Search

CN-122003673-A - Interactive education device and method for guiding by using artificial intelligence

CN122003673ACN 122003673 ACN122003673 ACN 122003673ACN-122003673-A

Abstract

The invention provides an interactive coaching device (100) and method. The device (100) includes a sensor, an input device and an output device disposed on a body of the device (100) for detecting, receiving user inputs and generating outputs, 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 output device may include an accelerometer (116) and a speaker (112), respectively. The device (100) may receive input from a user as text or speech, convert the speech input to text by performing a contextual search (208) based on a large language model (214) approach, simulate dialog implementing interactive guidance, and generate output in text or speech form through an output device. The device (100) may be deactivated to a power saving mode when the device is in an idle state for more than a preset time.

Inventors

  • A. Jaiswar

Assignees

  • A·贾伊斯瓦尔

Dates

Publication Date
20260508
Application Date
20241128
Priority Date
20240201

Claims (13)

  1. 1. An interactive guiding device (100), characterized in that the device (100) comprises: A main body; One or more input devices for receiving user input, wherein the one or more input devices are disposed on the body; One or more output devices for generating an 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 the one or more sensors are disposed on the body; At least one processor (402) communicatively coupled to one or more computing devices, wherein one or more users operate the computing devices and are coupled to the device (100) via a network, and A memory (404) operatively coupled with the at least one processor (402), the memory (404) storing executable instructions that, when executed by the at least one processor (402), cause the at least one processor (402) to: Activating the device (100) into an operational mode when one or more input devices and one or more sensors detect an input; receiving input through one or more input devices; determining an output based on the input by one or more methods, and An output is generated by one or more output devices.
  2. 2. The device (100) of claim 1, wherein the one or more input devices comprise at least one of one or more touch sensitive buttons (106), a microphone (108), and a near field communication reader (110).
  3. 3. The device (100) of claim 1, wherein the one or more output devices include at least one speaker (112) for generating a speech output.
  4. 4. The device (100) of claim 1, comprising at least one of a method for charging one or more batteries for powering the device (100), and one or more output modules for regulating output, wherein the method for charging the one or more batteries, and the one or more output modules are all disposed within the body.
  5. 5. The apparatus (100) of claim 3, wherein the speech output is based on the sound of at least one of a parent, teacher, or caregiver.
  6. 6. The apparatus (100) of claim 1, wherein the one or more methods include one or more large language model (214) based methods.
  7. 7. The device (100) of claim 1, wherein the device connects to a cloud server to establish a connection with a cloud platform.
  8. 8. An interactive teaching method (500), characterized in that the method (500) comprises: Activating (502) a device (100) associated with at least one processor (402) to an operational mode when user input is detected by one or more sensors and one or more input devices, wherein the one or more sensors and one or more input devices are disposed 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 the computing devices and are connected to the device (100) through a network; At least one processor (402) receives (504) input through one or more input devices; at least one processor determines (506) an output based on the input by one or more methods (402), and An output is generated (508) by at least one processor (402) through one or more output devices, wherein the one or more output devices are disposed on the body.
  9. 9. The method (500) of claim 8, wherein the one or more input devices detecting user input includes at least one of one or more touch sensitive buttons (106), a microphone (108), and a near field communication reader (110).
  10. 10. The method (500) of claim 8, wherein generating output via one or more output devices includes at least one speaker (112) for generating speech output.
  11. 11. The method (500) of claim 8, wherein determining the output by one or more methods includes one or more large language model (214) based methods.
  12. 12. The method (500) of claim 11, wherein the method further comprises: The large language model (214) is trained to simulate conversations of user voices.
  13. 13. The method (500) of claim 8, wherein the method further comprises: and establishing connection with the cloud platform.

Description

Interactive education device and method for guiding by using artificial intelligence Technical Field The present invention relates to the field of guiding tools. More particularly, the present invention relates to an interactive guidance apparatus and method. Background description The background description contains information that is helpful in understanding the present disclosure. The information provided herein does not constitute an admission of prior art nor does it suggest that it was relevant to the presently claimed disclosure or that any publication specifically or implicitly referenced is prior art. Learning during childhood has a key impact on overall mental and emotional development of humans. Toys are an integral part of childhood. Thus, there are many teaching and knowledge instruction tools that include toys. Some educational tools include toys that play prerecorded content, toys that have remote message applications, educational mobile applications, internet of things toys, and child personalized voice assistants. Learning in childhood is mainly achieved through interaction with people and the environment. Existing teaching solutions lack interactive components that facilitate learning. Children may quickly lose interest due to limited toy interactivity, which limits their engagement and learning potential. With the development of generative Artificial Intelligence (AI), particularly the advancement of large language models, it has become possible to generate raw content to simulate human-like conversations. With AI technology, computers can automatically accomplish the tasks of high precision conversion of speech (speech) to text and text to speech, multilingual text inter-interpretation, conversion of personal sound (source sound) to other person's sound (target sound). There is therefore a great need to develop interactive coaching solutions, applying current AI technology to the field of modern education. While educational mobile applications today can provide learning opportunities, screen time is often required and physical game time is limited. They lack the tactile engagement and personalized interaction provided by solid toys, which is detrimental to facilitating interactive learning and emotion tie establishment. There is therefore a need to integrate digital technology with solid toys to stimulate cognitive and sensory development. The patent document of us patent number 11663182 discloses AI toy systems, methods and apparatus with enhanced dialog capability and personality development. The AI toy determines a response to the stimulus based on the user profile and personality profile established by the user interaction and the external media input. AI personality and dialog capabilities were developed by combining semantic interaction techniques such as Natural Language Processing (NLP) with archival data. However, the toy provides only voice question-and-answer interactions and may lack interactive learning and game functionality. Patent document of China patent No. 2717504Y discloses an interactive dynamic toy. The toy main body is internally provided with the camera device and the playing device, so that a user can freely record and select the needed sound and images to play. Different control instructions are input into a control processing unit through sensors (), which are distributed at all parts of the toy main body, and the unit drives a playing device to execute corresponding pre-recorded response actions, so that an interaction effect is generated. The toy main body is also provided with a signal comparison processing unit which can analyze and compare input signals and execute specific reverberation so as to strengthen interactive experience and language learning functions. Although the device allows parents to pre-record sounds for later playback, the range of pre-recorded stories or sounds is limited, possibly limiting the child's engagement and learning potential. Therefore, there is a need to provide real-time interaction and adaptability functions based on the interests of children, and a method not found in the above prior art documents, nor common general knowledge in the art, is needed to improve the creativity and family tie of children. Patent document 215202006U discloses a robot device capable of customizing simulated voice, which belongs to the technical field of intelligent robots and comprises a CPU, wherein the CPU is respectively connected with a distance sensor module, a light sensor module, a temperature sensor module, a voice playing module, a power management module, an LED, a storage module and a voice synthesis module, the voice synthesis module is connected with the voice recognition module for voice recognition, the voice recognition module is connected with a network communication module, and the voice recognition module is connected with a voice acquisition module through the network communication module. According to the utility model, the