TWI858021B - Audio-based interactive system, interactive method, and interactive device - Google Patents

Abstract

An audio-based interactive system, an interactive method, and an interactive device are provided. The interactive method includes: generating, by one of at least one sensor of the interactive device and a microphone of a smart speaker, first sensed data, wherein the at least one sensor including at least one of a switch, a G-sensor, a color sensor, and a pressure sensor; communicatively connecting, via the smart speaker, the interactive device to a cloud server; and playing, via the smart speaker, a first audio data corresponding to the first sensed data and playing, via an image output interface, a first image corresponding to the first sensed data by the cloud server in response to receiving the first sensed data.

Description

Audio-based interactive system, interactive method and interactive device

The present invention relates to a system, a method and an electronic device, and in particular to an interactive system, an interactive method and an interactive device based on audio.

With the development of Internet technology, more and more e-commerce companies or Internet service providers have begun to promote voice assistant related services. Voice assistants are usually composed of a microphone and a speaker, and can communicate with the Internet. Voice assistants can be controlled by cloud servers to interact with users. For example, voice assistants can answer users' questions or provide users with information obtained from the Internet.

However, current voice assistants can only have simple conversations with users, but cannot interact with users further. Therefore, how to propose a method for more diverse interactions with voice assistants is one of the goals that researchers in this field are committed to.

The present invention provides an audio-based interactive system, an interactive method and an interactive device, which allow users to interact with a smart speaker through an interactive device with a variety of sensors.

The present invention discloses an audio-based interactive system, comprising a cloud server, a smart speaker, and an interactive device. The cloud server stores first audio data and a first image. The smart speaker comprises a microphone and is communicatively connected to the cloud server. The interactive device comprises at least one sensor and an image output interface and is communicatively connected to the smart speaker, wherein at least one sensor comprises at least one of a button, an accelerometer, a color sensor, and a pressure sensor, wherein at least one of the sensor and the microphone generates first sensing data; the interactive device is communicatively connected to the cloud server through the smart speaker; and the cloud server plays first audio data corresponding to the first sensing data through the smart speaker and plays a first image corresponding to the first sensing data through the image output interface in response to receiving the first sensing data.

In one embodiment of the present invention, the cloud server further stores reference data, and the cloud server determines whether to play the first audio data and the first image according to the matching result between the first sensing data and the reference data.

In one embodiment of the present invention, the cloud server plays the second audio data through the smart speaker, and decides to play the first audio data and the first image in response to receiving the first sensing data within a preset time after playing the second audio data.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes a button, and the first sensing data includes a pulse signal, wherein an image output interface is provided on the surface of the button, wherein the cloud server plays the image through the image output interface, and in response to receiving the pulse signal during the playback of the image, plays the first audio data through the smart speaker and plays the first image through the image output interface.

In one embodiment of the present invention, the at least one sensor further includes a second microphone.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes an accelerometer, and the first sensing data includes a tilt value, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the tilt value being less than a threshold.

In an embodiment of the present invention, the first image corresponds to a tilt value.

In one embodiment of the present invention, the first sensing data further includes audio data, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the audio data matching the reference data stored in the cloud server and the tilt value being less than the threshold.

In one embodiment of the present invention, the cloud server plays the countdown image through the image output interface, and in response to receiving the audio data before the countdown ends, plays the first audio data through the smart speaker and the first image through the image output interface.

In one embodiment of the present invention, the first sensing data includes audio data, wherein the cloud server further stores a speech recognition model and user information, identifies the user corresponding to the audio data by the speech recognition model to generate a recognition result, and updates the user information according to the recognition result.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes an accelerometer, and the first sensing data includes an acceleration value, wherein the cloud server plays the first audio data through the smart speaker and displays the first image through the image output interface in response to the acceleration value being greater than a threshold.

In an embodiment of the present invention, the at least one sensor includes a color sensor, and the first sensing data includes a color value.

In one embodiment of the present invention, the at least one sensor includes a pressure sensor, and the first sensing data includes a pressure value.

An audio-based interaction method of the present invention is applicable to an interactive system including a cloud server, a smart speaker and an interactive device, wherein the interaction method includes: generating first sensing data by at least one sensor of the interactive device and one of the microphones of the smart speaker, wherein the at least one sensor includes at least one of a button, an accelerometer, a color sensor and a pressure sensor; the interactive device is connected to the cloud server through the smart speaker for communication; and the cloud server plays first audio data corresponding to the first sensing data through the smart speaker and plays a first image corresponding to the first sensing data through the image output interface of the interactive device in response to receiving the first sensing data.

In one embodiment of the present invention, the cloud server further stores reference data, and the cloud server determines whether to play the first audio data and the first image according to the matching result between the first sensing data and the reference data.

In one embodiment of the present invention, the cloud server plays the second audio data through the smart speaker, and decides to play the first audio data and the first image in response to receiving the first sensing data within a preset time after playing the second audio data.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes a button, and the first sensing data includes a pulse signal, wherein an image output interface is provided on the surface of the button, wherein the cloud server plays the image through the image output interface, and in response to receiving the pulse signal during the playback of the image, plays the first audio data through the smart speaker and plays the first image through the image output interface.

In one embodiment of the present invention, the at least one sensor further includes a second microphone.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes an accelerometer, and the first sensing data includes a tilt value, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the tilt value being less than a threshold.

In an embodiment of the present invention, the first image corresponds to a tilt value.

In one embodiment of the present invention, the first sensing data further includes audio data, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the audio data matching the reference data stored in the cloud server and the tilt value being less than the threshold.

In one embodiment of the present invention, the cloud server plays the countdown image through the image output interface, and in response to receiving the audio data before the countdown ends, plays the first audio data through the smart speaker and the first image through the image output interface.

In one embodiment of the present invention, the first sensing data includes audio data, wherein the cloud server further stores a speech recognition model and user information, identifies the user corresponding to the audio data by the speech recognition model to generate a recognition result, and updates the user information according to the recognition result.

In one embodiment of the present invention, at least one sensor of the above-mentioned interactive device includes an accelerometer, and the first sensing data includes an acceleration value, wherein the cloud server plays the first audio data through the smart speaker and displays the first image through the image output interface in response to the acceleration value being greater than a threshold.

In an embodiment of the present invention, the at least one sensor includes a color sensor, and the first sensing data includes a color value.

In one embodiment of the present invention, the at least one sensor includes a pressure sensor, and the first sensing data includes a pressure value.

An interactive device of the present invention is suitable for interacting with a cloud server and a smart speaker, wherein the interactive device includes a transceiver, at least one sensor, an image output interface, and a processor. The transceiver is communicatively connected to the smart speaker, and is communicatively connected to the cloud server through the smart speaker. At least one sensor generates first sensing data. The processor is coupled to the transceiver, at least one sensor, and the image output interface, wherein the processor transmits the first sensing data through the transceiver, receives a first image corresponding to the first sensing data through the transceiver, and plays the first image through the image output interface, wherein the first sensing data is used to instruct the cloud server to configure the smart speaker to play the first audio data corresponding to the first sensing data.

Based on the above, the interactive system of the present invention provides users with an interactive device with multiple types of sensors. Users can interact with the smart speaker through the interactive device to obtain a more diverse entertainment experience.

In order to make the content of the present invention more clearly understood, the following embodiments are specifically cited as examples by which the present invention can be truly implemented. In addition, wherever possible, elements/components/steps with the same reference numerals in the drawings and embodiments represent the same or similar components.

In order to provide users with a more diverse entertainment experience, the present invention proposes an audio-based interactive system. FIG1 shows a schematic diagram of an audio-based interactive system 100 according to an embodiment of the present invention. The interactive system 100 may include a cloud server 100, a smart speaker 200, and an interactive device 300, wherein the cloud server 100 may be disposed at a remote end, and the smart speaker 200 and the interactive device 300 may be disposed at a local end. The smart speaker 200 may be communicatively connected to the cloud server 100 and the interactive device 300. The cloud server 100 and the interactive device 300 may forward signals to each other through the smart speaker 200.

FIG2 is a schematic diagram of a cloud server 100 according to an embodiment of the present invention. The cloud server 100 may include a processor 110, a storage medium 120, and a transceiver 130.

The processor 110 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose micro control unit (MCU), microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar components or combinations of the above components. The processor 110 may be coupled to the storage medium 120 and the transceiver 130 , and access and execute a plurality of modules and various applications stored in the storage medium 120 .

The storage medium 120 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid state drive (SSD) or similar components or a combination of the above components, and is used to store multiple modules or various applications that can be executed by the processor 110. In this embodiment, the storage medium 120 can store various audio data, or can store reference data and program codes used for interaction between the smart speaker 200 and the interactive device 300.

The transceiver 130 transmits and receives signals wirelessly or wiredly. The transceiver 130 may also perform operations such as low noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The cloud server 100 may communicate with the smart speaker 200 or the interactive device 300 via the transceiver 130 .

FIG3 is a schematic diagram of a smart speaker 200 according to an embodiment of the present invention. The smart speaker 200 can be used to play received audio data. The smart speaker 200 can include a processor 210, a storage medium 220, and a transceiver 230. In one embodiment, the smart speaker 200 can further include a microphone 240.

The processor 210 is, for example, a central processing unit, or other programmable general-purpose or special-purpose microcontroller unit, microprocessor, digital signal processor, programmable controller, special application integrated circuit, graphics processor, image signal processor, image processing unit, arithmetic logic unit, complex programmable logic device, field programmable logic gate array or other similar components or combinations of the above components. The processor 210 can be coupled to the storage medium 220, the transceiver 230 and the microphone 240, and access and execute multiple modules and various applications stored in the storage medium 220.

The storage medium 220 is, for example, any type of fixed or removable random access memory, read-only memory, flash memory, hard disk, solid state drive or similar element or a combination of the above elements, and is used to store multiple modules or various applications that can be executed by the processor 210.

The transceiver 230 transmits and receives signals wirelessly or wiredly. The transceiver 230 may also perform operations such as low noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The smart speaker 200 may communicate with the cloud server 100 or the interactive device 300 via the transceiver 230.

The microphone 240 can be used to receive sound. For example, the microphone 240 can generate corresponding audio data from the user's voice and upload the audio data to the cloud server 100.

FIG4 is a schematic diagram of an interactive device 300 according to an embodiment of the present invention. A user can perform audio-based interaction with the smart speaker 200 through the interactive device 300. The interactive device 300 is, for example, a handheld device. The interactive device 300 may include a processor 310, a storage medium 320, a transceiver 330, and a sensor 340. In one embodiment, the interactive device 300 may further include an image output interface 350. It is worth noting that the type and quantity of the sensor 340 can be adjusted according to the needs of the user, and the present invention is not limited thereto. For example, the interactive device 300 may include more than two sensors 340.

The processor 310 is, for example, a central processing unit, or other programmable general-purpose or special-purpose microcontroller unit, microprocessor, digital signal processor, programmable controller, special application integrated circuit, graphics processor, image signal processor, image processing unit, arithmetic logic unit, complex programmable logic device, field programmable logic gate array or other similar components or combinations of the above components. The processor 310 can be coupled to the storage medium 320, the transceiver 330, the sensor 340 and the image output interface 350, and access and execute multiple modules and various applications stored in the storage medium 320.

The storage medium 320 is, for example, any type of fixed or removable random access memory, read-only memory, flash memory, hard disk, solid state drive or similar element or a combination of the above elements, and is used to store multiple modules or various applications that can be executed by the processor 310.

The transceiver 330 transmits and receives signals wirelessly or wiredly. The transceiver 230 may also perform operations such as low noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and the like. The interactive device 300 may communicate with the cloud server 100 or the smart speaker 200 via the transceiver 330.

The sensor 340 is, for example, one of the following or a combination thereof: a microphone, a button, an accelerometer, a angular velocity meter, a magnetometer, a pressure sensor, or a color sensor, but the present invention is not limited thereto.

The image output interface 350 is, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an LED array, a vacuum fluorescent display (VFD), a plasma display panel (PDP), an organic light-emitting diode (OLED) or a field-emission display (FED), but the present invention is not limited thereto. The cloud server 100 can send a command to the interactive device 300 through the smart speaker 200 to instruct the image output interface 350 to play a corresponding image, wherein the image is, for example, from the cloud server 100 or pre-stored in the storage medium 320.

The smart speaker 200 may generate the first sensing data through the microphone 240, or receive the first sensing data generated by the sensor 340 from the interactive device 300. After obtaining the first sensing data, the smart speaker 200 may transmit the first sensing data to the cloud server 100. The cloud server 100 may play the first audio data corresponding to the first sensing data through the smart speaker 200 in response to receiving the first sensing data. The first sensing data may include audio data, acceleration value, tilt value, pressure value or color value, but the present invention is not limited thereto.

In one embodiment, the sensor 340 of the interactive device 300 may include a microphone. The smart speaker 200 may receive the sound emitted by the user through the microphone 240 to generate corresponding audio data, or receive the audio data generated by the microphone 240 from the interactive device 300. The smart speaker 200 may transmit the audio data to the cloud server 100. The cloud server 100 may play the corresponding audio data through the smart speaker 200 according to the received audio data.

For example, the cloud server 100 can play audio data to the user through the smart speaker 200 to ask the user questions. The user can answer the question through the microphone 240 or the sensor 340. The cloud server 100 can determine whether the content of the user's answer matches the reference data based on the reference data pre-stored in the storage medium 120, and decide to play the audio data representing "correct" or "wrong" through the smart speaker 200 based on the matching result. The cloud server 100 can also limit the user's answer time. For example, after the cloud server 100 asks a question to the user, the cloud server 100 may play audio data representing "correct" through the smart speaker 200 in response to receiving a correct answer within a preset time, and may play audio data representing "error" through the smart speaker 200 in response to not receiving a correct answer within the preset time. During the preset time, the cloud server 100 may play audio data through the smart speaker 200 to count down.

The above-mentioned embodiments allow the user to communicate with the smart speaker 200 through the microphone of the interactive device 100 or the microphone 240 of the smart speaker 200. In this way, interactive behaviors such as quiz games, song guessing games, or raising virtual pets can be realized.

In one embodiment, the smart speaker 200 can receive the sound emitted by the user through the microphone 240 to generate corresponding audio data, or can receive the audio data generated by the microphone 240 from the interactive device 300. Then, the smart speaker 200 can amplify the power of the audio data through the amplifier circuit in the smart speaker 200 to generate amplified audio data, and play the amplified audio data. In this way, the user can use the smart speaker 200 as a loudspeaker.

In one embodiment, the storage medium 120 of the cloud server 100 can store a voice recognition module and store user information corresponding to one or more users of the interactive system 10. After the cloud server 100 receives audio data from the smart speaker 200, the cloud server 100 can use the voice recognition model to identify the user corresponding to the audio data and generate a corresponding recognition result. Then, the cloud server 100 can update the user information of the user based on the recognition result. For example, after the cloud server 100 plays a question through the smart speaker 200, the smart speaker 200 can receive the audio data of the answer of person A and forward the audio data to the cloud server 100. The cloud server 100 determines through the speech recognition model that the received audio data corresponds to person A. Then, the cloud server 100 can update the user information of person A in response to the audio data representing the correct answer content. For example, the cloud server 100 can increase the score of person A.

In one embodiment, the sensor 340 of the interactive device 300 may include an accelerometer. The sensor 340 may be used to detect the acceleration value of the interactive device 300. The smart speaker 200 may transmit the acceleration value received from the interactive device 300 to the cloud server 100. The cloud server 100 may play audio data corresponding to the acceleration value through the smart speaker 200 in response to the acceleration value being greater than the threshold.

For example, the interactive device 300 is a ball. When the user throws the interactive device 300, the sensor 340 in the interactive device 300 can sense the acceleration value. When the acceleration value is greater than the threshold, the cloud server 100 can play audio data related to the movement of the ball through the smart speaker 200.

For another example, the interactive device 300 is a sword-shaped toy. When the user swings the interactive device 300, the sensor 340 in the interactive device 300 can sense the acceleration value. When the acceleration value is greater than the threshold, the cloud server 100 can play audio data related to the movement of the sword-shaped toy through the smart speaker 200.

In one embodiment, the sensor 340 of the interactive device 300 may include a color sensor. The sensor 340 can be used to detect the color of an object. For example, the interactive device 300 is a color detection pen. Assume that the user has a board with color blocks of multiple different colors drawn on it. The cloud server 100 can instruct the user through the smart speaker 200 to point the interactive device 300 at a color block of one of the colors on the board. After the user points the interactive device 300 at a specific color block on the board, the interactive device 300 can generate a color value corresponding to the specific color block, and can transmit the color value to the cloud server 100 through the smart speaker 200. The cloud server 100 can determine whether the user's operation is correct based on the color value, and play audio data representing "correct" or "error" through the smart speaker 200.

In one embodiment, the sensor 340 of the interactive device 300 may include a pressure sensor. The sensor 340 may be used to detect the pressure value applied to the interactive device 300. The smart speaker 200 may transmit the pressure value received from the interactive device 300 to the cloud server 100. In response to receiving the pressure value, the cloud server 100 plays audio data corresponding to the pressure value through the smart speaker 200.

For example, the interactive device 300 is a keyboard instrument. When the user presses a key on the interactive device 300, the sensor 340 of the interactive device 300 can sense the pressure value. The smart speaker 200 can forward the pressure value to the cloud server 100. The cloud server 100 can play audio data corresponding to the key and/or the pressure value through the smart speaker 200 in response to receiving the pressure value.

For another example, the interactive device 300 is a percussion instrument. When the user strikes the interactive device 300 (e.g., strikes the drumhead of the interactive device 300), the sensor 340 of the interactive device 300 can sense the pressure value. The smart speaker 200 can forward the pressure value to the cloud server 100. In response to receiving the pressure value, the cloud server 100 can play audio data corresponding to the pressure value through the smart speaker 200.

In one embodiment, the sensor 340 of the interactive device 300 may include a button. When the user presses the sensor 340, the sensor 340 may generate a pulse signal. The interactive device 300 may transmit the pulse signal to the cloud server through the smart speaker 200. The cloud server 100 may play audio data corresponding to the pulse signal through the smart speaker 200 in response to receiving the pulse signal.

FIG5 is a schematic diagram of an interactive device 300 according to an embodiment of the present invention. In this embodiment, the interactive device 300 may include a sensor 340 and an image output interface 350. The sensor 340 of the interactive device 300 may be, for example, a button. When the user presses the sensor 340, the sensor 340 may generate a pulse signal. The interactive device 300 may forward the pulse signal to the cloud server 100 through the smart speaker 200. The image output interface 350 may be provided on the surface of the sensor 340, and the image output interface 350 may be, for example, an LED array. The image output interface 350 can be controlled by the processor 310 or the cloud server 100 to play images from the cloud server 100 or pre-stored in the storage medium 320 .

FIG6 is a schematic diagram showing an image output through the image output interface 350 according to an embodiment of the present invention. The image output interface 350 can output, for example, animal patterns (e.g., cats or dogs), geometric shapes (e.g., hearts, circles, or squares), numbers (e.g., 22), or emoticons (e.g., smiling faces or crying faces), as shown in FIG6 , but the present invention is not limited thereto.

In one embodiment, the cloud server 100 can control the image output interface 350 to play the image for countdown through the smart speaker 200. For example, the cloud server 100 can play audio data through the smart speaker 200 to ask questions to the user, and control the image output interface 350 to play the image for countdown. If the cloud server 100 receives audio data corresponding to the correct answer through the smart speaker 200 before the countdown ends, the cloud server 100 can determine that the user's answer is correct. Accordingly, the cloud server 100 can play the audio data corresponding to "correct" through the smart speaker 200. On the other hand, if the cloud server 100 does not receive the audio data corresponding to the correct answer through the smart speaker 200 before the countdown ends, the cloud server 100 can determine that the user's answer is wrong. Accordingly, the cloud server 100 can play the audio data corresponding to "error" through the smart speaker 200.

In one embodiment, the cloud server 100 may play audio data corresponding to the sensing data through the smart speaker 200 in response to receiving sensing data (or audio data) from the smart speaker 200 during the playback of the image. For example, the cloud server 100 may play audio data through the smart speaker 200 to indicate that the user presses the sensor 340 during the period when the image output interface 350 outputs a specific image, wherein the sensor 340 is, for example, a button. Then, the cloud server 100 may play audio data through the smart speaker 200 in response to receiving a pulse signal generated by the user pressing the sensor 340 during the period when the image output interface 350 displays the specific image, thereby indicating that the user's response is correct through the audio data.

In one embodiment, the cloud server 100 may instruct the image output interface 350 to play the image corresponding to the sensing data through the smart speaker 200 in response to receiving the sensing data (or audio data) from the smart speaker 200 during the playback of the image. For example, the cloud server 100 may instruct the user to press the sensor 340 during the period when the image output interface 350 outputs a specific image by playing the audio data through the smart speaker 200, wherein the sensor 340 is, for example, a button. Then, the cloud server 100 may determine that the time point when the user presses the sensor 340 is correct in response to receiving the pulse signal generated by the user pressing the sensor 340 during the period when the image output interface 350 outputs the specific image. Accordingly, the cloud server 100 can control the image output interface 350 through the smart speaker 200, so as to display the image corresponding to the "correct" through the image output interface 350, wherein the image is, for example, a smiley face. On the other hand, the cloud server 100 can play the audio data corresponding to the "correct" through the smart speaker 200.

FIG. 7 is a flow chart of a method for executing a quiz game according to an embodiment of the present invention, wherein the method can be implemented by the interactive system 10 shown in FIG. 1 , wherein the interactive device 300 of the interactive system 10 is, for example, the interactive device 300 shown in FIG. 5 .

In step S701, the cloud server 100 may detect audio data corresponding to the user's call. In this embodiment, any audio data obtained by the cloud server 100 is, for example, generated from the microphone 240 of the smart speaker 200 or the microphone of the interactive device 300. If the source of the audio data is the microphone of the interactive device 300, the sensor 340 of the interactive device 300 shown in FIG5 may further include a microphone in addition to a button.

In step S702, the cloud server 100 can play audio data to respond to the user's call through the smart speaker 200. On the other hand, the cloud server 100 can instruct the image output interface 350 of the interactive device 300 to display an image for responding to the user's call through the smart speaker 200.

In step S703, the cloud server 100 may start executing an interactive process in response to the user's call, wherein the interactive process is, for example, a question-and-answer game.

In step S704, the cloud server 100 can play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to explain the game content to the user and ask the user to select the difficulty. On the other hand, the cloud server 100 can instruct the image output interface 350 of the interactive device 300 to display an image for the user to select the difficulty through the smart speaker 200.

In step S705, the cloud server 100 can determine the difficulty of the user's selection based on the audio data from the smart speaker 200.

In step S706, the cloud server 100 may play audio data through the smart speaker 200 to confirm with the user whether to start the quiz game.

In step S707, the cloud server 100 can determine whether the user agrees to start the quiz game based on the audio data from the smart speaker 200.

In step S708 , the cloud server 100 may start playing the audio data for the countdown through the smart speaker 200 . The cloud server 100 may further play the image for the countdown through the image output interface 350 of the interactive device 300 .

In step S709, after the countdown ends, the cloud server 100 can play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask questions or give instructions to the user. For example, the cloud server 100 can instruct the user to press the sensor 340 on the interactive device 300 when the image output interface 350 of the interactive device 300 displays a specific animal through the smart speaker 200.

In step S710, the cloud server 100 can control the image output interface 350 of the interactive device 300 to randomly display multiple different images through the smart speaker 200, wherein the multiple images include, for example, images of various types of animals, numbers, or symbols. In addition, the cloud server 100 can further randomly play multiple different audio data through the smart speaker 200, wherein the multiple audio data include, for example, sounds of various types of animals.

In step S711, the cloud server 100 may receive a pulse signal generated from the sensor 340 from the smart speaker 200, and determine whether the time when the user presses the sensor 340 is correct based on the pulse signal. For example, if the user presses the sensor 340 when the image output interface 350 displays an image of a specific animal specified by the cloud server 100, the cloud server 100 may determine that the user's response is correct. If the user presses the sensor 340 when the image output interface 350 displays an image of another animal not specified by the cloud server 100, or the user does not press the sensor 340 within a preset time, the cloud server 100 may determine that the user's response is wrong.

In step S712, the cloud server 100 may respond to judging that the user's response is correct by playing the audio data corresponding to "correct" through the smart speaker 200. On the other hand, the cloud server 100 may respond to judging that the user's response is correct by instructing the image output interface 350 of the interactive device 300 to display the image corresponding to "correct" through the smart speaker 200.

In step S713, the cloud server 100 may receive audio data for requesting to change the difficulty level of the quiz game through the smart speaker 200.

In step S714, the cloud server 100 may play audio data through the smart speaker 200 to inquire the user about the difficulty level to be selected.

In step S715 , the cloud server 100 may receive audio data for selecting the difficulty level through the smart speaker 200 .

In step S716, the cloud server 100 may play audio data through the smart speaker 200 to confirm with the user whether to start the quiz game.

In step S717, the cloud server 100 can determine whether the user agrees to start the quiz game based on the audio data from the smart speaker 200.

In step S718, the cloud server 100 can play the audio data for countdown through the smart speaker 200. On the other hand, the cloud server 100 can instruct the image output device 350 of the interactive device 300 to play the image for countdown through the smart speaker 200.

In step S719, after the countdown ends, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask questions or give instructions to the user.

In step S720, the cloud server 100 can control the image output interface 350 of the interactive device 300 to randomly display multiple different images through the smart speaker 200, wherein the multiple images include, for example, images of various types of animals, numbers, or symbols. In addition, the cloud server 100 can further randomly play multiple different audio data through the smart speaker 200, wherein the multiple audio data include, for example, sounds of various types of animals.

In step S721, the cloud server 100 may receive a pulse signal generated from the sensor 340 from the smart speaker 200, and determine whether the time when the user presses the sensor 340 is correct based on the pulse signal. For example, if the user presses the sensor 340 when the image output interface 350 displays an image of a specific animal specified by the cloud server 100, the cloud server 100 may determine that the user's response is correct. If the user presses the sensor 340 when the image output interface 350 displays an image of another animal not specified by the cloud server 100, or the user does not press the sensor 340 within a preset time, the cloud server 100 may determine that the user's response is wrong.

In step S722, the cloud server 100 may respond to judging that the user's response is correct by playing the audio data corresponding to "correct" through the smart speaker 200. On the other hand, the cloud server 100 may respond to judging that the user's response is correct by instructing the image output interface 350 of the interactive device 300 to display the image corresponding to "correct" through the smart speaker 200.

In step S723, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask questions or give instructions to the user.

In step S724, the cloud server 100 may determine that the user has instructed the interactive system 10 to terminate the ongoing quiz game in response to receiving audio data corresponding to the termination command from the smart speaker 200 (e.g., generated by the microphone 240 of the smart speaker 200).

In step S725, the cloud server 100 may play audio data corresponding to "error" through the smart speaker 200 in response to determining that the user's response is erroneous. On the other hand, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 to display an image corresponding to "error" through the smart speaker 200 in response to determining that the user's response is erroneous.

In step S726, the cloud server 100 may play audio data through the smart speaker 200 to inquire whether the user is ready to accept the punishment game.

In step S727, the cloud server 100 can determine whether the user agrees to start the punishment game based on the audio data from the smart speaker 200.

In step S728, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to inquire the user about the type of punishment game he wants to play.

In step S729, the cloud server 100 can determine the punishment game selected by the user based on the audio data from the smart speaker 200.

In step S730, the cloud server 100 can play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to instruct the user to play the punishment game. For example, the cloud server 100 can instruct the user to perform push-ups through the smart speaker 200.

In step S731, the interactive system 10 may end the quiz game. Before ending the quiz game, the cloud server 100 may play audio data through the smart speaker 200 to notify the user that the quiz game is about to end. In addition, the cloud server 100 may also instruct the image output interface 350 of the interactive device 300 to play an image through the smart speaker 200 to notify the user that the quiz game is about to end.

FIG8 is a schematic diagram showing another embodiment of the interactive device 300 according to an embodiment of the present invention. In this embodiment, the interactive device 300 may include a sensor 340 and an image output interface 350. The sensor 340 of the interactive device 300 may be, for example, an accelerometer. When the interactive device 300 is tilted, the sensor 340 may detect the interactive device 300 and generate a corresponding tilt value. The image output interface 350 may be, for example, an LED array. The image output interface 350 may be controlled by the processor 310 or the cloud server 100 to play images from the cloud server 100 or pre-stored in the storage medium 320, wherein the image output interface 350 may be associated with the tilt value.

In one embodiment, the interactive device 300 can transmit the tilt value to the cloud server 100 through the smart speaker 200. The cloud server 100 can send a command to the interactive device 300 through the smart speaker 200 according to the tilt value, thereby instructing the image output interface 350 to play the image corresponding to the tilt value. In one embodiment, the processor 310 of the interactive device 300 can send a control command to the image output interface 350 according to the tilt value, thereby instructing the image output interface 350 to play the image corresponding to the tilt value.

In one embodiment, the cloud server 100 may ask questions to the user through the smart speaker 200. The user may answer the questions while maintaining the balance of the interactive device 300. The cloud server 100 may receive audio data corresponding to the user's answer and the tilt value generated by the sensor 340 of the interactive device 300 through the smart speaker 200. If the cloud server 100 determines that the user can maintain the balance of the interactive device 300 so that the tilt value generated by the sensor 340 is less than the threshold, and the user's answer matches the reference data pre-stored in the storage medium 120 of the cloud server 100, the cloud server 100 may play the audio data corresponding to the "correct" answer through the smart speaker 200. On the other hand, if the cloud server 100 determines that the user cannot maintain the balance of the interactive device 300, causing the tilt value generated by the sensor 340 to be greater than or equal to the threshold, or the user's answer does not match the reference data in the storage medium 120, the cloud server 100 can play audio data corresponding to "error" through the smart speaker 200.

In one embodiment, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 to display an object corresponding to the tilt value through the smart speaker 200 according to the tilt value. In this embodiment, the object corresponding to the tilt value is, for example, an image of a ball. When the tilt value is smaller, the cloud server 100 may instruct the image output interface 350 to display the image of the object corresponding to the tilt value at a position closer to the center of the image output interface 350. When the tilt value is larger, the cloud server 100 may instruct the image output interface 350 to display the image of the object corresponding to the tilt value at a position farther from the center of the image output interface 350.

FIG. 9 is a schematic diagram showing an image outputting an image corresponding to a tilt value through the image output interface 350 according to an embodiment of the present invention. As shown in FIG. 9 , image 361 or image 362 corresponds to a smaller tilt value, and image 363 or image 364 corresponds to a larger tilt value. The fact that image 362 is closer to the center of the image output interface 350 than image 361 indicates that the tilt value corresponding to image 362 is smaller than the tilt value corresponding to image 361. The cloud server 100 may instruct the image output interface 350 to change the appearance of the displayed image in response to the tilt value being greater than the threshold value. For example, the cloud server 100 may instruct the image output interface 350 to display the image 361 or 362 corresponding to the tilt value less than or equal to the threshold in a lighter color, and to display the image 363 or 364 corresponding to the tilt value greater than the threshold in a darker color.

FIG. 10 is a flow chart showing another method for executing a quiz game according to an embodiment of the present invention, wherein the method can be implemented by the interactive system 10 shown in FIG. 1 , wherein the interactive device 300 of the interactive system 10 is, for example, the interactive device 300 shown in FIG. 8 .

In step S1001, the cloud server 100 may detect audio data corresponding to a user's call. In this embodiment, any audio data obtained by the cloud server 100 is, for example, generated from the microphone 240 of the smart speaker 200 or the microphone of the interactive device 300. If the source of the audio data is the microphone of the interactive device 300, the sensor 340 of the interactive device 300 shown in FIG8 may further include a microphone in addition to an accelerometer.

In step S1002, the cloud server 100 can play audio data to respond to the user's call through the smart speaker 200. On the other hand, the cloud server 100 can instruct the image output interface 350 of the interactive device 300 to display an image for responding to the user's call through the smart speaker 200.

In step S1003, the cloud server 100 may start executing an interactive process in response to the user's call, wherein the interactive process is, for example, a question-and-answer game.

In step S1004, the cloud server 100 can play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to explain the game content to the user and ask the user to select the difficulty. On the other hand, the cloud server 100 can instruct the image output interface 350 of the interactive device 300 to display an image for the user to select the difficulty through the smart speaker 200.

In step S1005, the cloud server 100 can determine the difficulty of the user's selection based on the audio data from the smart speaker 200.

In step S1006, the cloud server 100 may play audio data via the smart speaker 200 to inquire the user about the length of the game time.

In step S1007, the cloud server 100 can determine the length of the game time selected by the user based on the audio data from the smart speaker 200.

In step S1008, the cloud server 100 may play audio data through the smart speaker 200 to confirm with the user whether to explain the game rules to the user.

In step S1009, the cloud server 100 can determine whether to explain the game rules to the user based on the audio data from the smart speaker 200.

In step S1010, the cloud server 100 may respond to the determination to explain the game rules to the user by playing audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to explain the game rules to the user.

In step S1011, the cloud server 100 can determine whether the user agrees to start the quiz game based on the audio data from the smart speaker 200.

In step S1012, the cloud server 100 can start playing the audio data for the countdown through the smart speaker 200. The cloud server 100 can further play the image for the countdown through the image output interface 350 of the interactive device 300.

In step S1013, after the countdown ends, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask questions to the user.

In step S1014, the cloud server 100 may receive audio data corresponding to the user's answer from the smart speaker 200.

In step S1015, the cloud server 100 may determine whether the user's answer matches the reference data pre-stored in the storage medium 120 of the cloud server 100, and in response to the user's answer matching the reference data, record the number of correct answers of the user in the user data of the user in the storage medium 120. Then, the cloud server 100 may play the audio data through the smart speaker 200 to instruct the user to pass the interactive device 300 to the next user, and the next user will answer the next question.

In step S1016, the cloud server 100 may receive audio data corresponding to the user's answer from the smart speaker 200.

In step S1017, the cloud server 100 may determine whether the user's answer matches the reference data pre-stored in the storage medium 120 of the cloud server 100, and in response to the user's answer not matching the reference data, record the number of times the user's answer is wrong in the user data of the user in the storage medium 120. Then, the cloud server 100 may play audio data through the smart speaker 200 to instruct the user to continue answering the next question.

In step S1018, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask the user a question. Then, the cloud server 100 may receive audio data corresponding to the user's answer from the smart speaker 200, and determine whether the user's answer matches the reference data pre-stored in the storage medium 120 of the cloud server 100. If the user's answer matches the reference data, then proceed to step S1019. If the user's answer does not match the reference data, then proceed to step S1020.

In step S1019, the cloud server 100 may record the number of correct answers of the user in the user data of the user in the storage medium 120 in response to the user's answer matching the reference data.

In step S1020 , the cloud server 100 records the number of incorrect answers of the user in the user data of the user in the storage medium 120 in response to the user's answer not matching the reference data.

In step S1021, the cloud server 100 may play audio data representing "correct" through the smart speaker 200. On the other hand, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play an image representing "correct". Then, the cloud server 100 may play audio data through the smart speaker 200 to prompt the user to pass the interactive device 300 to the next user. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play an image to prompt the user to pass the interactive device 300 to the next user.

In step S1022, the cloud server 100 may play audio data representing "error" through the smart speaker 200. On the other hand, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play an image representing "error". Then, the cloud server 100 may play audio data through the smart speaker 200 to prompt the user not to pass the interactive device 300 to the next user and continue to answer the next question. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play an image to prompt the user not to pass the interactive device 300 to the next user and continue to answer the next question.

In step S1023, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask the user a question. Then, the cloud server 100 may receive audio data corresponding to the user's answer from the smart speaker 200, and determine whether the user's answer matches the reference data pre-stored in the storage medium 120 of the cloud server 100. If the user's answer matches the reference data, then proceed to step S1024. If the user's answer does not match the reference data, then proceed to step S1025.

In step S1024, the cloud server 100 may record the number of correct answers of the user in the user data of the user in the storage medium 120 in response to the user's answer matching the reference data.

In step S1025, the cloud server 100 records the number of incorrect answers of the user in the user data of the user in the storage medium 120 in response to the user's answer not matching the reference data.

In step S1026, the cloud server 100 may play the audio data representing "correct" through the smart speaker 200. On the other hand, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play the image representing "correct". Then, the cloud server 100 may play the audio data through the smart speaker 200 to prompt the user to pass the interactive device 300 to the next user. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 through the smart speaker 200 to play the image to prompt the user to pass the interactive device 300 to the next user.

In step S1027, the cloud server 100 may determine whether the number of wrong answers given by the user is greater than a threshold, and in response to the number of wrong answers given by the user being greater than the threshold, determine that the user has lost the quiz game. The cloud server 100 may play audio data (e.g., an explosion sound effect) through the smart speaker 200 to prompt the user that he has lost the quiz game. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 to play an image (e.g., an image of a crying face) through the smart speaker 200 to prompt the user that he has lost the quiz game.

In step S1028, the cloud server 100 can determine whether the user has maintained the balance of the interactive device 300 based on the sensed value from the smart speaker 200 (i.e., the tilt value generated by the sensor 340). Specifically, the cloud server 100 can determine whether the tilt value is less than the threshold value. If the tilt value is less than the threshold value, the process proceeds to step S1030. If the tilt value is greater than or equal to the threshold value, the process proceeds to step S1029.

In step S1029, the cloud server 100 may determine that the user has lost the quiz game in response to the tilt value being greater than or equal to the threshold value. The cloud server 100 may play audio data (e.g., explosion sound effects) through the smart speaker 200 to prompt the user that the quiz game has been lost. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 to play an image (e.g., a crying face image) through the smart speaker 200 to prompt the user that the quiz game has been lost.

In step S1030, the cloud server 100 may play audio data through the smart speaker 200 according to the script pre-stored in the storage medium 120 to ask questions to the user.

In step S1031, the cloud server 100 may decide to end the quiz game in response to the game time having ended. In addition, the cloud server 100 may also determine which user is the loser of the quiz game based on the user information stored in the storage medium 120. The cloud server 100 may play audio data through the smart speaker 200 to prompt the user that the quiz game has ended or to prompt which user is the loser of the quiz game. In addition, the cloud server 100 may instruct the image output interface 350 of the interactive device 300 to play an image through the smart speaker 200 to prompt the user that the quiz game has ended or to prompt which user is the loser of the quiz game.

In step S1032, the interactive system 10 may end the quiz game. Before ending the quiz game, the cloud server 100 may play audio data through the smart speaker 200 to notify the user that the quiz game is about to end. In addition, the cloud server 100 may also instruct the image output interface 350 of the interactive device 300 to play an image through the smart speaker 200 to notify the user that the quiz game is about to end.

FIG11 is a flow chart of an audio-based interactive method according to an embodiment of the present invention, wherein the interactive method can be implemented as the interactive system 10 shown in FIG1 . In step S1101, at least one sensor 340 of the interactive device 300 and one of the microphones 240 of the smart speaker 200 generate first sensing data, wherein the at least one sensor 340 includes at least one of a button, an accelerometer, a color sensor, and a pressure sensor. In step S1102, the interactive device 300 is connected to the cloud server 100 through the smart speaker 200 for communication. In step S1103 , the cloud server 100 plays first audio data corresponding to the first sensing data through the smart speaker 200 and plays a first image corresponding to the first sensing data through the image output interface 350 of the interactive device 300 in response to receiving the first sensing data.

In summary, the interactive system of the present invention provides users with an interactive device with multiple types of sensors. Users can play a question-and-answer game with the smart speaker through the interactive device or the microphone on the smart speaker. The interactive device may include buttons, and the cloud server may determine whether the user presses the button in accordance with the voice command issued by the smart speaker or the image displayed by the interactive device, and control the smart speaker to play the corresponding audio and image based on the judgment result. Multiple users can determine the winner by pressing the button first at the appropriate time, as shown in Figure 12. The interactive device may include an accelerometer, and the cloud server may determine whether the interactive device is in a tilted or swung state based on the sensing data of the accelerometer, thereby controlling the smart speaker to play corresponding audio and images based on the interactive device. For example, multiple users can pass the interactive device and answer questions played by the smart speaker. If a specific user answers incorrectly or tilts the interactive device too much, the cloud server may determine that the specific user has lost the game, as shown in Figure 13. The interactive device may include a color sensor or a pressure sensor, and the cloud server may control the smart speaker to play corresponding audio based on the color value or pressure value measured by the interactive device. Accordingly, users can interact with the smart speaker through the interactive device to obtain a more diverse entertainment experience.

10: Interactive system 100: Cloud server 110, 210, 310: Processor 120, 220, 320: Storage media 130, 230, 330: Transceiver 200: Smart speaker 240: Microphone 300: Interactive device 340: Sensor 350: Image output interface 361, 362, 363, 364: Image S701, S702, S703, S704, S705, S706, S707, S708, S709, S710, S711, S712, S713, S714, S715, S716, S717, S718, S719, S720, S721, S722, S723, S72 4. S725, S726, S727, S728, S729, S730, S731, S1001, S1002, S1003, S1004, S1005, S1006, S1007, S1008, S1009, S1010, S1011, S1012, S1013, S1014, S10 15. S1016, S1017, S1018, S1019, S1020, S1021, S1022, S1023, S1024, S1025, S1026, S1027, S1028, S1029, S1030, S1031, S1032, S1101, S1102, S1103: Step

FIG. 1 is a schematic diagram of an audio-based interactive system according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a cloud server according to an embodiment of the present invention. FIG. 3 is a schematic diagram of a smart speaker according to an embodiment of the present invention. FIG. 4 is a schematic diagram of an interactive device according to an embodiment of the present invention. FIG. 5 is a schematic diagram of an interactive device according to an embodiment of the present invention. FIG. 6 is a schematic diagram of outputting an image through an image output interface according to an embodiment of the present invention. FIG. 7 is a flow chart of a method for executing a question-and-answer game according to an embodiment of the present invention. FIG. 8 is a schematic diagram of another embodiment of an interactive device according to an embodiment of the present invention. FIG. 9 is a schematic diagram of outputting an image corresponding to a tilt value through an image output interface according to an embodiment of the present invention. FIG. 10 is a flow chart of another method for executing a quiz game according to an embodiment of the present invention. FIG. 11 is a flow chart of an audio-based interactive method according to an embodiment of the present invention. FIG. 12 is a schematic diagram of using an interactive device to perform a quiz game according to an embodiment of the present invention. FIG. 13 is a schematic diagram of using an interactive device to perform a quiz game according to another embodiment of the present invention.

S1101, S1102, S1103: Steps

Claims (25)

An audio-based interactive system includes: a cloud server storing first audio data and a first image; a smart speaker including a microphone and communicatively connected to the cloud server; and an interactive device including at least one sensor and an image output interface and communicatively connected to the smart speaker, wherein the at least one sensor includes an accelerometer, wherein one of the at least one sensor and the microphone generates first sensing data, wherein the first sensing data includes a tilt value; the interactive device is communicatively connected to the cloud server through the smart speaker; and the cloud server plays the first audio data corresponding to the first sensing data through the smart speaker and plays the first image corresponding to the first sensing data through the image output interface in response to receiving the first sensing data and the tilt value being less than a first threshold. An interactive system as described in claim 1, wherein the cloud server further stores reference data, and the cloud server determines whether to play the first audio data and the first image based on the matching result between the first sensing data and the reference data. An interactive system as described in claim 1, wherein the cloud server plays the second audio data through the smart speaker, and decides to play the first audio data and the first image in response to receiving the first sensing data within a preset time after playing the second audio data. An interactive system as described in claim 1, wherein the at least one sensor of the interactive device further includes a button, and the first sensing data further includes a pulse signal, wherein the surface of the button is provided with the image output interface, wherein the cloud server plays the image through the image output interface, and in response to receiving the pulse signal during the playback of the image, plays the first audio data through the smart speaker and plays the first image through the image output interface. An interactive system as described in claim 1, wherein the at least one sensor further includes a second microphone. An interactive system as described in claim 1, wherein the first image corresponds to the tilt value. An interactive system as described in claim 1, wherein the first sensing data further includes audio data, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the audio data matching the reference data stored in the cloud server and the tilt value being less than the first threshold. An interactive system as described in claim 7, wherein the cloud server plays the image used for countdown through the image output interface, and in response to receiving the audio data before the countdown ends, plays the first audio data through the smart speaker and the first image through the image output interface. An interactive system as described in claim 1, wherein the first sensing data further includes audio data, wherein the cloud server further stores a speech recognition model and user information, and the speech recognition model is used to recognize the user corresponding to the audio data to generate a recognition result, and the user information is updated according to the recognition result. An interactive system as described in claim 1, wherein the first sensing data further includes an acceleration value, wherein the cloud server plays the first audio data through the smart speaker and displays the first image through the image output interface in response to the acceleration value being greater than a second threshold. An interactive system as described in claim 1, wherein the at least one sensor further includes a color sensor, and the first sensing data further includes a color value. An interactive system as described in claim 1, wherein the at least one sensor further includes a pressure sensor, and the first sensing data further includes a pressure value. An audio-based interaction method is applicable to an interactive system including a cloud server, a smart speaker, and an interactive device, wherein the interaction method includes: generating first sensing data by at least one sensor of the interactive device and one of the microphones of the smart speaker, wherein the at least one sensor includes an accelerometer, wherein the first sensing data includes a tilt value; the interactive device is connected to the cloud server through the smart speaker for communication; and the cloud server responds to receiving the first sensing data and the tilt value is less than a first threshold by playing first audio data corresponding to the first sensing data through the smart speaker and playing a first image corresponding to the first sensing data through the image output interface of the interactive device. As described in claim 13, the cloud server further stores reference data, and the cloud server determines whether to play the first audio data and the first image based on the matching result between the first sensing data and the reference data. The interactive method as described in claim 13, wherein the cloud server plays the second audio data through the smart speaker, and decides to play the first audio data and the first image in response to receiving the first sensing data within a preset time after playing the second audio data. As described in claim 13, the at least one sensor of the interactive device further includes a button, and the first sensing data further includes a pulse signal, wherein the surface of the button is provided with the image output interface, wherein the cloud server plays the image through the image output interface, and in response to receiving the pulse signal during the playback of the image, plays the first audio data through the smart speaker and plays the first image through the image output interface. An interactive method as described in claim 13, wherein the at least one sensor further includes a second microphone. An interactive method as described in claim 13, wherein the first image corresponds to the tilt value. The interactive method as described in claim 13, wherein the first sensing data further includes audio data, wherein the cloud server plays the first audio data through the smart speaker and plays the first image through the image output interface in response to the audio data matching the reference data stored in the cloud server and the tilt value being less than the first threshold. The interactive method as described in claim 19, wherein the cloud server plays the image used for countdown through the image output interface, and in response to receiving the audio data before the countdown ends, plays the first audio data through the smart speaker and the first image through the image output interface. As described in claim 13, the first sensing data further includes audio data, wherein the cloud server further stores a speech recognition model and user information, identifies the user corresponding to the audio data by the speech recognition model to generate a recognition result, and updates the user information according to the recognition result. As described in claim 13, the first sensing data further includes an acceleration value, wherein the cloud server plays the first audio data through the smart speaker and the first image through the image output interface in response to the acceleration value being greater than a second threshold. The interactive method as described in claim 13, wherein the at least one sensor further includes a color sensor, and the first sensing data further includes a color value. An interactive method as described in claim 14, wherein the at least one sensor further includes a pressure sensor, and the first sensing data further includes a pressure value. An interactive device is suitable for interacting with a cloud server and a smart speaker, wherein the interactive device includes: a transceiver, communicatively connected to the smart speaker, and communicatively connected to the cloud server through the smart speaker; at least one sensor, generating first sensing data, wherein the at least one sensor includes an accelerometer, and the first sensing data includes a tilt value; an image output interface; and a processor, coupled to the transceiver, the at least one sensor, and the image output interface, wherein the processor transmits the first sensing data through the transceiver, receives a first image corresponding to the first sensing data through the transceiver in response to the tilt value being greater than a first threshold, and plays the first image through the image output interface, wherein the first sensing data is used to instruct the cloud server to configure the smart speaker to play first audio data corresponding to the first sensing data.

Images