Interactive education device and method using artificial intelligence to guide

Abstract

An interactive guidance device (100) and method are provided. The device (100) comprises a sensor, an input device and an output device configured on the body of the device (100) for detecting, receiving user input and generating output, respectively. The input device may include a touch sensitive button (106), a microphone (108), and a near field communication (NFC) reader (110). The sensor and the output device may include an accelerometer (116) and a speaker (112), respectively. The device (100) may receive input as text or speech from a user, convert the speech input into text by a contextual search (208) based on a large language model (214) method, simulate a dialog to achieve interactive guidance, and generate an output in text or speech form by an output device. The power saving mode may be deactivated when the device (100) is in an idle state for more than a preset time.

Description

Technical Field

[0001] This invention relates to the field of boot tools. More specifically, this invention relates to an interactive boot device and method.

[0002] Background Information

[0003] The background information contains information that helps in understanding this disclosure. The information provided herein does not constitute an admission of prior art, nor does it imply any connection to the disclosure currently claimed, or that any express or implied references to publications constitute prior art.

[0004] Early childhood learning has a crucial impact on a person's overall intellectual and emotional development. Toys are an indispensable part of childhood. Therefore, many teaching and knowledge-transfer guidance tools that incorporate toys exist.

[0005] Some teaching tools include: toys that play pre-recorded content, toys with telematics applications, educational mobile applications, IoT toys, and personalized voice assistants for children. Early childhood learning primarily occurs through interaction with people and the environment. Existing teaching methods lack interactive components that promote learning. Children may quickly lose interest due to the limited interactivity of toys, limiting their engagement and learning potential. With the development of generative artificial intelligence (AI), especially advancements in large language models, generating original content to simulate human-like dialogue has become possible. Using AI technology, computers can automatically perform tasks such as: high-precision speech-to-text and text-to-speech conversion, multilingual text translation, and conversion of one's own voice (source voice) to another's voice (target voice).

[0006] Therefore, there is a great need to develop interactive guidance solutions that apply current AI technology to the field of modern education.

[0007] While educational mobile apps offer learning opportunities, they often require screen time and limit physical playtime. They lack the tactile engagement and personalized interaction of physical toys, hindering interactive learning and the development of emotional bonds. Therefore, there is an urgent need to integrate digital technology with physical toys to stimulate cognitive and sensory development.

[0008] US Patent No. 11663182 discloses an AI toy system, method, and apparatus with enhanced conversational abilities and personality development. This AI toy uses user profiles and personality profiles built based on user interaction and external media input to determine responses to stimuli. By combining semantic interaction technologies such as Natural Language Processing (NLP) with the profile data, it develops AI personality and conversational abilities. However, this toy only provides voice question-and-answer interaction and may lack interactive learning and game functions.

[0009] Chinese Patent No. 2717504Y discloses an interactive dynamic toy. The toy's main body is equipped with a camera and a playback device, allowing users to freely record and select desired sounds and images for playback. Sensors distributed throughout the toy's main body input different control commands into a control processing unit, which drives the playback device to execute pre-recorded corresponding echo actions, thus producing an interactive effect. The toy's main body is also equipped with a signal comparison processing unit, which can analyze and compare input signals and execute specific echoes, enhancing the interactive experience and language learning functions. Although this device allows parents to pre-record sounds for later playback, the selection of pre-recorded stories or sounds is limited, potentially restricting children's participation and learning potential. Therefore, there is an urgent need to provide real-time interactive and adaptive functions based on children's interests, and a method that is neither found in the aforementioned prior art nor common knowledge in the field is needed to enhance children's creativity and family bonds.

[0010] Chinese Patent No. 215202006U discloses a robot device capable of customizing simulated human voices. This device belongs to the field of intelligent robot technology and includes a CPU. The CPU is connected to a distance sensor module, a light sensor module, a temperature sensor module, a voice playback module, a power management module, an LED, a storage module, and a voice synthesis module. The voice synthesis module connects to a voice recognition module for voice recognition, and the voice recognition module connects to a network communication module. The voice recognition module, through the network communication module, connects to a voice acquisition module. This invention preprocesses the collected background sound via a toy terminal using a WIFI or 5G bridge, and then utilizes the cloud-based voice processing server cluster capabilities of the voice recognition module to achieve deep voice recognition and analysis, completing voice customization. It also synthesizes audio highly similar to the parent's voice using the parent's voiceprint features to play text information for the child. However, this device only focuses on voice stimulation and lacks natural dialogue between the user and the device. Therefore, there is an urgent need to provide a personalized and emotionally resonant learning experience, enhancing parent-child emotional connection through natural dialogue.

[0011] There is a need for a technological solution that combines cutting-edge technologies such as artificial intelligence, the Internet of Things, and emotional resonance with teaching methods to shape entirely new ways of learning, promote child development and strengthen family relationships in a deeply innovative way, thereby generating significant technological effects. Summary of the Invention

[0012] Several objectives of the present invention are listed below, and at least one embodiment satisfies these objectives.

[0013] One object of the present invention is to provide an interactive guidance device and method.

[0014] Another objective of this invention is to integrate advances in generative artificial intelligence (AI) to simulate and guide relevant interactive situation-specific dialogues, providing personalized dialogues and storytelling presented in the voices of parents or caregivers, fostering emotional bonds, strengthening family connections, and enriching educational interactions.

[0015] The present invention also aims to provide an interactive learning toy system and method integrating NFC interaction, which guides children on an educational journey that matches their interests through intuitive tactile theme selection.

[0016] A further objective of this invention is to provide a cloud-based interactive learning toy system and method that allows users to send personalized messages, stories, and songs, thereby enhancing the educational and emotional value of the toys.

[0017] Accordingly, the above objectives can be achieved by following the teachings of this invention. This invention relates to an interactive guidance device, characterized in that the device comprises: a main body; one or more input devices for receiving user input, wherein the one or more input devices are disposed on the main body; one or more output devices for generating output from the device, wherein the one or more output devices are disposed on the main body; one or more sensors for detecting user input, wherein the one or more sensors are disposed on the main body; at least one processor communicatively connected to one or more computing devices, wherein one or more users operate the computing devices and are connected to the device via a network; and a memory operatively coupled to the at least one processor, the memory storing executable instructions that, when executed by the at least one processor, cause the at least one processor to perform the following operations: activating the device to enter a running mode when one or more input devices and one or more sensors detect input; receiving input through one or more input devices; determining output based on the input through one or more methods; and generating output through one or more output devices. Attached Figure Description

[0018] The accompanying drawings are intended to further illustrate the present disclosure and are incorporated as part of the specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, illustrate the principles of the present disclosure.

[0019] In the illustrations, similar components and / or features may use the same reference numerals. Furthermore, components of the same class can be distinguished by adding a distinguishing mark after the reference numeral. If only the first reference numeral is used in the specification, the description applies to all similar components having the same first reference numeral, regardless of what their second reference numeral is.

[0020] Figure 1 An example interactive boot device according to an embodiment of this disclosure is shown.

[0021] Figure 2An interactive guidance example apparatus according to an embodiment of the present disclosure is shown, illustrating a flowchart example of generating output in response to user input.

[0022] Figure 3 A flowchart example of an interactive guidance device according to an embodiment of the present disclosure is shown, which generates multimodal output based on user multimodal input, including a language translation function performed by the device.

[0023] Figure 4 An example interactive booting device and its structural and functional components are shown according to embodiments of the present disclosure.

[0024] Figure 5 An example interactive bootstrapping method according to an embodiment of this disclosure is shown. Detailed Implementation

[0025] Specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. These embodiments are described in great detail and are intended to clearly convey the content of the present disclosure. However, the level of detail provided is not intended to limit variations of the contemplated embodiments; rather, it is intended to cover all modifications, equivalents, and alternatives consistent with the spirit and scope of the present disclosure, as defined in the appended claims.

[0026] The following description provides exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of this disclosure. Rather, the subsequent description of exemplary embodiments will provide those skilled in the art with operational guidance on implementing the exemplary embodiments. It should be understood that various changes may be made to the function and arrangement of the components without departing from the spirit and scope of the invention.

[0027] The following detailed description of specific aspects is provided to provide a comprehensive understanding of the embodiments. However, those skilled in the art will understand that the embodiments can still be implemented even with these specific details omitted. For example, circuits, systems, networks, processes, and other components may be presented in block diagram form to avoid redundant details obscuring the essence of the embodiments. In other cases, well-known circuits, processes, algorithms, structures, and technologies may also omit unnecessary details to ensure that the embodiments are clearly identifiable.

[0028] It should also be noted that some embodiments may be described as processes in the form of flowcharts, schematic diagrams, data flow diagrams, structural diagrams, or block diagrams. Although flowcharts may describe operations as sequential processes, many of these operations may be executed in parallel or simultaneously. Furthermore, the order of operations may be rearranged. The process terminates when an operation is completed, but there may be additional steps not shown in the illustrations. A process may correspond to a method, function, program, subroutine, subroutine set, etc. When a process corresponds to a function, its termination may correspond to the function returning to the calling function or the main function.

[0029] In this document, the terms "exemplary" and / or "illustrative" are intended as examples, instances, or illustrations. For the avoidance of doubt, the content disclosed herein is not limited to such examples. Furthermore, any aspect or design marked "exemplary" and / or "illustrative" herein is not necessarily to be construed as superior to other aspects or designs, nor does it exclude equivalent exemplary structures and techniques known to those skilled in the art. Moreover, when the terms "comprising," "having," "including," and other similar terms appear in the detailed description or claims, such terms are used in an inclusive manner—similar to the use of the open-ended transitional term "comprising"—and do not exclude any additional or other elements.

[0030] The terms "an embodiment," "an example," "an instance," or "an instance" used in this specification all indicate that a particular feature, structure, or characteristic described in that embodiment is included in at least one embodiment of the invention. Therefore, expressions such as "in one embodiment" or "in one embodiment" appearing throughout this specification do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0031] Reference to various aspects of the present invention Figures 1 to 5 Describe it.

[0032] This invention relates to the field of boot tools, and in particular to interactive boot devices and methods.

[0033] This invention provides an interactive guidance device 100. The device 100 includes a main body. The device 100 may include one or more input devices for receiving user input, wherein the one or more input devices are configured on the main body. The device 100 may include one or more output devices for generating output for the device 100, wherein the one or more output devices are configured on the main body. The device 100 includes one or more sensors for detecting input from the user, wherein the one or more sensors are configured on the main body. Furthermore, the device 100 includes at least one processor communicatively connected to one or more computing devices, wherein one or more users are connected to the computing devices of the device 100 via a network. The device 100 includes a memory operatively coupled to the at least one processor, the memory storing executable instructions. When the at least one processor executes the executable instructions, the processor performs the following steps: When one or more input devices and one or more sensors detect input, the at least one processor activates the device 100 to a running mode. The at least one processor receives input through one or more input devices. The at least one processor determines output based on the input using one or more methods. The at least one processor generates output through one or more output devices.

[0034] Figure 1 An example interactive guidance device 100 according to one embodiment of the present disclosure is shown. In one exemplary embodiment, the interactive guidance device can be used to teach children aged 2 to 12 years without adult supervision. (See also...) Figure 1 In one embodiment, the main body of device 100 can be designed in the form of a toy, and its name can be set as Gappu or HarmonyHeart, etc., or it can be customized by children or parents through voice commands or connected devices such as computers / smartphones. The main body of the device can take the shape of a plush teddy bear as shown in the illustration, or it can be made of plastic, metal, rubber, wood or other materials. Figure 1 A front view 102 and a rear view 104 of the device 100 are shown. In an exemplary embodiment, the shape and texture of the device body 100 are designed to ensure safe use by children and to provide emotional comfort.

[0035] In an embodiment, one or more input devices may include at least one of the following: one or more touch-sensitive buttons (numbered 106-1, 106-2, ..., 106-6 in the figure, collectively or individually referred to as 106), a microphone 108, and a near-field communication (NFC) reader 110. In an exemplary embodiment, touch button 106 may include at least one of the following function buttons: volume down button 106-1, volume up button 106-2, audio recording button 106-3, audio playback button 106-4, message listening button 106-5, and book reading button 106-6.

[0036] In one embodiment, the one or more output devices may include at least one speaker 112 for generating voice output. In an exemplary embodiment, the output device may include one or more light-emitting diodes (LEDs) 114. In one embodiment, one or more sensors for detecting user input may include an accelerometer 116 for detecting motion of the device 100.

[0037] In one embodiment, device 100 may include at least one means for charging one or more batteries that power device 100, and one or more output modules for regulating output, wherein the one or more battery charging means, the one or more batteries, and the one or more output modules are all disposed within body 100. In an exemplary embodiment, the one or more output modules may include a volume control means. In an exemplary embodiment, the charging means may include a wireless charging mechanism implemented via wireless charging means 118-1, or a wired charging mechanism implemented via a USB-C charging port (USB stands for Universal Serial Bus) 118-2.

[0038] In one embodiment, when the accelerometer 116 detects that the motion or touch-sensitive button 106 associated with the device 100 has been pressed, the device 100 will activate to the operating mode. In another embodiment, when the device 100 has been idle for a predetermined period of time, the device 100 may enter a non-operating mode (power-saving mode).

[0039] In one embodiment, the device 100 performs the following steps. Figure 2 A flowchart example 200 illustrating an interactive guided example device generating output in response to user input, according to an embodiment of this disclosure, is shown. Device 100 may receive input via one or more input devices. In an exemplary embodiment, user input 202 may be received in speech form via microphone 108 and converted to text via natural language processing (NLP) 206. In an exemplary embodiment, input may be received via one or more computing devices communicatively connected to device 100 via a network. In an exemplary embodiment, input may be received via a near-field communication reader that uses one or more near-field communication tags encoding unique identifiers to initiate a topic-specific interaction. Device 100 may determine the output based on one or more inputs using one or more methods. In an embodiment, the methods include one or more methods based on a large language model 214. In an embodiment, the output is determined via a contextual search 212 that retrieves data from a database 210 using the large language model 214. For example, user input might be a question based on the background of a story in a particular story list. The search space of the contextual search 212 is limited or constrained to the story content 208. In one embodiment, the interactive guidance device 100 may be an Internet of Things (IoT) device, an application running on a smartphone, or a website connected to the server via a computer / smartphone. AI-based tasks (speech-to-text / text-to-speech conversion and language translation) and content determination or generation via large language model 214 technology are all completed on the server side.

[0040] In one embodiment, device 100 may generate output via one or more output devices. In an exemplary embodiment, text-based output based on a large language model 214 may be converted into speech 216 and generated via speaker 112. In one embodiment, the speech output is based on the speech 218 of at least one of a parent, teacher, or caregiver. In an exemplary embodiment, device 100 may generate speech output using a pre-recorded database of parental speech (voice).

[0041] Figure 3 A flowchart example 300 illustrating the generation of multimodal output from multimodal input according to an embodiment of the present disclosure is shown, including a language translation performed by an apparatus under interactive guidance. (Refer to...) Figure 3In an embodiment, the user's multimodal input 302 may include at least one of speech (speaking) 304 and text 306. If the input is speech 304, speech-to-text conversion 308 needs to be performed. In an exemplary embodiment, the user's input may be in multiple languages, and the system may perform translation 310 to convert the source language text into English text 312. Based on the English text input, the system may perform a contextual search 314 in a contextual database 316 using a method based on a large language model 214. For example, the search may be based on a specific children's rhyme. In an exemplary embodiment, the contextual search 314 may generate English text output, which may be converted to the source language 320 used by the device 100 when receiving user input. In another embodiment, the text output may be converted to speech (speaking) 322. The content 324 output to the user may be speech 326 or text 328. In an embodiment, the device 100 connects to a cloud server to establish a cloud platform connection. New content (stories, rhymes, etc.) can be provided to the device 100 user from the cloud server via the network.

[0042] Figure 4 An interactive boot example apparatus according to an embodiment of the present disclosure is shown, which includes structural and functional components. (Refer to...) Figure 4 The device 100 may include at least one processor 402, which may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any means of processing data based on operating instructions. Among other functions, the processor 402 may be configured to retrieve and execute computer-readable instructions from a memory 404 of the device 100. The memory 404 may be configured to store one or more computer-readable instructions or programs in a non-transitory computer-readable storage medium, which may be retrieved and executed to create or share data packets via network services. The memory 404 may include any non-transitory storage device, such as volatile memory (e.g., random access memory, RAM) or non-volatile memory (e.g., erasable programmable read-only memory, flash memory, etc.).

[0043] In one embodiment, device 100 may include interface 406. Interface 406 may include various interfaces, such as interfaces for data input / output devices (I / O devices), storage devices, etc. Interface 406 facilitates communication with device 100. Interface 406 may also provide communication channels for one or more components of device 100. Such components include, but are not limited to, processing unit or engine 408 and local database 416. In one embodiment, local database 416 may exist independently of device 100.

[0044] In one embodiment, processing engine 408 may implement one or more of its functions through a combination of hardware and programming (e.g., programmable instructions). Such a hardware-programming combination can be implemented in various ways in the examples described herein. For example, the program for processing engine 408 may be processor-executable instructions stored on a non-temporary machine-readable storage medium, and the hardware for processing engine 408 may include processing resources (e.g., one or more processors) to execute such instructions. In this embodiment, the machine-readable storage medium may store instructions that, when executed by the processing resources, will implement processing engine 408. In these examples, device 100 may include a machine-readable storage medium storing instructions and processing resources executing the instructions, or the storage medium may exist independently but be accessible by device 100 and the processing resources. In other examples, processing engine 408 may be implemented through electronic circuitry.

[0045] In one embodiment, the processing engine 408 may include a data processing engine 410, an artificial intelligence (AI) engine 412, and other modules 414. When one or more sensors and input devices detect user input, the processor 402 may activate the device 100 to an operating mode via the data processing engine 410. The processor(s) 402 may receive input from the user via one or more input devices via the data processing engine 410. The processor(s) 402 may generate output based on one or more inputs using a method based on one or more large language models (LLMs) 214 via the AI ​​engine 412. In an exemplary embodiment, the processor(s) 402 may perform various tasks via the AI ​​engine 412, including Figure 3 The functions shown include speech-to-text 308, text-to-speech 322, and text-to-speech conversion 310. The processor 402 can generate output through one or more output devices. Other modules 416 can implement other functions of the device 100.

[0046] The present invention also discloses an interactive guidance method. Figure 5 An interactive bootstrapping example method 500 according to an embodiment of this disclosure is illustrated. The apparatus 100 mentioned in method 500 is... Figure 1The illustrated device 100 is similar. Method 500 may include the following steps. In step 502, when one or more sensors and one or more input devices detect user input, device 100 may be activated to an operating mode. The one or more sensors and one or more input devices are configured in a housing associated with device 100, device 100 is communicatively connected to one or more computing devices, and one or more users operate the computing devices and are connected to device 100 via a network. In step 504, device 100 may receive input through the one or more input devices. In step 506, device 100 may determine an output based on the input using one or more methods. In step 508, device 100 may generate an output through one or more output devices, wherein the one or more output devices are configured on the housing.

[0047] The device 100 of this invention provides dialogue functionality based on a large language model 214, which simulates the voice of a caregiver or parent for dialogue and storytelling. This feature provides a personalized and emotionally resonant experience, significantly enhancing family bonds and enriching educational interactions.

[0048] The device 100 of this invention provides a theme-driven near-field communication (NFC) interactive function, wherein the NFC tags can be heart-shaped, each representing a specific educational theme, and interaction is achieved through a magnetic NFC reader. This function supports intuitive tactile theme selection, guiding children on an educational journey that aligns with their interests.

[0049] The device 100 of this invention provides a dynamic artificial intelligence-driven dialogue function, which is achieved through touch buttons and a large language model 214 using artificial intelligence technology. This interactive mode guides children to participate in stimulating dialogues, promoting language development and cognitive growth.

[0050] The device 100 of this invention integrates a CloudConnect WiFi module, enabling seamless content exchange between the device 100 and a cloud platform. This function allows parents to send personalized messages, stories, and songs, thereby enhancing the educational and emotional value of the device 100.

[0051] The device 100 of this invention enhances family bonds by utilizing recorded parental voices in artificial intelligence interaction with a large language model 214, forming a unique innovation. This function creates a sense of familiarity, strengthening family emotional bonds and mental well-being during play and learning.

[0052] The device 100 of this invention achieves comprehensive sensor integration by integrating a wake-up-activated accelerometer, a wirelessly charging Qi charging pad, and a rationally arranged touch button. This design ensures a user-friendly and immersive experience for children.

[0053] The device 100 of this invention focuses on educational fields such as language development, mental health, mindfulness cultivation, cultural cognition, and STEAM subjects, and supports interactive customization functions, making a unique contribution to the field of interactive educational toys.

[0054] The present invention is not limited to the foregoing embodiments. It is obvious to those skilled in the art that various substitutions, modifications and alterations can be made without departing from the scope of the present invention.

Claims

1. An interactive guidance device (100), characterized in that, The device (100) includes: main body; One or more input devices for receiving user input, wherein one or more input devices are disposed on the main body; One or more output devices for generating output from the device (100), wherein the one or more output devices are disposed on the body; One or more sensors for detecting user input, wherein one or more sensors are configured on the body; At least one processor (402) communicatively connected to one or more computing devices, wherein one or more users operate the computing devices and are connected to the devices (100) via a network; and A memory (404) operably coupled to at least one processor (402), the memory (404) storing executable instructions that, when executed by at least one processor (402), cause at least one processor (402) to perform the following operations: When one or more input devices and one or more sensors detect an input, the device (100) is activated to enter the operating mode; Input is received through one or more input devices; Determine the output based on the input using one or more methods; and Output is generated through one or more output devices.

2. The apparatus (100) according to claim 1, characterized in that, The one or more input devices include at least one of the following: one or more touch-sensitive buttons (106), a microphone (108), and a near-field communication reader (110).

3. The apparatus (100) according to claim 1, characterized in that, The one or more output devices include at least one speaker (112) for generating voice output.

4. The apparatus (100) according to claim 1, characterized in that, It includes at least one of the following: a method for charging one or more batteries to power the device (100); and one or more output modules for regulating the output, wherein the method for charging the one or more batteries, the one or more batteries, and the one or more output modules are all disposed within the main body.

5. The apparatus (100) according to claim 3, characterized in that, The voice output is based on the voice of at least one of the following: a parent, teacher, or caregiver.

6. The apparatus (100) according to claim 1, characterized in that, One or more of these methods include one or more methods based on large language models (214).

7. The apparatus (100) according to claim 1, characterized in that, The device connects to the cloud server to establish a connection with the cloud platform.

8. An interactive teaching method (500), characterized in that, The method (500) includes: When one or more sensors and one or more input devices detect user input, a device (100) associated with at least one processor (402) activates (502) the device (100) to an operating mode, wherein the one or more sensors and one or more input devices are configured on a body associated with the device (100), the at least one processor (402) is communicatively connected to one or more computing devices, and one or more users operate computing devices and are connected to the device (100) via a network. At least one processor (402) receives (504) input via one or more input devices; At least one processor determines (506) the output based on the input using one or more methods (402); and The output (508) is generated by at least one processor (402) through one or more output devices, wherein the one or more output devices are configured on the body.

9. The method (500) according to claim 8, characterized in that, One or more of the input devices detect user input including at least one of the following: one or more touch-sensitive buttons (106), a microphone (108), and a near-field communication reader (110).

10. The method (500) according to claim 8, characterized in that, The output generated by one or more output devices includes at least one speaker (112) for generating voice output.

11. The method (500) according to claim 8, characterized in that, The output is determined by one or more methods, including one or more methods based on a large language model (214).

12. The method (500) according to claim 11, characterized in that, The method further includes: The large language model (214) is trained to simulate dialogue using the user's voice.

13. The method (500) according to claim 8, characterized in that, The method further includes: Establish a connection with the cloud platform.

Images