system

Abstract

We provide the system. [Solution] A means for transmitting voice data acquired by the user to a management device, A means for analyzing the aforementioned audio data and extracting characteristics related to speech disorders in infants, A means for automatically generating an individualized treatment plan based on the aforementioned characteristics, A means of presenting the aforementioned treatment plan to the user and supporting the training, A means of recording training progress data and using that data to evaluate the therapeutic effect, A means of sharing evaluation results with medical professionals and proposing interventions as needed, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although early intervention is important for speech disorders in infants, especially stuttering, it is difficult to receive appropriate treatment due to a shortage of specialized facilities and experts. In addition, since stuttering has individual characteristics, general treatment methods often do not achieve sufficient effects. The present invention aims to solve these problems and provide a method and system for providing individualized and effective treatment to infants.

Means for Solving the Problems

[0005] The present invention provides means for transmitting voice data acquired by a user to a management device, and means for analyzing the voice data to extract characteristics related to speech disorders in infants. Furthermore, it includes means for automatically generating an individualized treatment plan based on the characteristics, and means for presenting the treatment plan to the user to support training. It also provides means for recording training progress data and evaluating the treatment effect based on that data. By sharing these evaluation results with medical professionals and proposing interventions as needed, the present invention provides a system that realizes effective individualized treatment.

[0006] "User" refers to an individual or their guardian who uses the system to acquire speech data from an infant and administer treatment.

[0007] "Audio data" refers to digital information that records the speech of infants.

[0008] A "management device" refers to a computer system used for analyzing voice data, generating treatment plans, evaluating progress, and sharing information with specialists.

[0009] "Analysis" refers to the process of extracting speech characteristics from input audio data.

[0010] "Characteristics" refer to specific patterns or indicators related to speech disorders that can be obtained from voice data.

[0011] A "treatment plan" refers to a plan that outlines training methods and content designed based on analysis results, with the aim of improving a child's speech development.

[0012] "Training" refers to a series of practice activities that young children engage in to improve their speech abilities, based on a treatment plan.

[0013] "Progress data" refers to information regarding the status and effectiveness of training.

[0014] "Evaluation" refers to the act of analyzing the effectiveness of treatment using progress data.

[0015] "Medical professionals" refer to doctors and speech therapists who have specialized knowledge and experience in the treatment of speech disorders.

[0016] "Intervention" refers to the act of an expert adjusting the direction of treatment or providing direct support as necessary.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the 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.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0031] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This system analyzes speech data to provide personalized treatment plans for speech disorders in young children. The detailed implementation method of the system is described below.

[0039] The user records the infant's everyday speech using a smartphone or other device. The recorded audio data is sent from the device to a server, which acts as a management device. Upon receiving this audio data, the server analyzes it using its built-in artificial intelligence model. As a result of the analysis, characteristics related to the infant's speech, specifically stuttering patterns and frequency, are extracted.

[0040] The server then automatically generates a personalized treatment plan based on the extracted characteristics. This plan includes training content and approaches to improve the child's specific speech disorder. The generated treatment plan is notified to the user via the device, and daily training is guided.

[0041] The user conducts the designated training with the infant according to the treatment plan provided on the device. The progress of the training is recorded by the device and periodically sent to the server as progress data. The server evaluates the received progress data and analyzes the effectiveness of the treatment. Based on the evaluation results, the treatment plan may be adjusted as needed.

[0042] Furthermore, the server shares the evaluation results of the progress data with medical professionals. This allows professionals to assess the need for improvements to the treatment plan or direct guidance. If necessary, professional intervention is suggested, and the user can receive additional support.

[0043] As a concrete example, consider a situation where toddler B tries to say "A red car is coming" but stumbles and says "A red red car is coming." The user records B's speech and sends it to the server. The server analyzes the audio and recognizes that there is a repetition of the same sound. Based on this pattern, the server generates a plan that includes training menus to help B pronounce the initial sounds of words smoothly. The user uses this plan to train B daily, and the treatment progresses while regularly checking B's progress.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user records the infant's speech using a smartphone. The recorded audio data is saved to an application on the device.

[0047] Step 2:

[0048] The terminal prepares to send the recorded audio data to the database. The transmission is made to the server using a secure protocol.

[0049] Step 3:

[0050] The server analyzes the received audio data. Using an artificial intelligence model, it extracts features related to speech disorders from the audio data. Specifically, it identifies stuttering patterns, frequency, and the number of times sounds are repeated.

[0051] Step 4:

[0052] The server automatically generates an individualized treatment plan based on the analysis results. This treatment plan includes specific training content and guidance policies.

[0053] Step 5:

[0054] The server sends the generated treatment plan to the user's device. The user can receive and review this treatment plan using an application on their device.

[0055] Step 6:

[0056] The user conducts training with the infant according to the provided treatment plan. The user records the progress of the training and the infant's responses.

[0057] Step 7:

[0058] The terminal periodically uploads recorded training progress data to the server. This allows the server to track the latest progress.

[0059] Step 8:

[0060] The server analyzes the received progress data and evaluates the effectiveness of the treatment. The evaluation results are used to determine whether the training program is being followed appropriately.

[0061] Step 9:

[0062] The server shares the results of the effectiveness analysis with medical professionals. These professionals can use this data to assess the need for further treatment and propose interventions.

[0063] (Example 1)

[0064] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] Speech disorders in young children present challenges in selecting appropriate treatments and tracking their progress. Traditional methods struggle to provide individualized treatment plans quickly and effectively, and data collection and analysis for accurately evaluating treatment effectiveness are insufficient. Therefore, there is a need to experimentally implement more effective and sustainable treatments.

[0066] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0067] In this invention, the server includes means for transmitting voice data acquired by a user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in infants, and means for automatically generating an individualized treatment plan based on the characteristics. This makes it possible to quickly provide an individualized treatment plan for speech disorders in infants and to quantitatively evaluate its effectiveness.

[0068] "Audio data" refers to information recorded digitally using a recording device or similar equipment, capturing the sounds spoken by a young child.

[0069] An "information processing device" is a server or computer system that receives, analyzes, and processes audio data.

[0070] "Speech disorder" refers to a condition in which young children have difficulty pronouncing words as intended, and specifically includes stuttering.

[0071] "Methods for extracting features" refer to methods for identifying patterns and frequencies of speech disorders from audio data and extracting them as analysis results.

[0072] An "individualized treatment plan" is a set of training programs and approaches designed to improve a specific child's speech disorder based on identified characteristics.

[0073] "Educational progress data" refers to information used to record the progress of training based on a treatment plan and to evaluate the effectiveness of the treatment.

[0074] A "generative AI model" is an artificial intelligence system that implements machine learning algorithms used to analyze audio data.

[0075] This system is designed to treat speech disorders in infants. Users record their infant's everyday speech using a device such as a smartphone. This recorded audio data is then transmitted from the device to a server acting as an information processing unit.

[0076] The server uses a generative AI model to analyze the received audio data. This AI model extracts features such as stuttering patterns and frequencies from the audio data. The extracted data is then generated as a digital report.

[0077] Next, the server automatically generates an individualized treatment plan based on the extracted characteristics. This treatment plan includes training content and approaches to improve the child's speech impairment. This generated treatment plan is then communicated to the user via the device.

[0078] The user conducts training with the infant according to the educational plan displayed on the device. The progress of the training is recorded on the device and periodically sent to the server as educational progress data. Based on this data, the server can evaluate the effectiveness of the treatment and adjust the treatment plan as needed.

[0079] As a concrete example, consider a scenario where a toddler tries to say "The blue dog is running" but stumbles and says "Oh, the blue dog is running." When the user records this utterance and sends it to the server, the server analyzes the audio and recognizes the repetition of the same sound. Based on this pattern, the server generates a treatment plan that includes training to pronounce the initial sounds of words smoothly. The user then trains daily based on this plan, and the content of the training is adjusted according to their progress, resulting in effective treatment.

[0080] Example of a prompt:

[0081] "We record infant speech and transmit the audio data. We analyze stuttering patterns and generate an appropriate treatment plan."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user records the child's everyday speech using a device. To start recording, the user launches a recording app installed on the device and presses the record button to record the speech. The input is the child's speech, and the output is generated as digital audio data. This data is saved for later analysis.

[0085] Step 2:

[0086] The terminal sends recorded audio data to the server. Before sending, the terminal compresses the audio data and saves it in an appropriate file format (e.g., WAV or MP3). The input is the uncompressed audio data, and the output is the compressed audio data sent to the server using a secure protocol.

[0087] Step 3:

[0088] The server analyzes the audio data received from the terminal. Here, a generative AI model is used to extract features from the audio data. Specifically, the AI ​​model identifies stuttering patterns and frequencies and generates a digital report. Compressed audio data is the input, and the analysis results are obtained as the output.

[0089] Step 4:

[0090] The server automatically generates an individualized treatment plan based on the extracted features. The AI ​​model refers to the analysis results and selects the most suitable training content for the child's speech disorder. The analysis results are the input, and an individualized treatment plan is generated as the output.

[0091] Step 5:

[0092] The terminal notifies the user of the treatment plan from the server. The notified treatment plan is displayed through the user interface. The generated treatment plan is the input, and it is provided to the user in a visible form as output.

[0093] Step 6:

[0094] The user uses a device to conduct training with the infant according to the presented treatment plan. Specifically, this involves performing voice exercises according to on-screen instructions. The treatment plan is the input, and progress data is recorded as the output.

[0095] Step 7:

[0096] The terminal periodically sends recorded progress data to the server. The progress data is formatted and converted into a format easily sent to the server. The input is progress data, and the output is the completion of transmission to the server.

[0097] Step 8:

[0098] The server uses the received progress data to evaluate the effectiveness of the treatment. The AI ​​model is then utilized again to adjust the treatment plan based on the progress. Progress data is the input, evaluation results are obtained as output, and the plan is updated as needed.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] Speech disorders in early childhood, if not addressed appropriately, can affect language abilities in the future. However, conventional methods struggle to efficiently provide training tailored to individual speech characteristics, necessitating specialized support. Furthermore, there is a problem in obtaining appropriate feedback during daily practice at home. Therefore, a system is needed that can provide individualized and effective speech training and evaluate progress.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes means for transmitting voice data acquired by the user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in early childhood, and means for automatically generating an individualized training plan based on the characteristics. This makes it possible to automatically provide individualized speech training based on voice data and support optimal practice.

[0104] An "information processing device" is a computer or other device that acquires audio data, analyzes it, and generates training plans.

[0105] "Voice data" refers to digital audio signals that record speech during early childhood.

[0106] "Speech disorders" refer to symptoms such as pauses in speech and repetition of the same sound that affect the ability to speak fluently.

[0107] "Feature extraction" is the process of identifying and extracting speech patterns and types of speech disorders from audio data.

[0108] A "training plan" refers to a program that includes individualized practice content aimed at improving speech disorders.

[0109] A "human support device" is a device that uses sound and visuals to inform users of the practice content and complements the human instructor.

[0110] "Progress data" refers to information that records the degree of achievement and progress of training.

[0111] An "intelligent processing model" is an artificial intelligence algorithm that enables the analysis of speech data and the generation of training plans.

[0112] This invention is a system aimed at improving speech disorders in early childhood, and it collects and analyzes voice data, generates and provides training plans. The system mainly consists of an information processing device, a portable device, and a human assistance device.

[0113] The information processing device receives audio data and performs speech analysis using an intelligent processing model. For data analysis, artificial intelligence models on Google Cloud AI or Amazon Web Services (AWS) can be used. This allows for the extraction of speech disorder characteristics from the audio data and the generation of an individualized training plan. The generated training plan is then communicated to the user via a portable device.

[0114] The portable device is used by the user to record the infant's speech and transmit it to the information processing device. Furthermore, it displays the training plan visually or audibly to support daily training.

[0115] Human support devices play a role in guiding and instructing users on training content. They provide appropriate feedback to young children through voice and screens.

[0116] As a concrete example, imagine a young child trying to say "I like apples" but stumbling over, saying "I like ri-ri-ringo." The user records this utterance with a portable device and sends it to an information processing device. The information processing device, recognizing the consecutive identical sounds, uses an intelligent processing model to generate a training plan. This plan includes items to practice the smoothness of specific vowel sounds. The training plan is presented to the user via the portable device, enabling daily practice using a human assistance device.

[0117] An example of an input prompt for a generative AI model is, "Analyze the speech patterns in this audio data and propose a specific training plan for improvement."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The user uses a portable device to record the speech of an infant. The input is the infant's utterances, and the output is digitized audio data. The portable device activates its recording function and converts the audio into digital data via the microphone.

[0121] Step 2:

[0122] The portable device transmits recorded audio data to a server. The input is digital audio data, and the output is data transferred to the server. The data is transmitted via the internet using data communication capabilities.

[0123] Step 3:

[0124] The server analyzes the received audio data. The input is audio data, and the output is audio feature information. A generative AI model is used to analyze speech patterns within the audio and extract features such as stuttering patterns.

[0125] Step 4:

[0126] The server generates an individualized training plan based on the analysis results. The input is speech feature information, and the output is the training plan. The planning algorithm automatically generates appropriate practice content according to the extracted features.

[0127] Step 5:

[0128] The server sends the generated training plan to the portable device. The input is the training plan, and the output is the data transferred to the portable device. The training plan information is transmitted using the data communication function.

[0129] Step 6:

[0130] The portable device notifies and displays the training plan to the user. The input is the training plan received from the server, and the output is the information shown to the user via the portable device's screen or audio output. The training content is presented using a screen display or audio output module.

[0131] Step 7:

[0132] The user follows the instructions on the portable device and conducts daily training with the child. The input is training instructions, and the output is actual vocal exercises. Based on the guidance, the user supports the child's pronunciation practice.

[0133] Step 8:

[0134] The portable device records the progress of the training and periodically sends the progress data to the server. The input is the status of the training, and the output is digital progress data. The content of the training is recorded using sensors and timestamps and transmitted to the server via data communication.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] This invention is a system that combines emotion recognition to comprehensively improve speech disorders in infants. The specific implementation of this system is described below.

[0137] Users record their child's speech using a smartphone or tablet. This audio data is then saved to the device. The device sends this audio data to a server. The server analyzes the audio data and is equipped with an artificial intelligence model and emotion engine to recognize the content of the speech and the emotional state.

[0138] The server's artificial intelligence model extracts features related to speech disorders from the received audio data. This analysis identifies patterns and frequencies of stuttering. Additionally, the server's emotion engine identifies the child's emotional state from the audio data and extracts information corresponding to that state.

[0139] Next, the server automatically generates an individualized treatment plan, taking into account the extracted speech characteristics and emotional states. This treatment plan includes specific training content and adjustments to address the child's emotions. For example, if the child shows anxiety, the plan will include training activities that provide a sense of security.

[0140] The user reviews the treatment plan sent from the server on their device and conducts training tailored to the infant. During training, the device continuously records the infant's voice, and the emotion engine recognizes the infant's emotional state in real time. This recorded data is periodically sent from the device to the server and managed as progress data.

[0141] The server evaluates the effectiveness of the training based on progress data. This evaluation allows for monitoring the progress of treatment and adjusting the plan as needed. The evaluation results are also shared with medical professionals, allowing for expert feedback and intervention. For example, if toddler C becomes emotionally tense when trying to say "t-t-t-fun play," the emotional engine can detect this tension and add training to promote relaxation.

[0142] Thus, in addition to improving speech disorders, the system of the present invention supports the development of infants while addressing emotional changes.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The user records the infant's speech using the device. The audio data is recorded through a dedicated application on the device.

[0146] Step 2:

[0147] The device pre-processes the recorded audio data for emotion recognition and then sends it to the server via secure communication.

[0148] Step 3:

[0149] The server analyzes the received audio data. An artificial intelligence model extracts speech features and identifies stuttering patterns and frequencies.

[0150] Step 4:

[0151] The server uses an emotion engine to identify the child's emotional state from the audio data. Specifically, it analyzes the tone, volume, and intonation of the voice to detect changes in emotion.

[0152] Step 5:

[0153] The server generates an individualized treatment plan based on both speech characteristics and emotional states. This plan incorporates training menus adapted to the emotional state.

[0154] Step 6:

[0155] The server sends the generated treatment plan to the device. The user reviews the plan on the device and implements appropriate training for the infant.

[0156] Step 7:

[0157] During training, the device continuously records the infant's voice data, and the emotion engine recognizes their emotional state in real time. This information is transmitted from the device to the server.

[0158] Step 8:

[0159] The server analyzes progress data received in real time and evaluates the effectiveness of the treatment. Since changes in emotional state are also taken into consideration, more precise feedback is possible.

[0160] Step 9:

[0161] The server shares progress evaluation results with medical professionals. These professionals can provide data-driven feedback and suggest further treatment options. Users can continue their training under the guidance of these professionals.

[0162] (Example 2)

[0163] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0164] In the recovery process for speech disorders in young children, it is necessary to take into account individual characteristics and emotional states, but conventional systems have difficulty comprehensively handling these elements. Therefore, there is a need for a system that can automatically generate treatment methods that address both the characteristics and emotional aspects of speech disorders, and that can evaluate and adjust their effectiveness in a timely manner.

[0165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0166] In this invention, the server includes means for using an artificial intelligence engine to analyze voice data and extract features related to speech disorders, means for automatically generating an individualized treatment plan based on the features and emotional state, and means for sharing evaluation results and easily receiving feedback from experts. This enables the provision of individualized treatment and management of its progress.

[0167] "User" refers to a person who uses the system to acquire and provide voice data of infants.

[0168] A "terminal" refers to an electronic device used to record and store voice data and transfer it to a management device.

[0169] The "management device" refers to a central computer that receives, analyzes, and processes voice data transmitted by users.

[0170] "Audio data" refers to digital information that is a recording of a child's speech.

[0171] "Speech disorders" refer to specific abnormalities or delays related to language, such as stuttering or difficulty pronouncing words.

[0172] An "artificial intelligence engine" refers to a program that uses machine learning techniques to analyze the characteristics of speech and recognize and extract patterns of problems.

[0173] "Emotional state" refers to the psychological or emotional state of an infant as estimated from audio data.

[0174] A "treatment plan" refers to a plan designed individually for improving a child's speech based on the results of an analysis of their voice data.

[0175] "Progress data" refers to information collected during the training process, and data that shows the progress and effectiveness of treatment.

[0176] A "specialist" refers to a person who possesses specialized knowledge in medicine or speech therapy and can provide feedback based on evaluation results from the system.

[0177] To implement this invention, a system is required that performs a series of processes, from acquiring and analyzing audio data to generating treatment plans and managing their progress. This system consists of a user, a terminal, and a server.

[0178] Users utilize devices such as smartphones or tablets to record their infants' speech. The recorded audio data is stored digitally on the device's storage. The device incorporates a communication module for sending the audio data to the server, and a secure communication protocol (e.g., HTTPS) is used to ensure the safe transmission of the data.

[0179] The server is equipped with an artificial intelligence engine for analyzing received audio data. This engine is built using a common machine learning library (e.g., TENSORFLOW®) and extracts features of speech disorders from the audio data. Furthermore, the server can identify the emotional state of infants using an emotion engine. This emotion engine estimates the psychological state of infants by analyzing the intonation and tempo of their speech.

[0180] The server runs a program to automatically generate an individualized treatment plan based on the analyzed speech characteristics and emotional states. This program is written in a programming language such as Python and selects the most suitable content from multiple treatment templates. The generated treatment plan includes content that provides reassurance if the infant shows signs of anxiety.

[0181] For example, a young child might become tense when trying to say "t-t-t-fun play." In this case, the server's emotion engine can detect this tension and add training to encourage relaxation to the plan.

[0182] Users review the treatment plan displayed on the device and provide appropriate speech training to their infants. Progress data recorded during the training process is sent from the device to the server, where its effectiveness is continuously evaluated. The server manages this data and readjusts the treatment plan as needed. This evaluation result is shared with professionals through an appropriate interface, allowing for more effective feedback.

[0183] An example of an input prompt for the generative AI model is: "Based on the speech data of an infant, please identify speech disorders and emotional states, and propose an appropriate treatment plan."

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The user records the infant's speech using a device such as a smartphone or tablet. The input is the infant's speech, and the output is stored as audio data on the device. In this step, the device's microphone is used, and the audio data is converted into a digital format.

[0187] Step 2:

[0188] The terminal sends recorded audio data to the server. The input is the audio data within the terminal, and the output is the data transferred to the server. The terminal uses a secure communication protocol to protect the integrity of the data while transmitting it over the internet.

[0189] Step 3:

[0190] The server analyzes the received audio data. The input is the transmitted audio data, and the output is data that shows the characteristics of speech disorders. The server uses an artificial intelligence model to extract speech features. Specifically, data calculations are performed to identify stuttering patterns and frequencies from the audio signal.

[0191] Step 4:

[0192] The server performs analysis to identify emotional states in parallel with the audio data. The input is the same audio data, and the output is data representing the emotional state of the infant. Here, the emotion engine performs emotional analysis, extracting the psychological state from the intonation and tempo of the voice. An audio analysis algorithm is used in this process.

[0193] Step 5:

[0194] The server generates personalized treatment plans based on speech characteristics and emotional states. The input is analyzed speech characteristics and emotional state data, and the output is a treatment plan incorporating specific training content. The server uses a generation AI model to select the optimal treatment content and automatically create a plan. This involves template selection and customization by the AI ​​model.

[0195] Step 6:

[0196] The user reviews the treatment plan sent from the server on their device and then conducts training for the infant. The input is the treatment plan from the server, and the output is the specific training instructions displayed on the device. The device displays this information on its screen.

[0197] Step 7:

[0198] The device continuously records speech during training and acquires progress data. The input is the speech of the child during training, and the output is an audio recording that is organized as progress data. Here, the device records in real time and continuously collects audio data.

[0199] Step 8:

[0200] The terminal periodically sends recorded progress data to the server. The input is the progress data, and the output is the data transferred to the server. This process is performed via a secure connection.

[0201] Step 9:

[0202] The server evaluates the received progress data and analyzes the effectiveness of the treatment. The input is progress data, and the output is a treatment progress report. AI and data analysis techniques are used to measure the effectiveness of the training and adjust the treatment plan as needed.

[0203] Step 10:

[0204] The server facilitates the sharing of analysis results with medical professionals and provides an environment for easy feedback. The input is the analysis results of treatment effectiveness, and the output is returned as expert feedback. A dedicated online platform is used for this sharing process.

[0205] (Application Example 2)

[0206] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0207] Speech-related problems in the elderly and young children include speech disorders and communication difficulties. These problems require appropriate care and treatment, and individualized responses are necessary. Furthermore, there is a lack of systems for effectively assessing progress and intervening as needed. In addition, there is a need for technologies that can address the diversity of speech characteristics associated with emotional changes.

[0208] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0209] In this invention, the server includes means for transmitting voice data acquired by the user to a management device, means for analyzing the voice data and extracting features related to speech disorders and conversational characteristics, and means for automatically generating an individualized treatment or care plan based on the features. This enables appropriate support and effective intervention to address speech disorders and communication difficulties.

[0210] "Voice data" refers to information that electronically records the content of a user's speech.

[0211] A "management device" is an electronic device used to receive, analyze, and process audio data.

[0212] "Analysis" is the process of extracting important features related to speech from audio data.

[0213] "Speech disorders" refer to impairments in language fluency and psychological speech characteristics that occur in infants and the elderly.

[0214] "Characteristics" refer to patterns and tendencies in speech data that indicate speech disorders or characteristics.

[0215] A "treatment plan" is a set of automatically generated guidelines and procedures designed to improve an individual's speech disorder.

[0216] A "care plan" is a guideline for providing appropriate care based on the conversational characteristics of elderly individuals.

[0217] "Training" refers to specific activities or exercises conducted to improve the user's speech ability.

[0218] "Progress data" refers to information that shows the progress of training or care.

[0219] A "specialist" is a professional who possesses knowledge related to medicine or nursing care.

[0220] "Intervention" refers to specific actions or measures taken to address a particular problem.

[0221] This system primarily consists of devices such as smartphones and tablets, and a server. The user first records the subject's voice data using their device. This voice data is sent to the server via data communication. The server converts the received voice data to text using Google's Speech-to-Text API and other tools. Then, using TensorFlow and other machine learning models, it performs a detailed analysis of speech disorder characteristics and emotional states. This automatically generates treatment and care plans tailored to each individual. The generated plans are then returned to the user's device and used for implementing training and care.

[0222] To track progress, the device continuously records the subject's voice and transmits it to a server. This data is managed as progress data and used to evaluate the effectiveness of treatment and care. If necessary, these evaluation results are shared with medical and care professionals to adjust the plan.

[0223] As a concrete example, when person A speaks in a normal conversation, the device records what they say, and the server analyzes the content to extract the element "I've been feeling tired lately." Based on this, a plan is generated to suggest relaxation activities for person A. An example of a prompt message would be, "Person A seems to be feeling tired lately. What kind of relaxation activities should be suggested?"

[0224] As described above, this system enables efficient processing of voice data and flexible planning tailored to individual circumstances, supporting the improvement of speech disorders and communication problems among the elderly.

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The user uses a device to record the subject's voice data. This operation saves the subject's voice as digital data on the device. This data can then be converted from physical voice to digital elements such as pixels, enabling subsequent processing.

[0228] Step 2:

[0229] The device sends the recorded audio data to the server. The device uses a stable network connection to transfer the data. Once the audio data reaches the server, the server receives new data input.

[0230] Step 3:

[0231] The server uses Google's Speech-to-Text API to analyze the received audio data. This API performs data processing to convert the audio data into text data. The resulting text data can be used as output for structural analysis of the spoken content.

[0232] Step 4:

[0233] Text data is analyzed, and TensorFlow is used to analyze speech features and emotional states. The server leverages an AI model to analyze the input text data and derive patterns of speech disorders and emotional states. This output forms the basis for creating specific plans.

[0234] Step 5:

[0235] The server uses an AI model based on the analysis results to automatically generate personalized treatment or care plans. The AI ​​model designs the optimal plan for the user through data calculations and provides the plan's content as output.

[0236] Step 6:

[0237] The server sends the generated personalized plan to the terminal, where the user reviews it. The plan is displayed on the terminal, and the user uses this output to carry out training and care. The terminal invokes UI / UX functions that display this information intuitively.

[0238] Step 7:

[0239] The device continuously records the voice of the person receiving training or care and sends it to the server as new progress data. This data is used as input to provide the server with the progress of the plan and prepare it for evaluation.

[0240] Step 8:

[0241] The server uses progress data to evaluate the effectiveness of treatment and care, and generates the results as output. If necessary, the plan is adjusted, a new plan is generated, and it is sent back to the terminal. The server uses evaluation algorithms to perform data calculations throughout this process.

[0242] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0243] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0244] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0248] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0249] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0250] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0251] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0252] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0253] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0254] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0255] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0256] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0257] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0258] This system analyzes speech data to provide personalized treatment plans for speech disorders in young children. The detailed implementation method of the system is described below.

[0259] The user records the infant's everyday speech using a smartphone or other device. The recorded audio data is sent from the device to a server, which acts as a management device. Upon receiving this audio data, the server analyzes it using its built-in artificial intelligence model. As a result of the analysis, characteristics related to the infant's speech, specifically stuttering patterns and frequency, are extracted.

[0260] The server then automatically generates a personalized treatment plan based on the extracted characteristics. This plan includes training content and approaches to improve the child's specific speech disorder. The generated treatment plan is notified to the user via the device, and daily training is guided.

[0261] The user conducts the designated training with the infant according to the treatment plan provided on the device. The progress of the training is recorded by the device and periodically sent to the server as progress data. The server evaluates the received progress data and analyzes the effectiveness of the treatment. Based on the evaluation results, the treatment plan may be adjusted as needed.

[0262] Furthermore, the server shares the evaluation results of the progress data with medical professionals. This allows professionals to assess the need for improvements to the treatment plan or direct guidance. If necessary, professional intervention is suggested, and the user can receive additional support.

[0263] As a concrete example, consider a situation where toddler B tries to say "A red car is coming" but stumbles and says "A red red car is coming." The user records B's speech and sends it to the server. The server analyzes the audio and recognizes that there is a repetition of the same sound. Based on this pattern, the server generates a plan that includes training menus to help B pronounce the initial sounds of words smoothly. The user uses this plan to train B daily, and the treatment progresses while regularly checking B's progress.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] The user records the infant's speech using a smartphone. The recorded audio data is saved to an application on the device.

[0267] Step 2:

[0268] The terminal prepares to send the recorded audio data to the database. The transmission is made to the server using a secure protocol.

[0269] Step 3:

[0270] The server analyzes the received audio data. Using an artificial intelligence model, it extracts features related to speech disorders from the audio data. Specifically, it identifies stuttering patterns, frequency, and the number of times sounds are repeated.

[0271] Step 4:

[0272] The server automatically generates an individualized treatment plan based on the analysis results. This treatment plan includes specific training content and guidance policies.

[0273] Step 5:

[0274] The server sends the generated treatment plan to the user's device. The user can receive and review this treatment plan using an application on their device.

[0275] Step 6:

[0276] The user conducts training with the infant according to the provided treatment plan. The user records the progress of the training and the infant's responses.

[0277] Step 7:

[0278] The terminal periodically uploads recorded training progress data to the server. This allows the server to track the latest progress.

[0279] Step 8:

[0280] The server analyzes the received progress data and evaluates the effectiveness of the treatment. The evaluation results are used to determine whether the training program is being followed appropriately.

[0281] Step 9:

[0282] The server shares the result of the effect analysis with medical experts. The experts can use this data to evaluate the necessity of further treatment and propose interventions.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] There are issues with childhood speech disorders in that it is difficult to select an appropriate treatment method and track its progress. With conventional methods, it is difficult to provide an individualized treatment plan quickly and effectively, and data collection and analysis for accurately evaluating the effectiveness of treatment are not sufficient. Therefore, there is a need to experimentally implement more effective and sustainable treatments.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0287] In this invention, the server includes means for transmitting voice data acquired by a user to an information processing device, means for analyzing the voice data and extracting features related to childhood speech disorders, and means for automatically generating an individualized treatment plan based on the features. Thereby, it becomes possible to quickly provide an individualized treatment plan for childhood speech disorders and quantitatively evaluate its effect.

[0288] "Voice data" is information obtained by digitally recording the voice of a child speaking using a recording device or the like.

[0289] "Information processing device" is a server or computer system for receiving, analyzing, and processing the results of voice data.

[0290] "Speech disorder" refers to a condition in which young children have difficulty pronouncing words as intended, and specifically includes stuttering.

[0291] "Methods for extracting features" refer to methods for identifying patterns and frequencies of speech disorders from audio data and extracting them as analysis results.

[0292] An "individualized treatment plan" is a set of training programs and approaches designed to improve a specific child's speech disorder based on identified characteristics.

[0293] "Educational progress data" refers to information used to record the progress of training based on a treatment plan and to evaluate the effectiveness of the treatment.

[0294] A "generative AI model" is an artificial intelligence system that implements machine learning algorithms used to analyze audio data.

[0295] This system is designed to treat speech disorders in infants. Users record their infant's everyday speech using a device such as a smartphone. This recorded audio data is then transmitted from the device to a server acting as an information processing unit.

[0296] The server uses a generative AI model to analyze the received audio data. This AI model extracts features such as stuttering patterns and frequencies from the audio data. The extracted data is then generated as a digital report.

[0297] Next, the server automatically generates an individualized treatment plan based on the extracted characteristics. This treatment plan includes training content and approaches to improve the child's speech impairment. This generated treatment plan is then communicated to the user via the device.

[0298] The user conducts training with the infant according to the educational plan displayed on the device. The progress of the training is recorded on the device and periodically sent to the server as educational progress data. Based on this data, the server can evaluate the effectiveness of the treatment and adjust the treatment plan as needed.

[0299] As a concrete example, consider a scenario where a toddler tries to say "The blue dog is running" but stumbles and says "Oh, the blue dog is running." When the user records this utterance and sends it to the server, the server analyzes the audio and recognizes the repetition of the same sound. Based on this pattern, the server generates a treatment plan that includes training to pronounce the initial sounds of words smoothly. The user then trains daily based on this plan, and the content of the training is adjusted according to their progress, resulting in effective treatment.

[0300] Example of a prompt:

[0301] "We record infant speech and transmit the audio data. We analyze stuttering patterns and generate an appropriate treatment plan."

[0302] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0303] Step 1:

[0304] The user records the child's everyday speech using a device. To start recording, the user launches a recording app installed on the device and presses the record button to record the speech. The input is the child's speech, and the output is generated as digital audio data. This data is saved for later analysis.

[0305] Step 2:

[0306] The terminal sends recorded audio data to the server. Before sending, the terminal compresses the audio data and saves it in an appropriate file format (e.g., WAV or MP3). The input is the uncompressed audio data, and the output is the compressed audio data sent to the server using a secure protocol.

[0307] Step 3:

[0308] The server analyzes the voice data received from the terminal. Here, using the generated AI model, the features in the voice data are extracted. As a specific operation, the AI model identifies the stuttering patterns and frequencies and generates a digital report. There is compressed voice data as input, and the analysis result is obtained as output.

[0309] Step 4:

[0310] The server automatically generates an individualized treatment plan based on the extracted features. The AI model refers to the analysis result and selects the training content optimal for the child's speech disorder. There is the analysis result as input, and an individualized treatment plan is generated as output.

[0311] Step 5:

[0312] The terminal notifies the user of the treatment plan from the server. The notified treatment plan is displayed through the user interface. There is the generated treatment plan as input, and it is provided to the user in a visible form as output.

[0313] Step 6:

[0314] The user uses the terminal to conduct training with the child according to the presented treatment plan. As a specific operation, voice exercises are performed according to the instructions on the screen. There is the treatment plan as input, and progress data is recorded as output.

[0315] Step 7:

[0316] The terminal periodically sends the recorded progress data to the server. The progress data is formatted and converted into a form that is easy to send to the server. There is the progress data as input, and the transmission to the server is completed as output.

[0317] Step 8:

[0318] The server uses the received progress data to evaluate the effectiveness of the treatment. The AI ​​model is then utilized again to adjust the treatment plan based on the progress. Progress data is the input, evaluation results are obtained as output, and the plan is updated as needed.

[0319] (Application Example 1)

[0320] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0321] Speech disorders in early childhood, if not addressed appropriately, can affect language abilities in the future. However, conventional methods struggle to efficiently provide training tailored to individual speech characteristics, necessitating specialized support. Furthermore, there is a problem in obtaining appropriate feedback during daily practice at home. Therefore, a system is needed that can provide individualized and effective speech training and evaluate progress.

[0322] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0323] In this invention, the server includes means for transmitting voice data acquired by the user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in early childhood, and means for automatically generating an individualized training plan based on the characteristics. This makes it possible to automatically provide individualized speech training based on voice data and support optimal practice.

[0324] An "information processing device" is a computer or other device that acquires audio data, analyzes it, and generates training plans.

[0325] "Voice data" refers to digital audio signals that record speech during early childhood.

[0326] "Speech disorders" refer to symptoms such as pauses in speech and repetition of the same sound that affect the ability to speak fluently.

[0327] "Feature extraction" is the process of identifying and extracting speech patterns and types of speech disorders from audio data.

[0328] A "training plan" refers to a program that includes individualized practice content aimed at improving speech disorders.

[0329] A "human support device" is a device that uses sound and visuals to inform users of the practice content and complements the human instructor.

[0330] "Progress data" refers to information that records the degree of achievement and progress of training.

[0331] An "intelligent processing model" is an artificial intelligence algorithm that enables the analysis of speech data and the generation of training plans.

[0332] This invention is a system aimed at improving speech disorders in early childhood, and it collects and analyzes voice data, generates and provides training plans. The system mainly consists of an information processing device, a portable device, and a human assistance device.

[0333] The information processing device receives audio data and performs speech analysis using an intelligent processing model. For data analysis, artificial intelligence models on Google Cloud AI or Amazon Web Services (AWS) can be used. This allows for the extraction of speech disorder characteristics from the audio data and the generation of an individualized training plan. The generated training plan is then communicated to the user via a portable device.

[0334] The portable device is used by the user to record the infant's speech and transmit it to the information processing device. Furthermore, it displays the training plan visually or audibly to support daily training.

[0335] Human support devices play a role in guiding and instructing users on training content. They provide appropriate feedback to young children through voice and screens.

[0336] As a concrete example, imagine a young child trying to say "I like apples" but stumbling over, saying "I like ri-ri-ringo." The user records this utterance with a portable device and sends it to an information processing device. The information processing device, recognizing the consecutive identical sounds, uses an intelligent processing model to generate a training plan. This plan includes items to practice the smoothness of specific vowel sounds. The training plan is presented to the user via the portable device, enabling daily practice using a human assistance device.

[0337] An example of an input prompt for a generative AI model is, "Analyze the speech patterns in this audio data and propose a specific training plan for improvement."

[0338] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0339] Step 1:

[0340] The user uses a portable device to record the speech of an infant. The input is the infant's utterances, and the output is digitized audio data. The portable device activates its recording function and converts the audio into digital data via the microphone.

[0341] Step 2:

[0342] The portable device transmits recorded audio data to a server. The input is digital audio data, and the output is data transferred to the server. The data is transmitted via the internet using data communication capabilities.

[0343] Step 3:

[0344] The server analyzes the received audio data. The input is audio data, and the output is audio feature information. A generative AI model is used to analyze speech patterns within the audio and extract features such as stuttering patterns.

[0345] Step 4:

[0346] The server generates an individualized training plan based on the analysis results. The input is speech feature information, and the output is the training plan. The planning algorithm automatically generates appropriate practice content according to the extracted features.

[0347] Step 5:

[0348] The server sends the generated training plan to the portable device. The input is the training plan, and the output is the data transferred to the portable device. The training plan information is transmitted using the data communication function.

[0349] Step 6:

[0350] The portable device notifies and displays the training plan to the user. The input is the training plan received from the server, and the output is the information shown to the user via the portable device's screen or audio output. The training content is presented using a screen display or audio output module.

[0351] Step 7:

[0352] The user follows the instructions on the portable device and conducts daily training with the child. The input is training instructions, and the output is actual vocal exercises. Based on the guidance, the user supports the child's pronunciation practice.

[0353] Step 8:

[0354] The portable device records the progress of the training and periodically sends the progress data to the server. The input is the status of the training, and the output is digital progress data. The content of the training is recorded using sensors and timestamps and transmitted to the server via data communication.

[0355] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0356] This invention is a system that combines emotion recognition to comprehensively improve speech disorders in infants. The specific implementation of this system is described below.

[0357] Users record their child's speech using a smartphone or tablet. This audio data is then saved to the device. The device sends this audio data to a server. The server analyzes the audio data and is equipped with an artificial intelligence model and emotion engine to recognize the content of the speech and the emotional state.

[0358] The server's artificial intelligence model extracts features related to speech disorders from the received audio data. This analysis identifies patterns and frequencies of stuttering. Additionally, the server's emotion engine identifies the child's emotional state from the audio data and extracts information corresponding to that state.

[0359] Next, the server automatically generates an individualized treatment plan, taking into account the extracted speech characteristics and emotional states. This treatment plan includes specific training content and adjustments to address the child's emotions. For example, if the child shows anxiety, the plan will include training activities that provide a sense of security.

[0360] The user reviews the treatment plan sent from the server on their device and conducts training tailored to the infant. During training, the device continuously records the infant's voice, and the emotion engine recognizes the infant's emotional state in real time. This recorded data is periodically sent from the device to the server and managed as progress data.

[0361] The server evaluates the effectiveness of the training based on progress data. This evaluation allows for monitoring the progress of treatment and adjusting the plan as needed. The evaluation results are also shared with medical professionals, allowing for expert feedback and intervention. For example, if toddler C becomes emotionally tense when trying to say "t-t-t-fun play," the emotional engine can detect this tension and add training to promote relaxation.

[0362] Thus, in addition to improving speech disorders, the system of the present invention supports the development of infants while addressing emotional changes.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] The user records the infant's speech using the device. The audio data is recorded through a dedicated application on the device.

[0366] Step 2:

[0367] The device pre-processes the recorded audio data for emotion recognition and then sends it to the server via secure communication.

[0368] Step 3:

[0369] The server analyzes the received audio data. An artificial intelligence model extracts speech features and identifies stuttering patterns and frequencies.

[0370] Step 4:

[0371] The server uses an emotion engine to identify the child's emotional state from the audio data. Specifically, it analyzes the tone, volume, and intonation of the voice to detect changes in emotion.

[0372] Step 5:

[0373] The server generates an individualized treatment plan based on both speech characteristics and emotional states. This plan incorporates training menus adapted to the emotional state.

[0374] Step 6:

[0375] The server sends the generated treatment plan to the device. The user reviews the plan on the device and implements appropriate training for the infant.

[0376] Step 7:

[0377] During training, the device continuously records the infant's voice data, and the emotion engine recognizes their emotional state in real time. This information is transmitted from the device to the server.

[0378] Step 8:

[0379] The server analyzes progress data received in real time and evaluates the effectiveness of the treatment. Since changes in emotional state are also taken into consideration, more precise feedback is possible.

[0380] Step 9:

[0381] The server shares progress evaluation results with medical professionals. These professionals can provide data-driven feedback and suggest further treatment options. Users can continue their training under the guidance of these professionals.

[0382] (Example 2)

[0383] Next, we will describe Example 2. 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".

[0384] In the recovery process for speech disorders in young children, it is necessary to take into account individual characteristics and emotional states, but conventional systems have difficulty comprehensively handling these elements. Therefore, there is a need for a system that can automatically generate treatment methods that address both the characteristics and emotional aspects of speech disorders, and that can evaluate and adjust their effectiveness in a timely manner.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0386] In this invention, the server includes means for using an artificial intelligence engine to analyze voice data and extract features related to speech disorders, means for automatically generating an individualized treatment plan based on the features and emotional state, and means for sharing evaluation results and easily receiving feedback from experts. This enables the provision of individualized treatment and management of its progress.

[0387] "User" refers to a person who uses the system to acquire and provide voice data of infants.

[0388] A "terminal" refers to an electronic device used to record and store voice data and transfer it to a management device.

[0389] The "management device" refers to a central computer that receives, analyzes, and processes voice data transmitted by users.

[0390] "Audio data" refers to digital information that is a recording of a child's speech.

[0391] "Speech disorders" refer to specific abnormalities or delays related to language, such as stuttering or difficulty pronouncing words.

[0392] An "artificial intelligence engine" refers to a program that uses machine learning techniques to analyze the characteristics of speech and recognize and extract patterns of problems.

[0393] "Emotional state" refers to the psychological or emotional state of an infant as estimated from audio data.

[0394] A "treatment plan" refers to a plan designed individually for improving a child's speech based on the results of an analysis of their voice data.

[0395] "Progress data" refers to information collected during the training process, and data that shows the progress and effectiveness of treatment.

[0396] A "specialist" refers to a person who possesses specialized knowledge in medicine or speech therapy and can provide feedback based on evaluation results from the system.

[0397] To implement this invention, a system is required that performs a series of processes, from acquiring and analyzing audio data to generating treatment plans and managing their progress. This system consists of a user, a terminal, and a server.

[0398] Users utilize devices such as smartphones or tablets to record their infants' speech. The recorded audio data is stored digitally on the device's storage. The device incorporates a communication module for sending the audio data to the server, and a secure communication protocol (e.g., HTTPS) is used to ensure the safe transmission of the data.

[0399] The server is equipped with an artificial intelligence engine for analyzing received audio data. This engine is built using common machine learning libraries (e.g., TensorFlow) and extracts features of speech disorders from the audio data. Furthermore, the server can identify the emotional state of infants using an emotion engine. This emotion engine estimates the psychological state of infants by analyzing the intonation and tempo of their speech.

[0400] The server runs a program to automatically generate an individualized treatment plan based on the analyzed speech characteristics and emotional states. This program is written in a programming language such as Python and selects the most suitable content from multiple treatment templates. The generated treatment plan includes content that provides reassurance if the infant shows signs of anxiety.

[0401] For example, a young child might become tense when trying to say "t-t-t-fun play." In this case, the server's emotion engine can detect this tension and add training to encourage relaxation to the plan.

[0402] Users review the treatment plan displayed on the device and provide appropriate speech training to their infants. Progress data recorded during the training process is sent from the device to the server, where its effectiveness is continuously evaluated. The server manages this data and readjusts the treatment plan as needed. This evaluation result is shared with professionals through an appropriate interface, allowing for more effective feedback.

[0403] An example of an input prompt for the generative AI model is: "Based on the speech data of an infant, please identify speech disorders and emotional states, and propose an appropriate treatment plan."

[0404] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0405] Step 1:

[0406] The user records the infant's speech using a device such as a smartphone or tablet. The input is the infant's speech, and the output is stored as audio data on the device. In this step, the device's microphone is used, and the audio data is converted into a digital format.

[0407] Step 2:

[0408] The terminal sends recorded audio data to the server. The input is the audio data within the terminal, and the output is the data transferred to the server. The terminal uses a secure communication protocol to protect the integrity of the data while transmitting it over the internet.

[0409] Step 3:

[0410] The server analyzes the received audio data. The input is the transmitted audio data, and the output is data that shows the characteristics of speech disorders. The server uses an artificial intelligence model to extract speech features. Specifically, data calculations are performed to identify stuttering patterns and frequencies from the audio signal.

[0411] Step 4:

[0412] The server performs analysis to identify emotional states in parallel with the audio data. The input is the same audio data, and the output is data representing the emotional state of the infant. Here, the emotion engine performs emotional analysis, extracting the psychological state from the intonation and tempo of the voice. An audio analysis algorithm is used in this process.

[0413] Step 5:

[0414] The server generates personalized treatment plans based on speech characteristics and emotional states. The input is analyzed speech characteristics and emotional state data, and the output is a treatment plan incorporating specific training content. The server uses a generation AI model to select the optimal treatment content and automatically create a plan. This involves template selection and customization by the AI ​​model.

[0415] Step 6:

[0416] The user reviews the treatment plan sent from the server on their device and then conducts training for the infant. The input is the treatment plan from the server, and the output is the specific training instructions displayed on the device. The device displays this information on its screen.

[0417] Step 7:

[0418] The device continuously records speech during training and acquires progress data. The input is the speech of the child during training, and the output is an audio recording that is organized as progress data. Here, the device records in real time and continuously collects audio data.

[0419] Step 8:

[0420] The terminal periodically sends recorded progress data to the server. The input is the progress data, and the output is the data transferred to the server. This process is performed via a secure connection.

[0421] Step 9:

[0422] The server evaluates the received progress data and analyzes the effectiveness of the treatment. The input is progress data, and the output is a treatment progress report. AI and data analysis techniques are used to measure the effectiveness of the training and adjust the treatment plan as needed.

[0423] Step 10:

[0424] The server facilitates the sharing of analysis results with medical professionals and provides an environment for easy feedback. The input is the analysis results of treatment effectiveness, and the output is returned as expert feedback. A dedicated online platform is used for this sharing process.

[0425] (Application Example 2)

[0426] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0427] Speech-related problems in the elderly and young children include speech disorders and communication difficulties. These problems require appropriate care and treatment, and individualized responses are necessary. Furthermore, there is a lack of systems for effectively assessing progress and intervening as needed. In addition, there is a need for technologies that can address the diversity of speech characteristics associated with emotional changes.

[0428] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0429] In this invention, the server includes means for transmitting voice data acquired by the user to a management device, means for analyzing the voice data and extracting features related to speech disorders and conversational characteristics, and means for automatically generating an individualized treatment or care plan based on the features. This enables appropriate support and effective intervention to address speech disorders and communication difficulties.

[0430] "Voice data" refers to information that electronically records the content of a user's speech.

[0431] A "management device" is an electronic device used to receive, analyze, and process audio data.

[0432] "Analysis" is the process of extracting important features related to speech from audio data.

[0433] "Speech disorders" refer to impairments in language fluency and psychological speech characteristics that occur in infants and the elderly.

[0434] "Characteristics" refer to patterns and tendencies in speech data that indicate speech disorders or characteristics.

[0435] A "treatment plan" is a set of automatically generated guidelines and procedures designed to improve an individual's speech disorder.

[0436] A "care plan" is a guideline for providing appropriate care based on the conversational characteristics of elderly individuals.

[0437] "Training" refers to specific activities or exercises conducted to improve the user's speech ability.

[0438] "Progress data" refers to information that shows the progress of training or care.

[0439] A "specialist" is a professional who possesses knowledge related to medicine or nursing care.

[0440] "Intervention" refers to specific actions or measures taken to address a particular problem.

[0441] This system primarily consists of devices such as smartphones and tablets, and a server. The user first records the subject's voice data using their device. This voice data is sent to the server via data communication. The server converts the received voice data to text using Google's Speech-to-Text API and other tools. Then, using TensorFlow and other machine learning models, it performs a detailed analysis of speech disorder characteristics and emotional states. This automatically generates treatment and care plans tailored to each individual. The generated plans are then returned to the user's device and used for implementing training and care.

[0442] To track progress, the device continuously records the subject's voice and transmits it to a server. This data is managed as progress data and used to evaluate the effectiveness of treatment and care. If necessary, these evaluation results are shared with medical and care professionals to adjust the plan.

[0443] As a concrete example, when person A speaks in a normal conversation, the device records what they say, and the server analyzes the content to extract the element "I've been feeling tired lately." Based on this, a plan is generated to suggest relaxation activities for person A. An example of a prompt message would be, "Person A seems to be feeling tired lately. What kind of relaxation activities should be suggested?"

[0444] As described above, this system enables efficient processing of voice data and flexible planning tailored to individual circumstances, supporting the improvement of speech disorders and communication problems among the elderly.

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The user uses a device to record the subject's voice data. This operation saves the subject's voice as digital data on the device. This data can then be converted from physical voice to digital elements such as pixels, enabling subsequent processing.

[0448] Step 2:

[0449] The device sends the recorded audio data to the server. The device uses a stable network connection to transfer the data. Once the audio data reaches the server, the server receives new data input.

[0450] Step 3:

[0451] The server uses Google's Speech-to-Text API to analyze the received audio data. This API performs data processing to convert the audio data into text data. The resulting text data can be used as output for structural analysis of the spoken content.

[0452] Step 4:

[0453] Text data is analyzed, and TensorFlow is used to analyze speech features and emotional states. The server leverages an AI model to analyze the input text data and derive patterns of speech disorders and emotional states. This output forms the basis for creating specific plans.

[0454] Step 5:

[0455] The server uses an AI model based on the analysis results to automatically generate personalized treatment or care plans. The AI ​​model designs the optimal plan for the user through data calculations and provides the plan's content as output.

[0456] Step 6:

[0457] The server sends the generated personalized plan to the terminal, where the user reviews it. The plan is displayed on the terminal, and the user uses this output to carry out training and care. The terminal invokes UI / UX functions that display this information intuitively.

[0458] Step 7:

[0459] The device continuously records the voice of the person receiving training or care and sends it to the server as new progress data. This data is used as input to provide the server with the progress of the plan and prepare it for evaluation.

[0460] Step 8:

[0461] The server uses progress data to evaluate the effectiveness of treatment and care, and generates the results as output. If necessary, the plan is adjusted, a new plan is generated, and it is sent back to the terminal. The server uses evaluation algorithms to perform data calculations throughout this process.

[0462] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0463] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0464] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0465] [Third Embodiment]

[0466] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0467] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0468] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0469] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0470] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0471] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0472] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0473] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0474] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0475] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0476] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0477] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0478] This system analyzes speech data to provide personalized treatment plans for speech disorders in young children. The detailed implementation method of the system is described below.

[0479] The user records the infant's everyday speech using a smartphone or other device. The recorded audio data is sent from the device to a server, which acts as a management device. Upon receiving this audio data, the server analyzes it using its built-in artificial intelligence model. As a result of the analysis, characteristics related to the infant's speech, specifically stuttering patterns and frequency, are extracted.

[0480] The server then automatically generates a personalized treatment plan based on the extracted characteristics. This plan includes training content and approaches to improve the child's specific speech disorder. The generated treatment plan is notified to the user via the device, and daily training is guided.

[0481] The user conducts the designated training with the infant according to the treatment plan provided on the device. The progress of the training is recorded by the device and periodically sent to the server as progress data. The server evaluates the received progress data and analyzes the effectiveness of the treatment. Based on the evaluation results, the treatment plan may be adjusted as needed.

[0482] Furthermore, the server shares the evaluation results of the progress data with medical professionals. This allows professionals to assess the need for improvements to the treatment plan or direct guidance. If necessary, professional intervention is suggested, and the user can receive additional support.

[0483] As a concrete example, consider a situation where toddler B tries to say "A red car is coming" but stumbles and says "A red red car is coming." The user records B's speech and sends it to the server. The server analyzes the audio and recognizes that there is a repetition of the same sound. Based on this pattern, the server generates a plan that includes training menus to help B pronounce the initial sounds of words smoothly. The user uses this plan to train B daily, and the treatment progresses while regularly checking B's progress.

[0484] The following describes the processing flow.

[0485] Step 1:

[0486] The user records the infant's speech using a smartphone. The recorded audio data is saved to an application on the device.

[0487] Step 2:

[0488] The terminal prepares to send the recorded audio data to the database. The transmission is made to the server using a secure protocol.

[0489] Step 3:

[0490] The server analyzes the received audio data. Using an artificial intelligence model, it extracts features related to speech disorders from the audio data. Specifically, it identifies stuttering patterns, frequency, and the number of times sounds are repeated.

[0491] Step 4:

[0492] The server automatically generates an individualized treatment plan based on the analysis results. This treatment plan includes specific training content and guidance policies.

[0493] Step 5:

[0494] The server sends the generated treatment plan to the user's device. The user can receive and review this treatment plan using an application on their device.

[0495] Step 6:

[0496] The user conducts training with the infant according to the provided treatment plan. The user records the progress of the training and the infant's responses.

[0497] Step 7:

[0498] The terminal periodically uploads recorded training progress data to the server. This allows the server to track the latest progress.

[0499] Step 8:

[0500] The server analyzes the received progress data and evaluates the effectiveness of the treatment. The evaluation results are used to determine whether the training program is being followed appropriately.

[0501] Step 9:

[0502] The server shares the results of the effectiveness analysis with medical professionals. These professionals can use this data to assess the need for further treatment and propose interventions.

[0503] (Example 1)

[0504] Next, we will describe Example 1. 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."

[0505] Speech disorders in young children present challenges in selecting appropriate treatments and tracking their progress. Traditional methods struggle to provide individualized treatment plans quickly and effectively, and data collection and analysis for accurately evaluating treatment effectiveness are insufficient. Therefore, there is a need to experimentally implement more effective and sustainable treatments.

[0506] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0507] In this invention, the server includes means for transmitting voice data acquired by a user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in infants, and means for automatically generating an individualized treatment plan based on the characteristics. This makes it possible to quickly provide an individualized treatment plan for speech disorders in infants and to quantitatively evaluate its effectiveness.

[0508] "Audio data" refers to information recorded digitally using a recording device or similar equipment, capturing the sounds spoken by a young child.

[0509] An "information processing device" is a server or computer system that receives, analyzes, and processes audio data.

[0510] "Speech disorder" refers to a condition in which young children have difficulty pronouncing words as intended, and specifically includes stuttering.

[0511] "Methods for extracting features" refer to methods for identifying patterns and frequencies of speech disorders from audio data and extracting them as analysis results.

[0512] An "individualized treatment plan" is a set of training programs and approaches designed to improve a specific child's speech disorder based on identified characteristics.

[0513] "Educational progress data" refers to information used to record the progress of training based on a treatment plan and to evaluate the effectiveness of the treatment.

[0514] A "generative AI model" is an artificial intelligence system that implements machine learning algorithms used to analyze audio data.

[0515] This system is designed to treat speech disorders in infants. Users record their infant's everyday speech using a device such as a smartphone. This recorded audio data is then transmitted from the device to a server acting as an information processing unit.

[0516] The server uses a generative AI model to analyze the received audio data. This AI model extracts features such as stuttering patterns and frequencies from the audio data. The extracted data is then generated as a digital report.

[0517] Next, the server automatically generates an individualized treatment plan based on the extracted characteristics. This treatment plan includes training content and approaches to improve the child's speech impairment. This generated treatment plan is then communicated to the user via the device.

[0518] The user conducts training with the infant according to the educational plan displayed on the device. The progress of the training is recorded on the device and periodically sent to the server as educational progress data. Based on this data, the server can evaluate the effectiveness of the treatment and adjust the treatment plan as needed.

[0519] As a concrete example, consider a scenario where a toddler tries to say "The blue dog is running" but stumbles and says "Oh, the blue dog is running." When the user records this utterance and sends it to the server, the server analyzes the audio and recognizes the repetition of the same sound. Based on this pattern, the server generates a treatment plan that includes training to pronounce the initial sounds of words smoothly. The user then trains daily based on this plan, and the content of the training is adjusted according to their progress, resulting in effective treatment.

[0520] Example of a prompt:

[0521] "We record infant speech and transmit the audio data. We analyze stuttering patterns and generate an appropriate treatment plan."

[0522] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0523] Step 1:

[0524] The user records the child's everyday speech using a device. To start recording, the user launches a recording app installed on the device and presses the record button to record the speech. The input is the child's speech, and the output is generated as digital audio data. This data is saved for later analysis.

[0525] Step 2:

[0526] The terminal sends recorded audio data to the server. Before sending, the terminal compresses the audio data and saves it in an appropriate file format (e.g., WAV or MP3). The input is the uncompressed audio data, and the output is the compressed audio data sent to the server using a secure protocol.

[0527] Step 3:

[0528] The server analyzes the audio data received from the terminal. Here, a generative AI model is used to extract features from the audio data. Specifically, the AI ​​model identifies stuttering patterns and frequencies and generates a digital report. Compressed audio data is the input, and the analysis results are obtained as the output.

[0529] Step 4:

[0530] The server automatically generates an individualized treatment plan based on the extracted features. The AI ​​model refers to the analysis results and selects the most suitable training content for the child's speech disorder. The analysis results are the input, and an individualized treatment plan is generated as the output.

[0531] Step 5:

[0532] The terminal notifies the user of the treatment plan from the server. The notified treatment plan is displayed through the user interface. The generated treatment plan is the input, and it is provided to the user in a visible form as output.

[0533] Step 6:

[0534] The user uses a device to conduct training with the infant according to the presented treatment plan. Specifically, this involves performing voice exercises according to on-screen instructions. The treatment plan is the input, and progress data is recorded as the output.

[0535] Step 7:

[0536] The terminal periodically sends recorded progress data to the server. The progress data is formatted and converted into a format easily sent to the server. The input is progress data, and the output is the completion of transmission to the server.

[0537] Step 8:

[0538] The server uses the received progress data to evaluate the effectiveness of the treatment. The AI ​​model is then utilized again to adjust the treatment plan based on the progress. Progress data is the input, evaluation results are obtained as output, and the plan is updated as needed.

[0539] (Application Example 1)

[0540] Next, we will explain Application Example 1. In the following explanation, 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."

[0541] Speech disorders in early childhood, if not addressed appropriately, can affect language abilities in the future. However, conventional methods struggle to efficiently provide training tailored to individual speech characteristics, necessitating specialized support. Furthermore, there is a problem in obtaining appropriate feedback during daily practice at home. Therefore, a system is needed that can provide individualized and effective speech training and evaluate progress.

[0542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0543] In this invention, the server includes means for transmitting voice data acquired by the user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in early childhood, and means for automatically generating an individualized training plan based on the characteristics. This makes it possible to automatically provide individualized speech training based on voice data and support optimal practice.

[0544] An "information processing device" is a computer or other device that acquires audio data, analyzes it, and generates training plans.

[0545] "Voice data" refers to digital audio signals that record speech during early childhood.

[0546] "Speech disorders" refer to symptoms such as pauses in speech and repetition of the same sound that affect the ability to speak fluently.

[0547] "Feature extraction" is the process of identifying and extracting speech patterns and types of speech disorders from audio data.

[0548] A "training plan" refers to a program that includes individualized practice content aimed at improving speech disorders.

[0549] A "human support device" is a device that uses sound and visuals to inform users of the practice content and complements the human instructor.

[0550] "Progress data" refers to information that records the degree of achievement and progress of training.

[0551] An "intelligent processing model" is an artificial intelligence algorithm that enables the analysis of speech data and the generation of training plans.

[0552] This invention is a system aimed at improving speech disorders in early childhood, and it collects and analyzes voice data, generates and provides training plans. The system mainly consists of an information processing device, a portable device, and a human assistance device.

[0553] The information processing device receives audio data and performs speech analysis using an intelligent processing model. For data analysis, artificial intelligence models on Google Cloud AI or Amazon Web Services (AWS) can be used. This allows for the extraction of speech disorder characteristics from the audio data and the generation of an individualized training plan. The generated training plan is then communicated to the user via a portable device.

[0554] The portable device is used by the user to record the infant's speech and transmit it to the information processing device. Furthermore, it displays the training plan visually or audibly to support daily training.

[0555] Human support devices play a role in guiding and instructing users on training content. They provide appropriate feedback to young children through voice and screens.

[0556] As a concrete example, imagine a young child trying to say "I like apples" but stumbling over, saying "I like ri-ri-ringo." The user records this utterance with a portable device and sends it to an information processing device. The information processing device, recognizing the consecutive identical sounds, uses an intelligent processing model to generate a training plan. This plan includes items to practice the smoothness of specific vowel sounds. The training plan is presented to the user via the portable device, enabling daily practice using a human assistance device.

[0557] An example of an input prompt for a generative AI model is, "Analyze the speech patterns in this audio data and propose a specific training plan for improvement."

[0558] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0559] Step 1:

[0560] The user uses a portable device to record the speech of an infant. The input is the infant's utterances, and the output is digitized audio data. The portable device activates its recording function and converts the audio into digital data via the microphone.

[0561] Step 2:

[0562] The portable device transmits recorded audio data to a server. The input is digital audio data, and the output is data transferred to the server. The data is transmitted via the internet using data communication capabilities.

[0563] Step 3:

[0564] The server analyzes the received audio data. The input is audio data, and the output is audio feature information. A generative AI model is used to analyze speech patterns within the audio and extract features such as stuttering patterns.

[0565] Step 4:

[0566] The server generates an individualized training plan based on the analysis results. The input is speech feature information, and the output is the training plan. The planning algorithm automatically generates appropriate practice content according to the extracted features.

[0567] Step 5:

[0568] The server sends the generated training plan to the portable device. The input is the training plan, and the output is the data transferred to the portable device. The training plan information is transmitted using the data communication function.

[0569] Step 6:

[0570] The portable device notifies and displays the training plan to the user. The input is the training plan received from the server, and the output is the information shown to the user via the portable device's screen or audio output. The training content is presented using a screen display or audio output module.

[0571] Step 7:

[0572] The user follows the instructions on the portable device and conducts daily training with the child. The input is training instructions, and the output is actual vocal exercises. Based on the guidance, the user supports the child's pronunciation practice.

[0573] Step 8:

[0574] The portable device records the progress of the training and periodically sends the progress data to the server. The input is the status of the training, and the output is digital progress data. The content of the training is recorded using sensors and timestamps and transmitted to the server via data communication.

[0575] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0576] This invention is a system that combines emotion recognition to comprehensively improve speech disorders in infants. The specific implementation of this system is described below.

[0577] Users record their child's speech using a smartphone or tablet. This audio data is then saved to the device. The device sends this audio data to a server. The server analyzes the audio data and is equipped with an artificial intelligence model and emotion engine to recognize the content of the speech and the emotional state.

[0578] The server's artificial intelligence model extracts features related to speech disorders from the received audio data. This analysis identifies patterns and frequencies of stuttering. Additionally, the server's emotion engine identifies the child's emotional state from the audio data and extracts information corresponding to that state.

[0579] Next, the server automatically generates an individualized treatment plan, taking into account the extracted speech characteristics and emotional states. This treatment plan includes specific training content and adjustments to address the child's emotions. For example, if the child shows anxiety, the plan will include training activities that provide a sense of security.

[0580] The user reviews the treatment plan sent from the server on their device and conducts training tailored to the infant. During training, the device continuously records the infant's voice, and the emotion engine recognizes the infant's emotional state in real time. This recorded data is periodically sent from the device to the server and managed as progress data.

[0581] The server evaluates the effectiveness of the training based on progress data. This evaluation allows for monitoring the progress of treatment and adjusting the plan as needed. The evaluation results are also shared with medical professionals, allowing for expert feedback and intervention. For example, if toddler C becomes emotionally tense when trying to say "t-t-t-fun play," the emotional engine can detect this tension and add training to promote relaxation.

[0582] Thus, in addition to improving speech disorders, the system of the present invention supports the development of infants while addressing emotional changes.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The user records the infant's speech using the device. The audio data is recorded through a dedicated application on the device.

[0586] Step 2:

[0587] The device pre-processes the recorded audio data for emotion recognition and then sends it to the server via secure communication.

[0588] Step 3:

[0589] The server analyzes the received audio data. An artificial intelligence model extracts speech features and identifies stuttering patterns and frequencies.

[0590] Step 4:

[0591] The server uses an emotion engine to identify the child's emotional state from the audio data. Specifically, it analyzes the tone, volume, and intonation of the voice to detect changes in emotion.

[0592] Step 5:

[0593] The server generates an individualized treatment plan based on both speech characteristics and emotional states. This plan incorporates training menus adapted to the emotional state.

[0594] Step 6:

[0595] The server sends the generated treatment plan to the device. The user reviews the plan on the device and implements appropriate training for the infant.

[0596] Step 7:

[0597] During training, the device continuously records the infant's voice data, and the emotion engine recognizes their emotional state in real time. This information is transmitted from the device to the server.

[0598] Step 8:

[0599] The server analyzes progress data received in real time and evaluates the effectiveness of the treatment. Since changes in emotional state are also taken into consideration, more precise feedback is possible.

[0600] Step 9:

[0601] The server shares progress evaluation results with medical professionals. These professionals can provide data-driven feedback and suggest further treatment options. Users can continue their training under the guidance of these professionals.

[0602] (Example 2)

[0603] Next, we will describe Example 2. 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."

[0604] In the recovery process for speech disorders in young children, it is necessary to take into account individual characteristics and emotional states, but conventional systems have difficulty comprehensively handling these elements. Therefore, there is a need for a system that can automatically generate treatment methods that address both the characteristics and emotional aspects of speech disorders, and that can evaluate and adjust their effectiveness in a timely manner.

[0605] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0606] In this invention, the server includes means for using an artificial intelligence engine to analyze voice data and extract features related to speech disorders, means for automatically generating an individualized treatment plan based on the features and emotional state, and means for sharing evaluation results and easily receiving feedback from experts. This enables the provision of individualized treatment and management of its progress.

[0607] "User" refers to a person who uses the system to acquire and provide voice data of infants.

[0608] A "terminal" refers to an electronic device used to record and store voice data and transfer it to a management device.

[0609] The "management device" refers to a central computer that receives, analyzes, and processes voice data transmitted by users.

[0610] "Audio data" refers to digital information that is a recording of a child's speech.

[0611] "Speech disorders" refer to specific abnormalities or delays related to language, such as stuttering or difficulty pronouncing words.

[0612] An "artificial intelligence engine" refers to a program that uses machine learning techniques to analyze the characteristics of speech and recognize and extract patterns of problems.

[0613] "Emotional state" refers to the psychological or emotional state of an infant as estimated from audio data.

[0614] A "treatment plan" refers to a plan designed individually for improving a child's speech based on the results of an analysis of their voice data.

[0615] "Progress data" refers to information collected during the training process, and data that shows the progress and effectiveness of treatment.

[0616] A "specialist" refers to a person who possesses specialized knowledge in medicine or speech therapy and can provide feedback based on evaluation results from the system.

[0617] To implement this invention, a system is required that performs a series of processes, from acquiring and analyzing audio data to generating treatment plans and managing their progress. This system consists of a user, a terminal, and a server.

[0618] Users utilize devices such as smartphones or tablets to record their infants' speech. The recorded audio data is stored digitally on the device's storage. The device incorporates a communication module for sending the audio data to the server, and a secure communication protocol (e.g., HTTPS) is used to ensure the safe transmission of the data.

[0619] The server is equipped with an artificial intelligence engine for analyzing received audio data. This engine is built using common machine learning libraries (e.g., TensorFlow) and extracts features of speech disorders from the audio data. Furthermore, the server can identify the emotional state of infants using an emotion engine. This emotion engine estimates the psychological state of infants by analyzing the intonation and tempo of their speech.

[0620] The server runs a program to automatically generate an individualized treatment plan based on the analyzed speech characteristics and emotional states. This program is written in a programming language such as Python and selects the most suitable content from multiple treatment templates. The generated treatment plan includes content that provides reassurance if the infant shows signs of anxiety.

[0621] For example, a young child might become tense when trying to say "t-t-t-fun play." In this case, the server's emotion engine can detect this tension and add training to encourage relaxation to the plan.

[0622] Users review the treatment plan displayed on the device and provide appropriate speech training to their infants. Progress data recorded during the training process is sent from the device to the server, where its effectiveness is continuously evaluated. The server manages this data and readjusts the treatment plan as needed. This evaluation result is shared with professionals through an appropriate interface, allowing for more effective feedback.

[0623] An example of an input prompt for the generative AI model is: "Based on the speech data of an infant, please identify speech disorders and emotional states, and propose an appropriate treatment plan."

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The user records the infant's speech using a device such as a smartphone or tablet. The input is the infant's speech, and the output is stored as audio data on the device. In this step, the device's microphone is used, and the audio data is converted into a digital format.

[0627] Step 2:

[0628] The terminal sends recorded audio data to the server. The input is the audio data within the terminal, and the output is the data transferred to the server. The terminal uses a secure communication protocol to protect the integrity of the data while transmitting it over the internet.

[0629] Step 3:

[0630] The server analyzes the received audio data. The input is the transmitted audio data, and the output is data that shows the characteristics of speech disorders. The server uses an artificial intelligence model to extract speech features. Specifically, data calculations are performed to identify stuttering patterns and frequencies from the audio signal.

[0631] Step 4:

[0632] The server performs analysis to identify emotional states in parallel with the audio data. The input is the same audio data, and the output is data representing the emotional state of the infant. Here, the emotion engine performs emotional analysis, extracting the psychological state from the intonation and tempo of the voice. An audio analysis algorithm is used in this process.

[0633] Step 5:

[0634] The server generates personalized treatment plans based on speech characteristics and emotional states. The input is analyzed speech characteristics and emotional state data, and the output is a treatment plan incorporating specific training content. The server uses a generation AI model to select the optimal treatment content and automatically create a plan. This involves template selection and customization by the AI ​​model.

[0635] Step 6:

[0636] The user reviews the treatment plan sent from the server on their device and then conducts training for the infant. The input is the treatment plan from the server, and the output is the specific training instructions displayed on the device. The device displays this information on its screen.

[0637] Step 7:

[0638] The device continuously records speech during training and acquires progress data. The input is the speech of the child during training, and the output is an audio recording that is organized as progress data. Here, the device records in real time and continuously collects audio data.

[0639] Step 8:

[0640] The terminal periodically sends recorded progress data to the server. The input is the progress data, and the output is the data transferred to the server. This process is performed via a secure connection.

[0641] Step 9:

[0642] The server evaluates the received progress data and analyzes the effectiveness of the treatment. The input is progress data, and the output is a treatment progress report. AI and data analysis techniques are used to measure the effectiveness of the training and adjust the treatment plan as needed.

[0643] Step 10:

[0644] The server facilitates the sharing of analysis results with medical professionals and provides an environment for easy feedback. The input is the analysis results of treatment effectiveness, and the output is returned as expert feedback. A dedicated online platform is used for this sharing process.

[0645] (Application Example 2)

[0646] Next, we will explain application example 2. In the following explanation, 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."

[0647] Speech-related problems in the elderly and young children include speech disorders and communication difficulties. These problems require appropriate care and treatment, and individualized responses are necessary. Furthermore, there is a lack of systems for effectively assessing progress and intervening as needed. In addition, there is a need for technologies that can address the diversity of speech characteristics associated with emotional changes.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0649] In this invention, the server includes means for transmitting voice data acquired by the user to a management device, means for analyzing the voice data and extracting features related to speech disorders and conversational characteristics, and means for automatically generating an individualized treatment or care plan based on the features. This enables appropriate support and effective intervention to address speech disorders and communication difficulties.

[0650] "Voice data" refers to information that electronically records the content of a user's speech.

[0651] A "management device" is an electronic device used to receive, analyze, and process audio data.

[0652] "Analysis" is the process of extracting important features related to speech from audio data.

[0653] "Speech disorders" refer to impairments in language fluency and psychological speech characteristics that occur in infants and the elderly.

[0654] "Characteristics" refer to patterns and tendencies in speech data that indicate speech disorders or characteristics.

[0655] A "treatment plan" is a set of automatically generated guidelines and procedures designed to improve an individual's speech disorder.

[0656] A "care plan" is a guideline for providing appropriate care based on the conversational characteristics of elderly individuals.

[0657] "Training" refers to specific activities or exercises conducted to improve the user's speech ability.

[0658] "Progress data" refers to information that shows the progress of training or care.

[0659] A "specialist" is a professional who possesses knowledge related to medicine or nursing care.

[0660] "Intervention" refers to specific actions or measures taken to address a particular problem.

[0661] This system primarily consists of devices such as smartphones and tablets, and a server. The user first records the subject's voice data using their device. This voice data is sent to the server via data communication. The server converts the received voice data to text using Google's Speech-to-Text API and other tools. Then, using TensorFlow and other machine learning models, it performs a detailed analysis of speech disorder characteristics and emotional states. This automatically generates treatment and care plans tailored to each individual. The generated plans are then returned to the user's device and used for implementing training and care.

[0662] To track progress, the device continuously records the subject's voice and transmits it to a server. This data is managed as progress data and used to evaluate the effectiveness of treatment and care. If necessary, these evaluation results are shared with medical and care professionals to adjust the plan.

[0663] As a concrete example, when person A speaks in a normal conversation, the device records what they say, and the server analyzes the content to extract the element "I've been feeling tired lately." Based on this, a plan is generated to suggest relaxation activities for person A. An example of a prompt message would be, "Person A seems to be feeling tired lately. What kind of relaxation activities should be suggested?"

[0664] As described above, this system enables efficient processing of voice data and flexible planning tailored to individual circumstances, supporting the improvement of speech disorders and communication problems among the elderly.

[0665] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0666] Step 1:

[0667] The user uses a device to record the subject's voice data. This operation saves the subject's voice as digital data on the device. This data can then be converted from physical voice to digital elements such as pixels, enabling subsequent processing.

[0668] Step 2:

[0669] The device sends the recorded audio data to the server. The device uses a stable network connection to transfer the data. Once the audio data reaches the server, the server receives new data input.

[0670] Step 3:

[0671] The server uses Google's Speech-to-Text API to analyze the received audio data. This API performs data processing to convert the audio data into text data. The resulting text data can be used as output for structural analysis of the spoken content.

[0672] Step 4:

[0673] Text data is analyzed, and TensorFlow is used to analyze speech features and emotional states. The server leverages an AI model to analyze the input text data and derive patterns of speech disorders and emotional states. This output forms the basis for creating specific plans.

[0674] Step 5:

[0675] The server uses an AI model based on the analysis results to automatically generate personalized treatment or care plans. The AI ​​model designs the optimal plan for the user through data calculations and provides the plan's content as output.

[0676] Step 6:

[0677] The server sends the generated personalized plan to the terminal, where the user reviews it. The plan is displayed on the terminal, and the user uses this output to carry out training and care. The terminal invokes UI / UX functions that display this information intuitively.

[0678] Step 7:

[0679] The device continuously records the voice of the person receiving training or care and sends it to the server as new progress data. This data is used as input to provide the server with the progress of the plan and prepare it for evaluation.

[0680] Step 8:

[0681] The server uses progress data to evaluate the effectiveness of treatment and care, and generates the results as output. If necessary, the plan is adjusted, a new plan is generated, and it is sent back to the terminal. The server uses evaluation algorithms to perform data calculations throughout this process.

[0682] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0683] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0684] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0685] [Fourth Embodiment]

[0686] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0687] As shown in Figure 7, the 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.

[0688] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0689] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0690] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0691] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0692] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0693] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0694] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0695] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0696] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0697] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0698] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] This system analyzes speech data to provide personalized treatment plans for speech disorders in young children. The detailed implementation method of the system is described below.

[0700] The user records the infant's everyday speech using a smartphone or other device. The recorded audio data is sent from the device to a server, which acts as a management device. Upon receiving this audio data, the server analyzes it using its built-in artificial intelligence model. As a result of the analysis, characteristics related to the infant's speech, specifically stuttering patterns and frequency, are extracted.

[0701] The server then automatically generates a personalized treatment plan based on the extracted characteristics. This plan includes training content and approaches to improve the child's specific speech disorder. The generated treatment plan is notified to the user via the device, and daily training is guided.

[0702] The user conducts the designated training with the infant according to the treatment plan provided on the device. The progress of the training is recorded by the device and periodically sent to the server as progress data. The server evaluates the received progress data and analyzes the effectiveness of the treatment. Based on the evaluation results, the treatment plan may be adjusted as needed.

[0703] Furthermore, the server shares the evaluation results of the progress data with medical professionals. This allows professionals to assess the need for improvements to the treatment plan or direct guidance. If necessary, professional intervention is suggested, and the user can receive additional support.

[0704] As a concrete example, consider a situation where toddler B tries to say "A red car is coming" but stumbles and says "A red red car is coming." The user records B's speech and sends it to the server. The server analyzes the audio and recognizes that there is a repetition of the same sound. Based on this pattern, the server generates a plan that includes training menus to help B pronounce the initial sounds of words smoothly. The user uses this plan to train B daily, and the treatment progresses while regularly checking B's progress.

[0705] The following describes the processing flow.

[0706] Step 1:

[0707] The user records the infant's speech using a smartphone. The recorded audio data is saved to an application on the device.

[0708] Step 2:

[0709] The terminal prepares to send the recorded audio data to the database. The transmission is made to the server using a secure protocol.

[0710] Step 3:

[0711] The server analyzes the received audio data. Using an artificial intelligence model, it extracts features related to speech disorders from the audio data. Specifically, it identifies stuttering patterns, frequency, and the number of times sounds are repeated.

[0712] Step 4:

[0713] The server automatically generates an individualized treatment plan based on the analysis results. This treatment plan includes specific training content and guidance policies.

[0714] Step 5:

[0715] The server sends the generated treatment plan to the user's device. The user can receive and review this treatment plan using an application on their device.

[0716] Step 6:

[0717] The user conducts training with the infant according to the provided treatment plan. The user records the progress of the training and the infant's responses.

[0718] Step 7:

[0719] The terminal periodically uploads recorded training progress data to the server. This allows the server to track the latest progress.

[0720] Step 8:

[0721] The server analyzes the received progress data and evaluates the effectiveness of the treatment. The evaluation results are used to determine whether the training program is being followed appropriately.

[0722] Step 9:

[0723] The server shares the results of the effectiveness analysis with medical professionals. These professionals can use this data to assess the need for further treatment and propose interventions.

[0724] (Example 1)

[0725] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] Speech disorders in young children present challenges in selecting appropriate treatments and tracking their progress. Traditional methods struggle to provide individualized treatment plans quickly and effectively, and data collection and analysis for accurately evaluating treatment effectiveness are insufficient. Therefore, there is a need to experimentally implement more effective and sustainable treatments.

[0727] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0728] In this invention, the server includes means for transmitting voice data acquired by a user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in infants, and means for automatically generating an individualized treatment plan based on the characteristics. This makes it possible to quickly provide an individualized treatment plan for speech disorders in infants and to quantitatively evaluate its effectiveness.

[0729] "Audio data" refers to information recorded digitally using a recording device or similar equipment, capturing the sounds spoken by a young child.

[0730] An "information processing device" is a server or computer system that receives, analyzes, and processes audio data.

[0731] "Speech disorder" refers to a condition in which young children have difficulty pronouncing words as intended, and specifically includes stuttering.

[0732] "Methods for extracting features" refer to methods for identifying patterns and frequencies of speech disorders from audio data and extracting them as analysis results.

[0733] An "individualized treatment plan" is a set of training programs and approaches designed to improve a specific child's speech disorder based on identified characteristics.

[0734] "Educational progress data" refers to information used to record the progress of training based on a treatment plan and to evaluate the effectiveness of the treatment.

[0735] A "generative AI model" is an artificial intelligence system that implements machine learning algorithms used to analyze audio data.

[0736] This system is designed to treat speech disorders in infants. Users record their infant's everyday speech using a device such as a smartphone. This recorded audio data is then transmitted from the device to a server acting as an information processing unit.

[0737] The server uses a generative AI model to analyze the received audio data. This AI model extracts features such as stuttering patterns and frequencies from the audio data. The extracted data is then generated as a digital report.

[0738] Next, the server automatically generates an individualized treatment plan based on the extracted characteristics. This treatment plan includes training content and approaches to improve the child's speech impairment. This generated treatment plan is then communicated to the user via the device.

[0739] The user conducts training with the infant according to the educational plan displayed on the device. The progress of the training is recorded on the device and periodically sent to the server as educational progress data. Based on this data, the server can evaluate the effectiveness of the treatment and adjust the treatment plan as needed.

[0740] As a concrete example, consider a scenario where a toddler tries to say "The blue dog is running" but stumbles and says "Oh, the blue dog is running." When the user records this utterance and sends it to the server, the server analyzes the audio and recognizes the repetition of the same sound. Based on this pattern, the server generates a treatment plan that includes training to pronounce the initial sounds of words smoothly. The user then trains daily based on this plan, and the content of the training is adjusted according to their progress, resulting in effective treatment.

[0741] Example of a prompt:

[0742] "We record infant speech and transmit the audio data. We analyze stuttering patterns and generate an appropriate treatment plan."

[0743] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0744] Step 1:

[0745] The user records the child's everyday speech using a device. To start recording, the user launches a recording app installed on the device and presses the record button to record the speech. The input is the child's speech, and the output is generated as digital audio data. This data is saved for later analysis.

[0746] Step 2:

[0747] The terminal sends recorded audio data to the server. Before sending, the terminal compresses the audio data and saves it in an appropriate file format (e.g., WAV or MP3). The input is the uncompressed audio data, and the output is the compressed audio data sent to the server using a secure protocol.

[0748] Step 3:

[0749] The server analyzes the audio data received from the terminal. Here, a generative AI model is used to extract features from the audio data. Specifically, the AI ​​model identifies stuttering patterns and frequencies and generates a digital report. Compressed audio data is the input, and the analysis results are obtained as the output.

[0750] Step 4:

[0751] The server automatically generates an individualized treatment plan based on the extracted features. The AI ​​model refers to the analysis results and selects the most suitable training content for the child's speech disorder. The analysis results are the input, and an individualized treatment plan is generated as the output.

[0752] Step 5:

[0753] The terminal notifies the user of the treatment plan from the server. The notified treatment plan is displayed through the user interface. The generated treatment plan is the input, and it is provided to the user in a visible form as output.

[0754] Step 6:

[0755] The user uses a device to conduct training with the infant according to the presented treatment plan. Specifically, this involves performing voice exercises according to on-screen instructions. The treatment plan is the input, and progress data is recorded as the output.

[0756] Step 7:

[0757] The terminal periodically sends recorded progress data to the server. The progress data is formatted and converted into a format easily sent to the server. The input is progress data, and the output is the completion of transmission to the server.

[0758] Step 8:

[0759] The server uses the received progress data to evaluate the effectiveness of the treatment. The AI ​​model is then utilized again to adjust the treatment plan based on the progress. Progress data is the input, evaluation results are obtained as output, and the plan is updated as needed.

[0760] (Application Example 1)

[0761] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] Speech disorders in early childhood, if not addressed appropriately, can affect language abilities in the future. However, conventional methods struggle to efficiently provide training tailored to individual speech characteristics, necessitating specialized support. Furthermore, there is a problem in obtaining appropriate feedback during daily practice at home. Therefore, a system is needed that can provide individualized and effective speech training and evaluate progress.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0764] In this invention, the server includes means for transmitting voice data acquired by the user to an information processing device, means for analyzing the voice data and extracting characteristics related to speech disorders in early childhood, and means for automatically generating an individualized training plan based on the characteristics. This makes it possible to automatically provide individualized speech training based on voice data and support optimal practice.

[0765] An "information processing device" is a computer or other device that acquires audio data, analyzes it, and generates training plans.

[0766] "Voice data" refers to digital audio signals that record speech during early childhood.

[0767] "Speech disorders" refer to symptoms such as pauses in speech and repetition of the same sound that affect the ability to speak fluently.

[0768] "Feature extraction" is the process of identifying and extracting speech patterns and types of speech disorders from audio data.

[0769] A "training plan" refers to a program that includes individualized practice content aimed at improving speech disorders.

[0770] A "human support device" is a device that uses sound and visuals to inform users of the practice content and complements the human instructor.

[0771] "Progress data" refers to information that records the degree of achievement and progress of training.

[0772] An "intelligent processing model" is an artificial intelligence algorithm that enables the analysis of speech data and the generation of training plans.

[0773] This invention is a system aimed at improving speech disorders in early childhood, and it collects and analyzes voice data, generates and provides training plans. The system mainly consists of an information processing device, a portable device, and a human assistance device.

[0774] The information processing device receives audio data and performs speech analysis using an intelligent processing model. For data analysis, artificial intelligence models on Google Cloud AI or Amazon Web Services (AWS) can be used. This allows for the extraction of speech disorder characteristics from the audio data and the generation of an individualized training plan. The generated training plan is then communicated to the user via a portable device.

[0775] The portable device is used by the user to record the infant's speech and transmit it to the information processing device. Furthermore, it displays the training plan visually or audibly to support daily training.

[0776] Human support devices play a role in guiding and instructing users on training content. They provide appropriate feedback to young children through voice and screens.

[0777] As a concrete example, imagine a young child trying to say "I like apples" but stumbling over, saying "I like ri-ri-ringo." The user records this utterance with a portable device and sends it to an information processing device. The information processing device, recognizing the consecutive identical sounds, uses an intelligent processing model to generate a training plan. This plan includes items to practice the smoothness of specific vowel sounds. The training plan is presented to the user via the portable device, enabling daily practice using a human assistance device.

[0778] An example of an input prompt for a generative AI model is, "Analyze the speech patterns in this audio data and propose a specific training plan for improvement."

[0779] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0780] Step 1:

[0781] The user uses a portable device to record the speech of an infant. The input is the infant's utterances, and the output is digitized audio data. The portable device activates its recording function and converts the audio into digital data via the microphone.

[0782] Step 2:

[0783] The portable device transmits recorded audio data to a server. The input is digital audio data, and the output is data transferred to the server. The data is transmitted via the internet using data communication capabilities.

[0784] Step 3:

[0785] The server analyzes the received audio data. The input is audio data, and the output is audio feature information. A generative AI model is used to analyze speech patterns within the audio and extract features such as stuttering patterns.

[0786] Step 4:

[0787] The server generates an individualized training plan based on the analysis results. The input is speech feature information, and the output is the training plan. The planning algorithm automatically generates appropriate practice content according to the extracted features.

[0788] Step 5:

[0789] The server sends the generated training plan to the portable device. The input is the training plan, and the output is the data transferred to the portable device. The training plan information is transmitted using the data communication function.

[0790] Step 6:

[0791] The portable device notifies and displays the training plan to the user. The input is the training plan received from the server, and the output is the information shown to the user via the portable device's screen or audio output. The training content is presented using a screen display or audio output module.

[0792] Step 7:

[0793] The user follows the instructions on the portable device and conducts daily training with the child. The input is training instructions, and the output is actual vocal exercises. Based on the guidance, the user supports the child's pronunciation practice.

[0794] Step 8:

[0795] The portable device records the progress of the training and periodically sends the progress data to the server. The input is the status of the training, and the output is digital progress data. The content of the training is recorded using sensors and timestamps and transmitted to the server via data communication.

[0796] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0797] This invention is a system that combines emotion recognition to comprehensively improve speech disorders in infants. The specific implementation of this system is described below.

[0798] Users record their child's speech using a smartphone or tablet. This audio data is then saved to the device. The device sends this audio data to a server. The server analyzes the audio data and is equipped with an artificial intelligence model and emotion engine to recognize the content of the speech and the emotional state.

[0799] The server's artificial intelligence model extracts features related to speech disorders from the received audio data. This analysis identifies patterns and frequencies of stuttering. Additionally, the server's emotion engine identifies the child's emotional state from the audio data and extracts information corresponding to that state.

[0800] Next, the server automatically generates an individualized treatment plan, taking into account the extracted speech characteristics and emotional states. This treatment plan includes specific training content and adjustments to address the child's emotions. For example, if the child shows anxiety, the plan will include training activities that provide a sense of security.

[0801] The user reviews the treatment plan sent from the server on their device and conducts training tailored to the infant. During training, the device continuously records the infant's voice, and the emotion engine recognizes the infant's emotional state in real time. This recorded data is periodically sent from the device to the server and managed as progress data.

[0802] The server evaluates the effectiveness of the training based on progress data. This evaluation allows for monitoring the progress of treatment and adjusting the plan as needed. The evaluation results are also shared with medical professionals, allowing for expert feedback and intervention. For example, if toddler C becomes emotionally tense when trying to say "t-t-t-fun play," the emotional engine can detect this tension and add training to promote relaxation.

[0803] Thus, in addition to improving speech disorders, the system of the present invention supports the development of infants while addressing emotional changes.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The user records the infant's speech using the device. The audio data is recorded through a dedicated application on the device.

[0807] Step 2:

[0808] The device pre-processes the recorded audio data for emotion recognition and then sends it to the server via secure communication.

[0809] Step 3:

[0810] The server analyzes the received audio data. An artificial intelligence model extracts speech features and identifies stuttering patterns and frequencies.

[0811] Step 4:

[0812] The server uses an emotion engine to identify the child's emotional state from the audio data. Specifically, it analyzes the tone, volume, and intonation of the voice to detect changes in emotion.

[0813] Step 5:

[0814] The server generates an individualized treatment plan based on both speech characteristics and emotional states. This plan incorporates training menus adapted to the emotional state.

[0815] Step 6:

[0816] The server sends the generated treatment plan to the device. The user reviews the plan on the device and implements appropriate training for the infant.

[0817] Step 7:

[0818] During training, the device continuously records the infant's voice data, and the emotion engine recognizes their emotional state in real time. This information is transmitted from the device to the server.

[0819] Step 8:

[0820] The server analyzes progress data received in real time and evaluates the effectiveness of the treatment. Since changes in emotional state are also taken into consideration, more precise feedback is possible.

[0821] Step 9:

[0822] The server shares progress evaluation results with medical professionals. These professionals can provide data-driven feedback and suggest further treatment options. Users can continue their training under the guidance of these professionals.

[0823] (Example 2)

[0824] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0825] In the recovery process for speech disorders in young children, it is necessary to take into account individual characteristics and emotional states, but conventional systems have difficulty comprehensively handling these elements. Therefore, there is a need for a system that can automatically generate treatment methods that address both the characteristics and emotional aspects of speech disorders, and that can evaluate and adjust their effectiveness in a timely manner.

[0826] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0827] In this invention, the server includes means for using an artificial intelligence engine to analyze voice data and extract features related to speech disorders, means for automatically generating an individualized treatment plan based on the features and emotional state, and means for sharing evaluation results and easily receiving feedback from experts. This enables the provision of individualized treatment and management of its progress.

[0828] "User" refers to a person who uses the system to acquire and provide voice data of infants.

[0829] A "terminal" refers to an electronic device used to record and store voice data and transfer it to a management device.

[0830] The "management device" refers to a central computer that receives, analyzes, and processes voice data transmitted by users.

[0831] "Audio data" refers to digital information that is a recording of a child's speech.

[0832] "Speech disorders" refer to specific abnormalities or delays related to language, such as stuttering or difficulty pronouncing words.

[0833] An "artificial intelligence engine" refers to a program that uses machine learning techniques to analyze the characteristics of speech and recognize and extract patterns of problems.

[0834] "Emotional state" refers to the psychological or emotional state of an infant as estimated from audio data.

[0835] A "treatment plan" refers to a plan designed individually for improving a child's speech based on the results of an analysis of their voice data.

[0836] "Progress data" refers to information collected during the training process, and data that shows the progress and effectiveness of treatment.

[0837] A "specialist" refers to a person who possesses specialized knowledge in medicine or speech therapy and can provide feedback based on evaluation results from the system.

[0838] To implement this invention, a system is required that performs a series of processes, from acquiring and analyzing audio data to generating treatment plans and managing their progress. This system consists of a user, a terminal, and a server.

[0839] Users utilize devices such as smartphones or tablets to record their infants' speech. The recorded audio data is stored digitally on the device's storage. The device incorporates a communication module for sending the audio data to the server, and a secure communication protocol (e.g., HTTPS) is used to ensure the safe transmission of the data.

[0840] The server is equipped with an artificial intelligence engine for analyzing received audio data. This engine is built using common machine learning libraries (e.g., TensorFlow) and extracts features of speech disorders from the audio data. Furthermore, the server can identify the emotional state of infants using an emotion engine. This emotion engine estimates the psychological state of infants by analyzing the intonation and tempo of their speech.

[0841] The server runs a program to automatically generate an individualized treatment plan based on the analyzed speech characteristics and emotional states. This program is written in a programming language such as Python and selects the most suitable content from multiple treatment templates. The generated treatment plan includes content that provides reassurance if the infant shows signs of anxiety.

[0842] For example, a young child might become tense when trying to say "t-t-t-fun play." In this case, the server's emotion engine can detect this tension and add training to encourage relaxation to the plan.

[0843] Users review the treatment plan displayed on the device and provide appropriate speech training to their infants. Progress data recorded during the training process is sent from the device to the server, where its effectiveness is continuously evaluated. The server manages this data and readjusts the treatment plan as needed. This evaluation result is shared with professionals through an appropriate interface, allowing for more effective feedback.

[0844] An example of an input prompt for the generative AI model is: "Based on the speech data of an infant, please identify speech disorders and emotional states, and propose an appropriate treatment plan."

[0845] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0846] Step 1:

[0847] The user records the infant's speech using a device such as a smartphone or tablet. The input is the infant's speech, and the output is stored as audio data on the device. In this step, the device's microphone is used, and the audio data is converted into a digital format.

[0848] Step 2:

[0849] The terminal sends recorded audio data to the server. The input is the audio data within the terminal, and the output is the data transferred to the server. The terminal uses a secure communication protocol to protect the integrity of the data while transmitting it over the internet.

[0850] Step 3:

[0851] The server analyzes the received audio data. The input is the transmitted audio data, and the output is data that shows the characteristics of speech disorders. The server uses an artificial intelligence model to extract speech features. Specifically, data calculations are performed to identify stuttering patterns and frequencies from the audio signal.

[0852] Step 4:

[0853] The server performs analysis to identify emotional states in parallel with the audio data. The input is the same audio data, and the output is data representing the emotional state of the infant. Here, the emotion engine performs emotional analysis, extracting the psychological state from the intonation and tempo of the voice. An audio analysis algorithm is used in this process.

[0854] Step 5:

[0855] The server generates personalized treatment plans based on speech characteristics and emotional states. The input is analyzed speech characteristics and emotional state data, and the output is a treatment plan incorporating specific training content. The server uses a generation AI model to select the optimal treatment content and automatically create a plan. This involves template selection and customization by the AI ​​model.

[0856] Step 6:

[0857] The user reviews the treatment plan sent from the server on their device and then conducts training for the infant. The input is the treatment plan from the server, and the output is the specific training instructions displayed on the device. The device displays this information on its screen.

[0858] Step 7:

[0859] The device continuously records speech during training and acquires progress data. The input is the speech of the child during training, and the output is an audio recording that is organized as progress data. Here, the device records in real time and continuously collects audio data.

[0860] Step 8:

[0861] The terminal periodically sends recorded progress data to the server. The input is the progress data, and the output is the data transferred to the server. This process is performed via a secure connection.

[0862] Step 9:

[0863] The server evaluates the received progress data and analyzes the effectiveness of the treatment. The input is progress data, and the output is a treatment progress report. AI and data analysis techniques are used to measure the effectiveness of the training and adjust the treatment plan as needed.

[0864] Step 10:

[0865] The server facilitates the sharing of analysis results with medical professionals and provides an environment for easy feedback. The input is the analysis results of treatment effectiveness, and the output is returned as expert feedback. A dedicated online platform is used for this sharing process.

[0866] (Application Example 2)

[0867] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0868] Speech-related problems in the elderly and young children include speech disorders and communication difficulties. These problems require appropriate care and treatment, and individualized responses are necessary. Furthermore, there is a lack of systems for effectively assessing progress and intervening as needed. In addition, there is a need for technologies that can address the diversity of speech characteristics associated with emotional changes.

[0869] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0870] In this invention, the server includes means for transmitting voice data acquired by the user to a management device, means for analyzing the voice data and extracting features related to speech disorders and conversational characteristics, and means for automatically generating an individualized treatment or care plan based on the features. This enables appropriate support and effective intervention to address speech disorders and communication difficulties.

[0871] "Voice data" refers to information that electronically records the content of a user's speech.

[0872] A "management device" is an electronic device used to receive, analyze, and process audio data.

[0873] "Analysis" is the process of extracting important features related to speech from audio data.

[0874] "Speech disorders" refer to impairments in language fluency and psychological speech characteristics that occur in infants and the elderly.

[0875] "Characteristics" refer to patterns and tendencies in speech data that indicate speech disorders or characteristics.

[0876] A "treatment plan" is a set of automatically generated guidelines and procedures designed to improve an individual's speech disorder.

[0877] A "care plan" is a guideline for providing appropriate care based on the conversational characteristics of elderly individuals.

[0878] "Training" refers to specific activities or exercises conducted to improve the user's speech ability.

[0879] "Progress data" refers to information that shows the progress of training or care.

[0880] A "specialist" is a professional who possesses knowledge related to medicine or nursing care.

[0881] "Intervention" refers to specific actions or measures taken to address a particular problem.

[0882] This system primarily consists of devices such as smartphones and tablets, and a server. The user first records the subject's voice data using their device. This voice data is sent to the server via data communication. The server converts the received voice data to text using Google's Speech-to-Text API and other tools. Then, using TensorFlow and other machine learning models, it performs a detailed analysis of speech disorder characteristics and emotional states. This automatically generates treatment and care plans tailored to each individual. The generated plans are then returned to the user's device and used for implementing training and care.

[0883] To track progress, the device continuously records the subject's voice and transmits it to a server. This data is managed as progress data and used to evaluate the effectiveness of treatment and care. If necessary, these evaluation results are shared with medical and care professionals to adjust the plan.

[0884] As a concrete example, when person A speaks in a normal conversation, the device records what they say, and the server analyzes the content to extract the element "I've been feeling tired lately." Based on this, a plan is generated to suggest relaxation activities for person A. An example of a prompt message would be, "Person A seems to be feeling tired lately. What kind of relaxation activities should be suggested?"

[0885] As described above, this system enables efficient processing of voice data and flexible planning tailored to individual circumstances, supporting the improvement of speech disorders and communication problems among the elderly.

[0886] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0887] Step 1:

[0888] The user uses a device to record the subject's voice data. This operation saves the subject's voice as digital data on the device. This data can then be converted from physical voice to digital elements such as pixels, enabling subsequent processing.

[0889] Step 2:

[0890] The device sends the recorded audio data to the server. The device uses a stable network connection to transfer the data. Once the audio data reaches the server, the server receives new data input.

[0891] Step 3:

[0892] The server uses Google's Speech-to-Text API to analyze the received audio data. This API performs data processing to convert the audio data into text data. The resulting text data can be used as output for structural analysis of the spoken content.

[0893] Step 4:

[0894] Text data is analyzed, and TensorFlow is used to analyze speech features and emotional states. The server leverages an AI model to analyze the input text data and derive patterns of speech disorders and emotional states. This output forms the basis for creating specific plans.

[0895] Step 5:

[0896] The server uses an AI model based on the analysis results to automatically generate personalized treatment or care plans. The AI ​​model designs the optimal plan for the user through data calculations and provides the plan's content as output.

[0897] Step 6:

[0898] The server sends the generated personalized plan to the terminal, where the user reviews it. The plan is displayed on the terminal, and the user uses this output to carry out training and care. The terminal invokes UI / UX functions that display this information intuitively.

[0899] Step 7:

[0900] The device continuously records the voice of the person receiving training or care and sends it to the server as new progress data. This data is used as input to provide the server with the progress of the plan and prepare it for evaluation.

[0901] Step 8:

[0902] The server uses progress data to evaluate the effectiveness of treatment and care, and generates the results as output. If necessary, the plan is adjusted, a new plan is generated, and it is sent back to the terminal. The server uses evaluation algorithms to perform data calculations throughout this process.

[0903] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0904] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0905] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0906] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0907] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0908] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0909] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0910] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0911] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0912] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0913] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0914] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0915] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0916] 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.

[0917] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0918] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0919] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0920] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0921] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0922] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0923] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0924] The following is further disclosed regarding the embodiments described above.

[0925] (Claim 1)

[0926] A means for transmitting voice data acquired by the user to a management device,

[0927] A means for analyzing the aforementioned audio data and extracting characteristics related to speech disorders in infants,

[0928] A means for automatically generating an individualized treatment plan based on the aforementioned characteristics,

[0929] A means of presenting the aforementioned treatment plan to the user and supporting the training,

[0930] A means of recording training progress data and using that data to evaluate the therapeutic effect,

[0931] A means of sharing evaluation results with medical professionals and proposing interventions as needed,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, characterized in that the management device includes an artificial intelligence model for analyzing voice data and generating treatment plans.

[0935] (Claim 3)

[0936] The system according to claim 1, characterized in that the progress data of the training is recorded by the user's terminal device and periodically transmitted to the management device.

[0937] "Example 1"

[0938] (Claim 1)

[0939] A means for transmitting audio data acquired by the user to an information processing device,

[0940] A means for analyzing the aforementioned audio data and extracting characteristics related to speech disorders in infants,

[0941] A means for automatically generating an individualized treatment plan based on the aforementioned characteristics,

[0942] A means of presenting the aforementioned treatment plan to the user and supporting their education,

[0943] A means of recording educational progress data and using that data to evaluate treatment effectiveness,

[0944] A means of sharing evaluation results with medical professionals and proposing interventions as needed,

[0945] A means for verifying the integrity of audio data and securely transmitting compressed data to an information processing device,

[0946] A method for creating digital reports from analysis results using an AI model,

[0947] A means of adjusting the educational plan according to progress,

[0948] A system that includes this.

[0949] (Claim 2)

[0950] The system according to claim 1, characterized in that the information processing device includes a generative AI model for analyzing voice data and generating a treatment plan.

[0951] (Claim 3)

[0952] The system according to claim 1, characterized in that the progress data of the education is recorded by the user's terminal device and periodically transmitted to the information processing device.

[0953] "Application Example 1"

[0954] (Claim 1)

[0955] A means for transmitting audio data acquired by the user to an information processing device,

[0956] A means for analyzing the aforementioned audio data and extracting characteristics related to speech disorders in early childhood,

[0957] A means for automatically generating an individualized training plan based on the aforementioned characteristics,

[0958] A means for presenting the aforementioned training plan to the user and operating a human support device to assist in practice,

[0959] A means of recording practice progress data and using that data to evaluate the therapeutic effect,

[0960] A means of sharing evaluation results with medical professionals and proposing assistance as needed,

[0961] A system that includes this.

[0962] (Claim 2)

[0963] The system according to claim 1, characterized in that the information processing device includes an intelligent processing model for analyzing speech data and generating a training plan.

[0964] (Claim 3)

[0965] The system according to claim 1, characterized in that the progress data of the practice is recorded by the user's portable device and periodically transmitted to the information processing device.

[0966] "Example 2 of combining an emotion engine"

[0967] (Claim 1)

[0968] A means for saving voice data acquired by the user to a terminal and transmitting it to a management device,

[0969] A means for using an artificial intelligence engine to analyze the aforementioned voice data and extract features related to speech disorders,

[0970] A means for automatically generating an individualized treatment plan based on the aforementioned characteristics and emotional state,

[0971] A means of presenting the aforementioned treatment plan on the user's terminal and supporting speech training,

[0972] A means for recording progress data and emotional changes during training, and for evaluating the therapeutic effect based on that data,

[0973] A means to share evaluation results and easily receive feedback from experts,

[0974] A system that includes this.

[0975] (Claim 2)

[0976] The system according to claim 1, characterized in that the management device includes an artificial intelligence model for analyzing voice data and identifying emotional states.

[0977] (Claim 3)

[0978] The system according to claim 1, characterized in that the progress data of the training is recorded by a communication device used by the user and periodically transmitted to the management device.

[0979] "Application example 2 when combining with an emotional engine"

[0980] (Claim 1)

[0981] A means for transmitting voice data acquired by the user to a management device,

[0982] A means for analyzing the aforementioned audio data and extracting features related to speech disorders in infants and conversational characteristics of the elderly,

[0983] A means for automatically generating an individualized treatment or care plan based on the aforementioned characteristics,

[0984] The aforementioned plan is presented to the user, and means of supporting training or care are provided.

[0985] A means of recording training or care progress data and using that data to evaluate its effectiveness,

[0986] A means of sharing evaluation results with experts and proposing interventions as needed,

[0987] A system that includes this.

[0988] (Claim 2)

[0989] The system according to claim 1, characterized in that the management device includes an artificial intelligence model for analyzing voice data and generating plans.

[0990] (Claim 3)

[0991] The system according to claim 1, characterized in that the progress data is recorded by the user's terminal device and periodically transmitted to the management device. [Explanation of symbols]

[0992] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for transmitting voice data acquired by the user to a management device, A means for analyzing the aforementioned audio data and extracting characteristics related to speech disorders in infants, A means for automatically generating an individualized treatment plan based on the aforementioned characteristics, A means of presenting the aforementioned treatment plan to the user and supporting the training, A means of recording training progress data and using that data to evaluate the therapeutic effect, A means of sharing evaluation results with medical professionals and proposing interventions as needed, A system that includes this.

2. The system according to claim 1, characterized in that the management device includes an artificial intelligence model for analyzing voice data and generating treatment plans.

3. The system according to claim 1, characterized in that the progress data of the training is recorded by the user's terminal device and periodically transmitted to the management device.

Images