Voice AI intelligent Internet of Things platform

Abstract

The invention relates to the technical field of intelligent Internet of Things, and discloses a voice AI intelligent Internet of Things platform, which comprises a circuit board arranged in a magnetic therapy instrument and a plurality of visual cameras arranged outside the magnetic therapy instrument, a master control intelligent chip, a voice recording module, a voice playing module, a user information recording module, a current user information module and a visual analysis module are mounted in the circuit board; an artificial intelligence mode of the magnetic therapy instrument is realized, a user does not need to manually and slowly adjust and set, and the magnetic therapy instrument is more humanized; the visual camera and the visual analysis module are matched together to analyze whether a user is in a sleep state or not, and when the user is in the sleep state, the user can be automatically closed or switched to a small gear, so that the situation that the user manually opens a large gear before sleeping and does not have a set time length is avoided, and the user experience is improved. A user feels uncomfortable or resources are wasted due to long-term use of a large gear or overlong-time magnetic therapy.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent Internet of Things, and in particular to a voice AI intelligent Internet of Things platform. Background Art

[0002] The magnetic therapy devices on the market are not very intelligent. Users only have a few fixed modes when using them, and cannot use the mode they want. They need to adjust and dial manually when using them, which is troublesome. It is even more inconvenient for some elderly people with poor eyesight and not very humane. At present, there is no solution on the market that can make magnetic therapy devices have artificial intelligence functions. Therefore, those skilled in the art provide a voice AI intelligent Internet of Things platform to solve the problems raised in the above background technology. Summary of the invention

[0003] The purpose of the present invention is to provide a voice AI intelligent Internet of Things platform to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A voice AI intelligent Internet of Things platform comprises a circuit board installed inside a magnetic therapy device and a plurality of visual cameras installed outside the magnetic therapy device, wherein a master control intelligent chip, a voice recording module, a voice playback module, a user information recording module, a current user information module, and a visual analysis module are installed inside the circuit board, and the voice recording module, the voice playback module, the user information recording module, the current user information module, and the visual analysis module are all electrically connected to the master control intelligent chip.

[0006] As a further solution of the present invention: a wireless network card and a wired network card are also installed on the circuit board for connecting to a wireless network and a wired network respectively. The user can change the user information recorded in the user information recording module through a mobile phone, a computer or other terminal.

[0007] As a further solution of the present invention: the visual camera is used to perform local recognition of the user, the local part includes the user's face, and the visual camera is connected to a visual analysis module.

[0008] As a further solution of the present invention: the voice recording module is connected to a voice recording button, which is installed on the outer surface of the magnetic therapy device. The voice recognition and reception can be turned on by the voice recording button. The voice playing module is used to play the content stored in the current user information module;

[0009] The voice recording module has a voice feature analysis unit and a voice transmission unit inside. The voice feature analysis unit is used to analyze the keywords in the user's voice, and then transmit them to the user information recording module or the master control intelligent chip through the voice transmission unit; when the voice feature analysis unit analyzes that the keyword is to store user information, the voice transmission unit will transmit the keyword to the user information recording module, and the user information recording module will reorganize and arrange the keywords, and then form a specific user information, which can be switched to the current user information module according to needs; when the voice feature analysis unit analyzes that the keyword is to read user information, the voice transmission unit will transmit the keyword to the master control intelligent chip, and the master control intelligent chip can take corresponding actions.

[0010] As a further solution of the present invention: the user information recording module is used to record the usage information of each user, and the current user information module is used to store the current user usage information;

[0011] The current user information module is connected to the current user switching button, which is installed on the outer surface of the magnetic therapy device. Any user information in the user information recording module can be switched to the current user information module through the current user switching button.

[0012] As a further solution of the present invention: a plurality of visual cameras take real-time photos of the user's face from different angles, and transmit the photographed data to a visual analysis module, wherein a feature acquisition unit, a feature calculation unit, a timing unit and an alarm unit are installed inside the visual analysis module.

[0013] As a further solution of the present invention: the feature acquisition unit is used to acquire images of the user's face and eyes, and transmit the acquired images to the feature calculation unit, and the feature calculation unit is used to calculate the closure value of the user's eyes. When the closure value is lower than the set threshold, the timing unit starts timing. When the value lower than the set threshold continues for a certain period of time, the alarm unit starts and transmits the alarm information to the master control intelligent chip, and the master control intelligent chip controls the magnetic therapy device to take corresponding actions.

[0014] As a further solution of the present invention: the calculation method of the closing value is: construct a linear coordinate system, select the center position of the user's eye as the coordinate origin of the linear coordinate system, and then select six points P1, P2, P3, P4, P5, and P6 on the eye socket for calculation.

[0015] As a further solution of the present invention: the calculation formula of the closed value is:

[0016]

[0017] In formula (1), Q closed is the closed value, P1 is the coordinate point of the left corner of the eye, P4 is the coordinate point of the right corner of the eye, P2 is the coordinate point of the middle left position of the upper eye socket, P3 is the coordinate point of the middle right position of the upper eye socket, P5 is the coordinate point of the middle right position of the lower eye socket, and P6 is the coordinate point of the middle left position of the lower eye socket;

[0018] ‖P2-P6‖ is the distance between P2 and P6, that is, the distance between the middle left position of the upper eye socket and the middle left position of the lower eye socket; ‖P3-P5‖ is the distance between P3 and P5, that is, the distance between the middle right position of the upper eye socket and the middle right position of the lower eye socket; ‖P1-P4‖ is the distance between P1 and P4, that is, the distance between the left corner of the eye and the right corner of the eye.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] The present invention realizes the artificial intelligence mode of the magnetic therapy instrument through the cooperation of the master control intelligent chip, the voice recording module, the voice playing module, the user information recording module, the current user information module, and the visual analysis module. The user can set any mode and use the mode through AI voice, and can also switch any previously set mode when using it. There is no need to manually adjust and set it slowly, which is more user-friendly. When the user does not need a certain mode, he can log in to the network platform of the magnetic therapy instrument APP through a mobile phone, a computer or other terminal to delete or modify the mode. A visual camera is provided, and the visual camera and the visual analysis module can cooperate to analyze whether the user is in a sleeping state. When the user is in a sleeping state, it can automatically turn off or switch to a small gear, avoiding the user manually turning on a large gear before falling asleep and not setting the duration. Long-term use of a large gear or too long magnetic therapy will make the user feel uncomfortable or cause a waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a structural diagram of a voice AI intelligent IoT platform;

[0022] Figure 2 This is a structural diagram of a circuit board in a voice AI intelligent Internet of Things platform. DETAILED DESCRIPTION

[0023] See also Figures 1-2In an embodiment of the present invention, a voice AI intelligent Internet of Things platform includes a circuit board installed inside a magnetic therapy device and a plurality of visual cameras installed outside the magnetic therapy device. A master control intelligent chip, a voice recording module, a voice playback module, a user information recording module, a current user information module, and a visual analysis module are installed inside the circuit board. The voice recording module, the voice playback module, the user information recording module, the current user information module, and the visual analysis module are all electrically connected to the master control intelligent chip.

[0024] Preferably, a wireless network card and a wired network card are also installed on the circuit board for connecting to a wireless network and a wired network respectively. The user can change the user information recorded in the user information recording module through a terminal such as a mobile phone or a computer.

[0025] Preferably, the visual camera is used to perform local recognition of the user, the local area including the user's face, and the visual camera is connected to the visual analysis module.

[0026] Preferably, the voice recording module is connected to the voice recording button, and the voice recording button is installed on the outer surface of the magnetic therapy device. The voice recognition and reception can be turned on by the voice recording button, and the voice playback module is used to play the content stored in the current user information module; the voice recording module has a voice feature analysis unit and a voice transmission unit inside, and the voice feature analysis unit is used to analyze the keywords in the user's voice, and then transmit them to the user information recording module or the master control intelligent chip through the voice transmission unit; when the voice feature analysis unit analyzes that the keyword is to store user information, the voice transmission unit will transmit the keyword to the user information recording module, and the user information recording module will reorganize and arrange the keywords, and then form a specific user information, which can be switched to the current user information module according to needs; when the voice feature analysis unit analyzes that the keyword is to read user information, the voice transmission unit will transmit the keyword to the master control intelligent chip, and the master control intelligent chip can take corresponding actions.

[0027] Preferably, the user information recording module is used to record the usage information of each user, and the current user information module is used to store the current user usage information; the current user information module is connected to the current user switching button, and the current user switching button is installed on the outer surface of the magnetic therapy device. Through the current user switching button, any user information in the user information recording module can be switched to the current user information module.

[0028] Preferably, several visual cameras take real-time photos of the user's face from different angles and transmit the photographed data to a visual analysis module, which is internally equipped with a feature acquisition unit, a feature calculation unit, a timing unit and an alarm unit.

[0029] Preferably, the feature acquisition unit is used to acquire images of the user's face and eyes, and transmit the acquired images to the feature calculation unit, which is used to calculate the closure value of the user's eyes. When the closure value is lower than a set threshold, the timing unit starts timing. When the value lower than the set threshold continues for a certain period of time, the alarm unit starts and transmits the alarm information to the master control intelligent chip, which controls the magnetic therapy device to take corresponding actions.

[0030] Preferably, the closed value is calculated as follows: construct a linear coordinate system, select the exact center of the user's eye as the origin of the linear coordinate system, and then select six points P1, P2, P3, P4, P5, and P6 on the eye socket for calculation.

[0031] Preferably, the calculation formula of the closing value is:

[0032]

[0033] In formula (1), Q closed is the closed value, P1 is the coordinate point of the left corner of the eye, P4 is the coordinate point of the right corner of the eye, P2 is the coordinate point of the middle left position of the upper eye socket, P3 is the coordinate point of the middle right position of the upper eye socket, P5 is the coordinate point of the middle right position of the lower eye socket, and P6 is the coordinate point of the middle left position of the lower eye socket;

[0034] ‖P2-P6‖ is the distance between P2 and P6, that is, the distance between the middle left position of the upper eye socket and the middle left position of the lower eye socket; ‖P3-P5‖ is the distance between P3 and P5, that is, the distance between the middle right position of the upper eye socket and the middle right position of the lower eye socket; ‖P1-P4‖ is the distance between P1 and P4, that is, the distance between the left corner of the eye and the right corner of the eye.

[0035] When the user uses the magnetic therapy device for the first time, he can press the voice recording button to open the voice recording module. For example, the specific keyword of the magnetic therapy device can be "abab, store, 30 minutes for gear 1, 10 minutes for gear 2", the voice recording module will be started, and the voice feature analysis unit will analyze "store", "30 minutes for gear 1", "10 minutes for gear 2", and then transmit "30 minutes for gear 1, 10 minutes for gear 2" as a mode to the user information recording module through the voice transmission unit, define it as mode 1, and then the voice playback module broadcasts "it has been stored as mode 1". When the user wants to use this mode next time, he can turn on the voice recording. The recording button is pressed, and then "abab, read mode 1" is said. The voice feature analysis unit will analyze "read" and "mode 1", and the voice transmission unit will transmit the keyword to the master control smart chip. The master control smart chip starts the user information recording module, and the user information recording module transmits mode 1 to the current user information module. The voice playback module will broadcast "mode 1 is enabled", and the magnetic therapy device will perform 30 minutes in gear 1 and 10 minutes in gear 2. The user can also manually toggle the current user switch button to adjust the current mode. When the user does not need to use this mode, he can log in to the network platform of the magnetic therapy device APP through a mobile phone, computer or other terminal to delete or modify the mode.

[0036] The above “abab” is similar to the voice AI startup “SIRI” of Apple mobile phones, the voice AI startup “Xiaoai Xiaoai” of Xiaomi mobile phones, the voice AI startup “Xiaoyi Xiaoyi” of Huawei mobile phones, etc.

[0037] When the user uses the magnetic therapy device, the visual camera on the magnetic therapy device bracket needs to be aimed at the user's face at various angles and transmit the captured data to the visual analysis module. The feature acquisition unit in the visual analysis module collects images of the user's face and eyes, and analyzes the coordinate points of the user's left eye corner, the coordinate points of the right eye corner, the coordinate points of the middle left position of the upper eye socket, the coordinate points of the middle right position of the upper eye socket, the coordinate points of the middle right position of the lower eye socket, and the coordinate points of the middle left position of the lower eye socket. The feature calculation unit calculates the coordinate points according to the formula The closing value of the user's eyes is calculated, and the threshold of the closing value is 0.25. When the closing value is calculated to be less than 0.25, the timing unit starts timing. When the time less than 0.25 lasts for a certain period of time, the alarm unit starts and transmits the alarm information to the master control smart chip. The master control smart chip controls the magnetic therapy device to turn off or change it to the minimum gear, avoiding some users who manually adjust the high gear mode without limiting the use time. After falling asleep during use, the long-term high gear mode will make the user feel uncomfortable;

[0038] The above-mentioned closure value refers to the degree of closure of the eyes. When the closure degree is less than 0.25, it means that the eyes are closed. Combined with the closure duration, it can be determined that the user is in a sleeping state.

[0039] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0040] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A voice AI intelligent Internet of Things platform, characterized in that: It includes a circuit board installed inside the magnetic therapy device and several visual cameras installed outside the magnetic therapy device. A master control intelligent chip, a voice recording module, a voice playback module, a user information recording module, a current user information module, and a visual analysis module are installed inside the circuit board. The voice recording module, the voice playback module, the user information recording module, the current user information module, and the visual analysis module are all electrically connected to the master control intelligent chip.

2. According to claim 1, a voice AI intelligent Internet of Things platform is characterized in that: The circuit board is also equipped with a wireless network card and a wired network card for connecting to a wireless network and a wired network respectively. The user can change the user information recorded in the user information recording module through a mobile phone, a computer or other terminal.

3. According to claim 1, a voice AI intelligent Internet of Things platform is characterized in that: The visual camera is used to perform local recognition of the user, where the local part includes the user's face, and the visual camera is connected to a visual analysis module.

4. According to claim 1, a voice AI intelligent Internet of Things platform is characterized in that: The voice recording module is connected to a voice recording button, which is installed on the outer surface of the magnetic therapy device. The voice recording button can be used to start voice recognition and reception. The voice playing module is used to play the content stored in the current user information module. The voice recording module has a voice feature analysis unit and a voice transmission unit inside. The voice feature analysis unit is used to analyze the keywords in the user's voice and then transmit them to the user information recording module or the master control smart chip through the voice transmission unit; When the voice feature analysis unit analyzes that the keyword is to store user information, the voice transmission unit will transmit the keyword to the user information recording module, and the user information recording module will reorganize and arrange the keywords to form a specific user information, which can be switched to the current user information module as needed; when the voice feature analysis unit analyzes that the keyword is to read user information, the voice transmission unit will transmit the keyword to the master control intelligent chip, and the master control intelligent chip can take corresponding actions.

5. The voice AI intelligent IoT platform according to claim 1, characterized in that: The user information recording module is used to record the usage information of each user, and the current user information module is used to store the current user usage information; The current user information module is connected to the current user switching button, which is installed on the outer surface of the magnetic therapy device. Any user information in the user information recording module can be switched to the current user information module through the current user switching button.

6. A voice AI intelligent Internet of Things platform according to claim 3, characterized in that: Several of the visual cameras take real-time photos of the user's face from different angles and transmit the photographed data to the visual analysis module, which is internally equipped with a feature acquisition unit, a feature calculation unit, a timing unit and an alarm unit.

7. A voice AI intelligent Internet of Things platform according to claim 6, characterized in that: The feature acquisition unit is used to acquire images of the user's face and eyes, and transmit the acquired images to the feature calculation unit. The feature calculation unit is used to calculate the closure value of the user's eyes. When the closure value is lower than a set threshold, the timing unit starts timing. When the value lower than the set threshold continues for a certain period of time, the alarm unit starts and transmits the alarm information to the master control intelligent chip. The master control intelligent chip controls the magnetic therapy device to take corresponding actions.

8. A voice AI intelligent Internet of Things platform according to claim 7, characterized in that: The calculation method of the closing value is: construct a linear coordinate system, select the center position of the user's eye as the coordinate origin of the linear coordinate system, and then select six points P1, P2, P3, P4, P5, and P6 on the eye socket for calculation.

9. A voice AI intelligent Internet of Things platform according to claim 8, characterized in that: The calculation formula of the closing value is: In formula (1), Q closed is the closed value, P1 is the coordinate point of the left corner of the eye, P4 is the coordinate point of the right corner of the eye, P2 is the coordinate point of the middle left position of the upper eye socket, P3 is the coordinate point of the middle right position of the upper eye socket, P5 is the coordinate point of the middle right position of the lower eye socket, and P6 is the coordinate point of the middle left position of the lower eye socket; ‖P2-P6‖ is the distance between P2 and P6, that is, the distance between the middle left position of the upper eye socket and the middle left position of the lower eye socket; ‖P3-P5‖ is the distance between P3 and P5, that is, the distance between the middle right position of the upper eye socket and the middle right position of the lower eye socket; ‖P1-P4‖ is the distance between P1 and P4, that is, the distance between the left corner of the eye and the right corner of the eye.

Images