returns the path to the device.

[1511] Step 8:

[1512] The terminal receives the path of the audio file returned from the server, and uses this path to download the audio file from the server.

[1513] Step 9:

[1514] After the download is complete, the terminal uses the playback means to play the received audio file, and the terminal uses the audio playback function to play the audio data to the user.

[1515] Step 10:

[1516] If necessary, the device can store the received audio data for later playback, allowing the user to easily access the stored audio data if they wish to listen to it again.

[1517] Step 11:

[1518] The emotion engine analyzes the user's facial expressions and voice in real time to obtain emotional data, which is then sent to the server and reflected in the next speech synthesis.

[1519] In this way, the system provides a more personalized audio experience by providing voice data that reflects the user's emotions, and it can significantly improve information access for the visually impaired and busy people.

[1520] Example 2

[1521] 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."

[1522] In modern society, visually impaired people and busy people need efficient and intuitive ways to obtain information from print media. However, conventional systems cannot generate speech that takes the user's emotions into account, making it difficult to improve the user experience. Furthermore, the process of information acquisition and speech generation is limited to a single function, resulting in a lack of flexibility. To solve these problems, a technology that synthesizes speech based on the user's emotions is needed.

[1523] 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 means for capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, means for playing the returned speech data on the terminal, and an emotion engine for recognizing the user's emotion and adjusting the speech data based on the emotion. This allows visually impaired people and busy people to efficiently obtain information obtained from print media by speech, and the tone and speed of the speech reflect the user's emotion, enabling a more intuitive and comfortable user experience.

[1524] An "imaging device" is a device for capturing an image of a print medium, and examples include smartphones and tablets.

[1525] A "network" is a communication means for sending and receiving data between a terminal and a server, and may be an internet line or a wireless network.

[1526] An "optical character recognition device" is a technology for extracting text information from image data, and OCR technology is one such example.

[1527] A "speech synthesizer" is a technology for converting extracted text into audio data, and includes text-to-speech systems and speech synthesis engines.

[1528] A "server" is a device that processes received image data and performs text extraction and voice synthesis.

[1529] A "terminal" is a device that includes a photographing device, transmits image data to a server, and plays back received audio data.

[1530] An "emotion engine" is a technology that analyzes a user's facial expressions and voice to recognize their emotions and reflects that data in speech synthesis.

[1531] This invention relates to a system that converts text information from print media into speech for visually impaired people and busy people, and also combines it with an emotion engine that recognizes the user's emotions. Details of how to specifically implement this system are described below.

[1532] System configuration

[1533] This system consists of terminals, a network, a server, and an emotion engine.

[1534] Device:

[1535] The terminal is a device that captures images of print media using a photographing device. Specific examples include smartphones and tablets. The terminal has the function of sending the captured image data to a server via a network and has a playback means for playing back the voice data returned from the server. It also has an emotion engine and the function of recognizing emotions from the user's facial expressions and voice. It also has a storage means for saving the voice data as needed so that it can be played back later.

[1536] network:

[1537] A network is a communication means for sending and receiving data between a terminal and a server, and can be an internet line or a wireless network.

[1538] server:

[1539] The server processes image data received from the device. It uses optical character recognition (OCR) to extract text from the image and then includes a speech synthesizer that converts the text into speech data. During speech synthesis, the server also has the ability to adjust the tone and speed of the speech based on the user's emotional information received from the device.

[1540] Emotion Engine:

[1541] The emotion engine is equipped with technology that recognizes emotions by analyzing the user's facial expressions and voice. The emotion engine sends the acquired emotion data to the server, which can then be reflected in the generated voice data.

[1542] Specific examples

[1543] As a specific example, a series of processes when a user photographs a page of a book and listens to the contents of the book will be described.

[1544] 1. The user takes a photo of a page in a book using their smartphone camera.

[1545] 2. The application on the smartphone sends this image data to the server.

[1546] 3. The server extracts text information from the image using OCR technology (e.g., Tesseract), e.g., the text "Hello, World" is extracted.

[1547] 4. The server converts this text into voice data using speech synthesis technology (e.g., Google Text-to-Speech or OpenAI's speech synthesis library), and adjusts the voice tone and speed based on the emotion data sent from the device.

[1548] 5. The server sends the generated voice data to the smartphone.

[1549] 6. The smartphone plays the received audio data, and the user hears the message "Hello, world" in a voice that corresponds to the user's emotional state.

[1550] Examples of prompt statements

[1551] Below are some example prompts for a generative AI model:

[1552] "Write a program to design a system that generates speech based on the user's emotional data. The system should be able to adjust the tone and speed of the speech depending on the user's emotion. Explain how the user can use their device to send images of printed media to a server, which will then extract text from the images and convert it into speech."

[1553] In this way, the system of the present invention can further improve the quality of information access for visually impaired people and busy people by recognizing the user's emotions and providing voice data that reflects them.

[1554] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1555] Step 1:

[1556] The user acquires an image of the print medium using a terminal.

[1557] The user launches the camera app on their device (such as a smartphone) and takes a picture of the page of the book or document they want to read. Specifically, they capture the image by framing the image appropriately and pressing the shutter button. The input is an image of the printed media, and the output is the captured image data.

[1558] Step 2:

[1559] The terminal transmits the image data to the server.

[1560] The device sends the captured image data to a server in the background. An application in the smartphone processes the image data and sends it to a specified server address via an Internet connection (Wi-Fi or mobile data). Specifically, this involves the user tapping the "Send" button. The input is the captured image data, and the output is the image data sent to the server.

[1561] Step 3:

[1562] The server extracts the text from the image data.

[1563] The server analyzes the received image data and extracts text using optical character recognition (OCR) technology. Character recognition is performed using an OCR library such as Tesseract to obtain text information from the image data. For example, the text "Hello, world" is extracted from the image data. The input is the image data sent to the server, and the output is the extracted text data.

[1564] Step 4:

[1565] The server converts the text into audio data.

[1566] The server converts the extracted text into voice data using a speech synthesizer. It uses Google Text-to-Speech or OpenAI's speech synthesis library to convert text to voice. Furthermore, it adjusts the voice tone and speed based on the user's emotional data sent from the device. Specifically, the server calls the speech synthesis API to brighten or calm the tone based on the user's emotional state. The input is the extracted text data and emotional data, and the output is the adjusted voice data.

[1567] Step 5:

[1568] The server sends the audio data to the terminal.

[1569] The server sends the generated voice data to the terminal via the network. Specifically, the server creates the generated voice file, assembles the file into data packets for transmission to the terminal, and transmits them via the network. The input is the adjusted voice data, and the output is the voice data transmitted to the terminal.

[1570] Step 6:

[1571] The device plays the audio data.

[1572] The terminal plays the received audio data using a playback means (speaker or headphones). The user can listen to the audio by pressing the play button in the application. It is also possible to save the audio data via a storage means and play it later. Specifically, this includes operations for the terminal to load the received audio data and issue a play command. The input is the audio data sent to the terminal, and the output is the played audio.

[1573] Step 7:

[1574] The emotion engine recognizes and reflects the user's emotions.

[1575] The emotion engine analyzes the user's facial expressions and tone of voice in real time and generates the data. The device sends this emotion data to the server, which then reflects this data when synthesizing speech. Specifically, when the user faces the smartphone camera, the device performs facial recognition and voice analysis, generates emotion data, and sends it to the server. The input is the user's facial expressions and voice data, and the output is emotion data.

[1576] (Application example 2)

[1577] 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."

[1578] Visually impaired people and busy people have difficulty reading restaurant and food delivery menus. Furthermore, if the audio information provided is not tailored to the user's emotional state, it can be stressful to understand the information and experience it is used. Therefore, there is a need for a system that delivers printed text information in audio that adapts to the user's emotional state.

[1579] The identification process by the identification 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 capturing an image of a print medium using a photographing device, means for transmitting the captured image data to the server via a network, means for extracting text from the image data using an optical character recognition device, an emotion analysis engine for analyzing a user's emotion and adjusting the tone and speed of speech synthesis based on the analysis results, a speech synthesizer for converting the extracted text into speech, means for returning the converted speech data to the terminal via the network, and means for playing the returned speech data on the terminal. This makes it possible to provide text information on a print medium in a voice that corresponds to the user's emotion.

[1580] A "photography device" is a device for capturing an image of a print medium, such as a camera mounted on a smartphone or tablet.

[1581] "Image data" refers to image information of a print medium captured by a photographing device.

[1582] A "network" is a communication means for sending and receiving data between a terminal and a server, and includes the Internet and wireless networks.

[1583] A "server" is a device that analyzes image data received from a terminal and performs the necessary processing.

[1584] "Optical character recognition device" is a technology for extracting text information from image data, and generally refers to OCR (Optical Character Recognition) technology.

[1585] "Text" is written information in digital form that has been extracted by an optical character recognition device.

[1586] A "speech synthesizer" is a device equipped with technology for converting text information into voice data. For example, it includes text-to-speech technology.

[1587] "Voice data" refers to digital data in a voice format generated by a voice synthesizer.

[1588] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice to recognize their emotional state and output the results.

[1589] A "terminal" is a device that has a camera, audio playback function, and network communication function, and includes smartphones and tablets.

[1590] The "playback means" is hardware or software for playing back audio data received by the terminal.

[1591] System Overview

[1592] This invention is a system for converting text information from print media into speech for visually impaired people and busy people. The system also combines an emotion analysis engine that recognizes the user's emotions and adjusts the tone and speed of the speech accordingly. Specific embodiments of the system are described below.

[1593] Hardware and Software Configuration

[1594] Terminal

[1595] A device is a device that includes a camera, such as a smartphone or tablet. A device has the following functions:

[1596] A function to capture images of print media using a photographic device

[1597] A function to send acquired image data to a server via a network

[1598] A function to play back audio data returned from the server

[1599] Equipped with an emotion analysis engine that analyzes emotions from the user's facial expressions and voice

[1600] A storage method that allows audio data to be saved and played back later if necessary

[1601] server

[1602] The server has the following capabilities:

[1603] A function that analyzes image data received from a device using optical character recognition (OCR) technology and extracts text information.

[1604] A speech synthesizer that converts extracted text into speech data

[1605] Ability to adjust voice tone and speed based on user emotion data

[1606] network

[1607] A communication method for sending and receiving data between a terminal and a server, including the Internet and wireless networks.

[1608] Program processing overview

[1609] The device first captures an image of the print media using the smartphone's camera. The image data is then sent to a server via a network. The server uses OCR technology to extract text information from the received image data. The extracted text is then converted into voice data using a voice synthesizer. When synthesizing the voice, the tone and speed of the voice are adjusted based on the user's emotional data sent from the device. The generated voice data is sent to the device via a network, where it is played back.

[1610] Specific examples

[1611] We will explain the series of processes that occur when a user takes a photo of a restaurant menu with their smartphone camera and listens to the menu contents aloud.

[1612] 1. The user takes a photo of a restaurant menu using their smartphone camera.

[1613] 2. The application on the smartphone sends this image data to the server.

[1614] 3. The server uses OCR technology to extract text information from the image, such as "We have sushi, tempura, and eel."

[1615] 4. The server converts this text to speech using speech synthesis technology, adjusting the tone and speed of the speech based on data from the sentiment analysis engine.

[1616] 5. The server sends the generated voice data to the smartphone.

[1617] 6. The smartphone plays the received audio data, and the user can hear the menu contents aloud. For example, if the user is happy, the audio will be played in a bright tone.

[1618] Prompt Sentence Examples

[1619] Create an audio file that reads the following text aloud, assuming the user's emotion is "joy."

[1620] Text: "We have sushi, tempura, and eel. Which would you like to eat?"

[1621] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1622] Step 1:

[1623] A user uses the smartphone camera to take an image of a printed medium (e.g., a restaurant menu).

[1624] Input: User-taken image of printed material

[1625] Output: Captured image data file

[1626] Specific operation: The user opens the camera app on their smartphone, points it at the target print medium, and presses the shutter button to take a picture.

[1627] Step 2:

[1628] The terminal transmits the acquired image data to the server.

[1629] Input: Captured image data

[1630] Output: Image data sent to the server

[1631] Specific operation: An application on the smartphone automatically selects the captured image files and sends them to a specified server address via the Internet.

[1632] Step 3:

[1633] The server extracts text information from the received image data using an optical character recognition device.

[1634] Input: Image data sent to the server

[1635] Output: Extracted text information

[1636] What it does: OCR software on the server analyzes the image data and extracts the characters in the print media as digital text, for example, "We have sushi, tempura, and eel."

[1637] Step 4:

[1638] The server converts the extracted text information into audio data.

[1639] Input: Extracted text information

[1640] Output: Audio data file

[1641] What it does: Speech synthesis software on the server analyzes the text information and converts it into spoken audio, adjusting for the language and accent of the audio, if any.

[1642] Step 5:

[1643] The device uses an emotion analysis engine to analyze the user's emotions and sends the data to the server.

[1644] Input: User facial and voice data

[1645] Output: Sentiment analysis data

[1646] Specific operation: The emotion analysis engine analyzes the user's facial expressions and tone of voice in real time, generates emotion data (e.g., "happiness," "sadness," etc.) based on that, and sends it to the server.

[1647] Step 6:

[1648] The server adjusts the tone and speed of the voice based on the emotion analysis data.

[1649] Input: Audio data file, emotion analysis data

[1650] Output: Adjusted audio data file

[1651] What it does: The server's speech synthesis software uses the emotion analysis data to appropriately adjust the tone and speed of the speech. For example, if the user is "happy," a brighter tone will be generated.

[1652] Step 7:

[1653] The server transmits the generated voice data to the terminal.

[1654] Input: Adjusted audio data file

[1655] Output: Audio data sent to the device

[1656] Specific operation: The server sends an audio data file to the terminal via the network.

[1657] Step 8:

[1658] The terminal plays the concluded audio data.

[1659] Input: Audio data sent to the device

[1660] Output: Played audio

[1661] Specific operation: The smartphone's audio playback function analyzes the received audio data and plays it back through the speaker, allowing the user to hear the menu contents aloud.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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).

[1669] 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.

[1670] 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."

[1671] 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.

[1672] 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).

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] The following is further disclosed regarding the above embodiment.

[1684] (Claim 1)

[1685] means for capturing an image of a print medium by an imaging device;

[1686] means for transmitting the acquired image data to a server via a network;

[1687] means for extracting text from the image data using an optical character recognition device;

[1688] a speech synthesizer that converts the extracted text into speech;

[1689] means for returning the converted voice data to the terminal via the network;

[1690] means for playing back the returned audio data on a terminal;

[1691] A system including:

[1692] (Claim 2)

[1693] 2. The system according to claim 1, wherein the speech synthesizer supports multiple languages ​​or accents when synthesizing speech.

[1694] (Claim 3)

[1695] 2. The system of claim 1, wherein the terminal includes means for storing received audio data and for enabling later playback of the stored audio data.

[1696] "Example 1"

[1697] (Claim 1)

[1698] means for capturing an image of a print medium by an imaging device;

[1699] means for transmitting the acquired image data to a server via a network;

[1700] means for extracting text from the image data using an optical character recognition device;

[1701] a speech synthesizer that converts the extracted text into speech;

[1702] means for returning the converted voice data to the terminal via the network;

[1703] means for playing back the returned audio data on a terminal;

[1704] a means for the device to store the audio data in internal storage;

[1705] A system including:

[1706] (Claim 2)

[1707] 2. The system according to claim 1, wherein the speech synthesizer supports multiple languages ​​or accents when synthesizing speech.

[1708] (Claim 3)

[1709] 2. The system according to claim 1, wherein the terminal is capable of reproducing audio data using a built-in audio player.

[1710] "Application Example 1"

[1711] (Claim 1)

[1712] a means for acquiring an image of the actual object by an imaging device;

[1713] means for transmitting the acquired image data to an information processing device via a network;

[1714] means for extracting text from the image data using an optical character recognition device;

[1715] a speech synthesizer that converts the extracted text into speech;

[1716] means for returning the converted voice data to the terminal via the network;

[1717] means for playing back the returned audio data on a terminal;

[1718] A means of providing audio guidance of product labels and descriptions in the store,

[1719] A system including:

[1720] (Claim 2)

[1721] 2. The system of claim 1, wherein the speech synthesizer supports multiple spoken languages ​​or accents when synthesizing speech.

[1722] (Claim 3)

[1723] 2. The system of claim 1, wherein the terminal includes means for storing received audio data and for enabling later playback of the stored audio data.

[1724] "Example 2: Combining Emotion Engines"

[1725] (Claim 1)

[1726] means for capturing an image of a print medium by an imaging device;

[1727] means for transmitting the acquired image data to a server via a network;

[1728] means for extracting text from the image data using an optical character recognition device;

[1729] a speech synthesizer that converts the extracted text into speech;

[1730] means for returning the converted voice data to the terminal via the network;

[1731] means for playing back the returned audio data on a terminal;

[1732] an emotion engine that recognizes an emotion of a user and adjusts the voice data based on the emotion;

[1733] A system including:

[1734] (Claim 2)

[1735] 2. The system according to claim 1, wherein the speech synthesizer supports multiple languages ​​or accents when synthesizing speech.

[1736] (Claim 3)

[1737] 2. The system of claim 1, wherein the terminal includes means for storing received audio data and for enabling later playback of the stored audio data.

[1738] "Application example 2 when combining emotion engines"

[1739] (Claim 1)

[1740] means for capturing an image of a print medium by an imaging device;

[1741] means for transmitting the acquired image data to a server via a network;

[1742] means for extracting text from the image data using an optical character recognition device;

[1743] a speech synthesizer that converts the extracted text into speech;

[1744] An emotion analysis engine that analyzes the user's emotions and adjusts the tone and speed of the speech synthesis based on the analysis results;

[1745] means for returning the converted voice data to the terminal via the network;

[1746] means for playing back the returned audio data on a terminal;

[1747] A system including:

[1748] (Claim 2)

[1749] 2. The system according to claim 1, wherein the speech synthesizer supports multiple languages ​​or accents when synthesizing speech.

[1750] (Claim 3)

[1751] 2. The system of claim 1, wherein the terminal includes means for storing received audio data and for enabling later playback of the stored audio data. [Explanation of symbols]

[1752] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing an image of a print medium by an imaging device; means for transmitting the acquired image data to a server via a network; means for extracting text from the image data using an optical character recognition device; a speech synthesizer that converts the extracted text into speech; means for returning the converted voice data to the terminal via the network; means for playing back the returned audio data on a terminal; A system including:

2. 2. The system of claim 1, wherein the speech synthesizer supports multiple languages ​​or accents when synthesizing speech.

3. 2. The system of claim 1, wherein said terminal includes means for storing received audio data and for enabling later playback of the stored audio data.

Images