TWI702512B - Intelligent assistant device - Google Patents

Abstract

An intelligent assistant device includes an intelligent speaker and plurality of voice transmission device. All of the voice transmission devices connect each other and connect to the intelligent assistant device. The voice transmission device includes a voice input unit, a voice output unit and a communication unit. The voice input unit is used for receives a voice and generates a voice signal. The communication unit transmits the voice signal to the intelligent speaker. The intelligent speaker generates a feedback information based on the voice signal. The feedback information transmits to the voice transmission device. The voice output unit output the feedback information based on a speech.

Description

Smart assistant device

The invention provides an assistant device, in particular an intelligent assistant device.

In the prior art, the smart speaker device is mostly a single hardware, and the microphone receiving hole is on the surface of the smart speaker device, and the user must be close to the body of the smart speaker device when using it.

In addition, if you want to use it in more than two spaces, such as a kitchen and a bedroom, users can only choose to take the smart speaker to another space, or buy another smart speaker to be used in a different space, which not only requires extra money , Also cause inconvenience in use.

Furthermore, in the prior art, most of the smart speaker devices do not have the user's safety protection function, and therefore, it is impossible to provide further protection measures for the user's home safety.

In view of this, the present invention provides a smart assistant device, including: a smart speaker; and a plurality of voice transmission devices, which are connected to each other to form a local network and connected to the smart speaker. Each voice transmission device includes a voice input unit, a voice output unit, and communication. The sound input unit is used to receive sound to generate sound signals. The communication unit transmits the sound signals to the smart speakers. The smart speakers generate feedback messages based on the sound signals. The feedback messages are transmitted to the corresponding voice transmission device and the sound output unit uses voice Mode output.

Wherein, at least one voice transmission device further includes a proximity sensor to activate or disable the voice input unit or communication unit of the voice transmission device according to the signal of the proximity sensor.

Furthermore, the smart speaker stores the location of each voice transmission device, and locates the location of the voice transmission device according to the generated sound signal.

In addition, at least one voice transmission device further includes a camera for shooting images to generate image signals, and the communication unit transmits the image signals to the smart speaker.

Based on this, the smart speaker further includes a judgment module for judging whether the image signal is in a critical condition.

Furthermore, the smart speaker further includes a warning module, which is used to issue a warning when it is judged as a critical condition.

In addition, the smart speaker also includes a voice assistant module for recognizing sound signals as semantic information.

Based on this, when the voice assistant module recognizes the semantic information as distress information, the smart speaker sends out distress messages.

Among them, the present invention further includes a remote mobile device for receiving distress messages from the smart speaker.

Furthermore, the speaker device further includes an operation module for receiving operations or text input.

The detailed features and advantages of the present invention are described in detail in the following embodiments. The content is sufficient to enable anyone familiar with the relevant art to understand the technical content of the present invention and implement it accordingly, and in accordance with the content disclosed in this specification, the scope of patent application and the drawings Anyone who is familiar with the relevant art can easily understand the related purpose and advantages of the present invention.

Please refer to FIG. 1, which is a schematic diagram of the intelligent assistant device of the present invention. The smart assistant device of the present invention includes a smart speaker 10 and a voice transmission device 30.

The smart speaker 10 is a computer host. It can be placed near an unshielded space of a house, such as a living room, but the present invention is not limited to this.

Please refer to FIG. 2 and FIG. 3. FIG. 2 is a schematic diagram of the voice transmission device of the present invention. Figure 3 is a schematic diagram of the smart speaker of the present invention. Here, the voice transmission device 30 is an embedded device or a portable device. According to the present invention, the voice transmission device 30 may be plural, and they can be connected to each other to form a local area network. At the same time, the voice transmission device 30 And connect to smart speaker 10. Furthermore, the voice transmission device 30 can be placed in the kitchen, bedroom, doorway, etc. according to requirements. And it can be connected to the Internet of Things devices used in smart homes, such as smart switches, human sensors, gas detectors, and electronic locks.

The voice transmission device 30 includes a voice input unit 31, a voice output unit 32 and a communication unit 33. Preferably, the sound input unit 31 can be a microphone or other tools that can be used to receive sound. When the voice transmission device 30 is placed in a kitchen, a bedroom, a doorway, etc., the voice input unit 31 receives the sound from these places and converts the sound into a sound signal. Based on this, the communication unit 33 will transmit the audio signal to the smart speaker 10. At this time, the smart speaker 10 will generate a feedback message according to the received sound signal. Then, the feedback message will be transmitted to the corresponding voice transmission device 30 (that is, the voice input unit 31 that receives the sound), and then output by the voice output unit 32 on the corresponding voice transmission device 30. The aforementioned communication unit 33 can be a wireless transmission element such as Wi-Fi, Bluetooth, Zigbee, etc. The sound output unit 32 can be a speaker or other sound-producing tool.

In addition, the smart speaker 10 further includes a voice assistant module 11, which can be used to recognize sound signals as semantic information. Here, the voice assistant module 11 is a software or chip module and is built in the smart speaker 10. Based on this, the smart speaker 10 can generate a feedback message and send it to the corresponding voice transmission device 30 after identifying the received sound signal as semantic information. In some embodiments, the voice assistant module 11 transmits the sound signal to the server, and receives the result of semantic analysis of the sound signal by the server, and generates a feedback message. Furthermore, when the voice assistant module recognizes that the semantic information is a help message, the feedback message is a help message, that is, the smart speaker 10 will send a help message.

Please refer to FIG. 4, which is a schematic diagram of another embodiment of the smart assistant device of the present invention. The smart assistant device of the present invention further includes a remote mobile device 40 for receiving the distress message sent by the smart speaker 10. Based on this, when the user is located at the location of the voice transmission device 30 and sends a call for help, other people or rescue units outside can immediately receive the call for help message and go to the location of the user for rescue.

Based on this, the smart speaker 10 stores the location of each voice transmission device 30. For example, the device A is located in the kitchen and the device B is located in the room. The smart speaker 10 will locate the position of the voice transmission device 30 according to the generated sound signal, so that other people can immediately know where the person who is calling for help is located.

Furthermore, the voice transmission device 30 further includes a proximity sensor 34 for activating or disabling the voice input unit 31 or the communication unit 33 of the voice transmission device 30 according to the signal of the proximity sensor 34. Here, the proximity sensor 34 can be an infrared sensor, which can be used to detect whether people are around. If there are people around, the voice transmission device 30 enables the function of receiving or transmitting the sound to the smart speaker 10. Based on this, the voice transmission device 30 can save power. Or, when a person is around, the voice transmission device 30 does not enable the function of sound collection or transmission to the smart speaker 10, so as to ensure the privacy of the user. However, if the user needs voice input at this time, he can additionally trigger the operation through the button.

Please refer to FIG. 5, which is a schematic diagram of another embodiment of the smart assistant device of the present invention. The smart assistant device of the present invention further includes a camera 20 for shooting images and generating image signals. According to the present invention, there are preferably a plurality of cameras, and each location where the voice transmission device 30 is installed is configured There is a camera 20. Based on this, each camera 20 is connected to the smart speaker 10, and the image signal generated by shooting images will be transmitted to the smart speaker 10 through the transmission unit 21 of the camera 20.

Please refer to FIG. 3 again. Based on this, the smart speaker 10 further includes a judging module 12 for judging whether the image signal is a critical condition. For example, the judgment module 12 can preferably be a software program that can be used to judge images or images. When the camera 20 shoots an image, the generated image signal is transmitted to the smart speaker 10 by the transmission unit 21, and the judgment module Group 12 can judge people and things in the image based on the image signal. Furthermore, for example, the determining module 12 can determine whether the person in the image has fallen down, how long it has been in the image that no one has been in the mirror, and so on.

For example, in the present invention, because the sound is received through multiple locations at a long distance, and the smart speaker 10 stores the location of each voice transmission device 30, the sound localization function is added. When the camera 20 is connected, the captured image can be identified through the judgment module 12 to identify whether someone stays in the toilet for too long. When the stay is too long, the voice assistant module 11 will send a call through the voice transmission device 30 Ask for a response. If there has been no response, after reaching a certain number of times, a message will be sent to the designated contact person or contact organization, or the smart speaker 10 will issue a warning, so as to avoid the situation that only the elderly are alone at home and go to the toilet accidentally but no one finds it. Or, when an elderly person falls in the living room or bedroom or in a place without a camera 20 connected to the smart speaker 10, and cannot move but can make a sound, the voice positioning function can allow emergency contact persons or emergency contact agencies to Quickly grasp which floor or place the old man is in, so as not to miss the golden rescue time.

Here, the smart speaker 10 further includes a warning module 13. When the judgment module 12 determines that it is in a critical condition based on the image signal, the warning module 13 will issue a warning to warn users located near the smart speaker 10. Based on this, the warning module 13 can preferably be a light warning device or a warning sound, but the invention is not limited to this.

In addition, the smart speaker 10 further includes an operating module 14 which can be used to receive user input or text input. Here, the operation module 14 can preferably be a keyboard, function button keys, and so on. According to the present invention, it is preferable that three buttons (volume increase, volume decrease, static radio) are arranged on the surface of the smart speaker 10 and equipped with LED light bars to display the status of the smart speaker 10.

In the present invention, the smart speaker and the voice transmission device are connected to form a local network and connected to the smart speaker. The sound signal can be sent to the smart speaker in multiple places, and the smart speaker generates a feedback message based on the sound signal. At the same time, smart speakers have a judgment module that can judge critical situations and locate the place where the critical situation occurs. To solve the problem that in the conventional technology, multiple smart speakers need to be purchased to be placed in different spaces and most smart speaker devices do not have the safety protection function of the user.

Although the technical content of the present invention has been disclosed in the preferred embodiment as above, it is not intended to limit the present invention. Anyone who is familiar with this technique and makes some changes and modifications without departing from the spirit of the present invention should be covered by the present invention Therefore, the scope of protection of the present invention shall be subject to the scope of the attached patent application.

10 Smart speaker 11 Voice Assistant Module 12 Judgment module 13 Warning module 14 Operation module 20 camera twenty one Delivery unit 30 Voice transmission device 31 Voice input unit 32 Sound output unit 33 Communication unit 34 sensor 40 Remote mobile device

[Figure 1] is a schematic diagram of the smart assistant device of the present invention. [Figure 2] is a schematic diagram of the voice transmission device of the present invention. [Figure 3] is a schematic diagram of the smart speaker of the present invention. [Figure 4] is a schematic diagram of another embodiment of the smart assistant device of the present invention. [Figure 5] is a schematic diagram of another embodiment of the smart assistant device of the present invention.

10 Smart speaker 30 Voice transmission device

Claims (9)

A smart assistant device includes: a smart speaker; and a plurality of voice transmission devices connected to each other to form a local area network and connected to the smart speaker. Each voice transmission device includes a voice input unit, a voice output unit, and a communication Unit, the sound input unit is used to receive sound to generate a sound signal, the communication unit transmits the sound signal to the smart speaker, the smart speaker generates a feedback message according to the sound signal, and the feedback message is transmitted to the corresponding The voice transmission device is output by the voice output unit in a voice manner, wherein the smart speaker stores the location of each voice transmission device, and locates the location of the voice transmission device according to the generated voice signal. The smart assistant device according to claim 1, wherein at least one of the voice transmission devices further includes a proximity sensor to activate or disable the voice input unit or the communication of the voice transmission device according to the signal of the proximity sensor unit. The smart assistant device according to claim 1, further comprising a plurality of cameras for shooting images to generate an image signal, wherein each of the cameras is connected to the smart speaker, and a transmission unit of each of the cameras the image signal Send to the smart speaker. The smart assistant device according to claim 3, wherein the smart speaker further includes a judging module for judging whether the image signal is a critical condition. The smart assistant device of claim 4, wherein the smart speaker further includes a warning module, and when the critical condition is determined, the warning module is used to issue a warning. The smart assistant device according to claim 1, wherein the smart speaker further includes a voice assistant module for recognizing the voice signal as semantic information. The smart assistant device according to claim 6, wherein when the voice assistant module recognizes that the semantic information is a distress message, the smart speaker sends a distress message. The smart assistant device described in claim 7 further includes a remote mobile device for receiving the distress message sent by the smart speaker. The smart assistant device according to claim 1, wherein the smart speaker further includes an operation module for receiving an operation or a text input.

Images