CN216562450U

CN216562450U - Voice interaction device based on deep learning

Info

Publication number: CN216562450U
Application number: CN202122786609.4U
Authority: CN
Inventors: 何静
Original assignee: Beihang University
Current assignee: Beihang University
Priority date: 2021-11-15
Filing date: 2021-11-15
Publication date: 2022-05-17
Anticipated expiration: 2031-11-15

Abstract

The utility model discloses a voice interaction device based on deep learning, which relates to the field of voice interaction devices and comprises a voice interaction equipment body, wherein an interaction display screen and a camera are arranged on the voice interaction equipment body, and a controller is arranged on the top side of the voice interaction equipment body. In the utility model, in the process of using the voice interaction equipment body, when writing is needed, a user lifts the cover plate upwards to drive the telescopic rod to move upwards, the pull ring is pulled after the cover plate moves to a certain height, one side of the pull ring is contacted with the top side of the voice interaction equipment body after the pull ring rotates for a half circle, and the opened cover plate is supported, so that the inner side of the cover plate on the cover plate is horizontally arranged, the user can conveniently place books or notes on the cover plate for recording and writing, and the voice interaction can be performed while the user writes, thereby enhancing the effect of the voice interaction.

Description

Voice interaction device based on deep learning

Technical Field

The utility model relates to the technical field of voice interaction devices, in particular to a voice interaction device based on deep learning.

Background

The voice recognition technology is a high technology which enables the machine to convert voice signals into corresponding texts or commands through a recognition and understanding process, and is a cross subject.

Through the retrieval, the patent of publication No. CN213890034U discloses a pronunciation interactive installation based on degree of depth study, belong to pronunciation interactive equipment technical field, specifically install the decoration headset on the robot head, remove the both sides of base and install the decoration leg and be carrying out the pronunciation interactive in-process, most pronunciation interactive equipment does not have the mutual strorage device who uses equipment, the equipment that the interaction needs to use, need place alone, can not take out the use fast when using, and most interactive equipment can not provide auxiliary platform, be used for the record to write, consequently, need a pronunciation interactive installation based on degree of depth study to satisfy people's demand.

SUMMERY OF THE UTILITY MODEL

The utility model aims to provide a voice interaction device based on deep learning, and aims to solve the problems that most voice interaction devices do not have storage devices for interaction devices, the interaction devices need to be used and placed independently, the interaction devices cannot be taken out and used quickly when being used, and most interaction devices cannot provide auxiliary platforms for recording and writing.

In order to achieve the purpose, the utility model provides the following technical scheme: a voice interaction device based on deep learning comprises a voice interaction device body, wherein an interaction display screen and a camera are arranged on the voice interaction device body, a controller is arranged on the top side of the voice interaction device body, a placing box is fixedly arranged on one side of the voice interaction equipment body, a placing groove is arranged on the top side of the placing box, two telescopic grooves are arranged on the top side of the placing box, telescopic rods are movably arranged in the two telescopic grooves, the top ends of the two telescopic rods extend out of the telescopic grooves, and are respectively rotatably provided with rotating support rods, one side of each of the two rotating support rods is fixedly provided with a same cover plate, the cover plate is matched with the placing box, the cover plate is provided with a cover plate outer side surface and a cover plate inner side surface, one side of placing the box is seted up threaded hole, threaded hole and two flexible groove homogeneous phases intercommunication, and the threaded rod is installed to the threaded hole internal thread, and the one end movable mounting of threaded rod is on two telescopic links.

Preferably, a rotating groove is formed in the top side of the telescopic rod, and one end of the rotating support rod is rotatably installed in the rotating groove.

Preferably, a hand-pulling ring is fixedly installed on the outer side face of the cover plate on the cover plate, and one side of the hand-pulling ring is in contact with the top side of the voice interaction device body.

Preferably, one side of two telescopic links has all been seted up and has been opened the fixed orifices and accomodate the fixed orifices, the threaded rod all with open the fixed orifices and accomodate fixed orifices looks adaptation, the one end activity of threaded rod runs through and opens the fixed orifices.

Preferably, the partition plate is placed in the placing groove and is arranged in a cross shape.

Preferably, one end of the threaded rod is fixedly provided with a cross rotating block, and a protective sleeve is sleeved on the cross rotating block.

Preferably, one side of the voice interaction equipment body is provided with a loudspeaker, the top side of the voice interaction equipment body is provided with a mounting groove, and an operation keyboard is placed in the mounting groove.

The utility model has the beneficial effects that:

according to the voice interaction device, when voice interaction is carried out with a voice interaction device body, some interaction devices need to be used, a placing box is arranged on one side of the voice interaction device body, a partition plate is arranged in the placing box and can partition the space in a placing groove, the interaction devices can be placed in order, an interaction display screen, a camera, a loudspeaker and an operation keyboard are arranged on the voice interaction device body, and therefore better voice interaction of users can be facilitated;

in the utility model, in the process of using the voice interaction equipment body, when writing is needed, a user can rotate the threaded rod to rotate, after the threaded rod rotates, the cover plate is lifted upwards, the telescopic rod can be driven to move upwards, after the threaded rod is moved to a certain height, the threaded rod is rotated reversely again, the threaded rod can be driven to move into the opening fixed hole, then the hand pull ring is pulled, after the threaded rod rotates for half a circle, one side of the hand pull ring is contacted with the top side of the voice interaction equipment body, the opened cover plate is supported, the inner side of the cover plate on the cover plate is horizontally arranged, the user can conveniently place books or notes on the cover plate for recording and writing, the writing can be carried out while voice interaction is carried out, the voice interaction effect is enhanced, and when the writing is not used, the writing can be carried out.

Drawings

Fig. 1 is a schematic three-dimensional structure diagram of a deep learning-based speech interaction device according to the present invention;

FIG. 2 is a schematic cross-sectional structural diagram of a deep learning-based speech interaction apparatus according to the present invention;

FIG. 3 is a schematic partial sectional view of a deep learning based speech interaction apparatus according to the present invention;

fig. 4 is a schematic perspective view of a cover plate of a speech interaction device based on deep learning according to the present invention.

In the figure: 1. a voice interaction device body; 2. an interactive display screen; 3. a camera; 4. a controller; 5. a loudspeaker; 6. mounting grooves; 7. operating a keyboard; 8. placing the box; 9. a placement groove; 10. a partition plate; 11. a telescopic groove; 12. a telescopic rod; 13. a rotating groove; 14. rotating the supporting rod; 15. a cover plate; 16. the outer side surface of the cover plate; 17. the inner side surface of the cover plate; 18. a hand-pulling ring; 19. a threaded hole; 20. a threaded rod; 21. opening the fixing hole; 22. and a receiving fixing hole.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.

Referring to fig. 1-4, a voice interaction device based on deep learning comprises a voice interaction device body 1, an interaction display screen 2 and a camera 3 are arranged on the voice interaction device body 1, a controller 4 is arranged on the top side of the voice interaction device body 1, a placing box 8 is fixedly arranged on one side of the voice interaction device body 1, a placing groove 9 is arranged on the top side of the placing box 8, two telescopic grooves 11 are arranged on the top side of the placing box 8, telescopic rods 12 are movably arranged in the two telescopic grooves 11, the top ends of the two telescopic rods 12 extend out of the telescopic grooves 11 and are respectively rotatably provided with a rotating support rod 14, one side of each of the two rotating support rods 14 is fixedly provided with a same cover plate 15, the cover plate 15 is matched with the placing box 8, a cover plate outer side surface 16 and a cover plate inner side surface 17 are arranged on the cover plate 15, a threaded hole 19 is arranged on one side of the placing box 8, and the threaded hole 19 is communicated with the two telescopic grooves 11, a threaded rod 20 is arranged in the threaded hole 19 in a threaded manner, and one end of the threaded rod 20 is movably arranged on the two telescopic rods 12.

In the utility model, a rotating groove 13 is formed on the top side of the telescopic rod 12, one end of a rotating support rod 14 is rotatably arranged in the rotating groove 13, and the rotating support rod 14 can rotate on the telescopic rod 12.

In the utility model, a hand-pulling ring 18 is fixedly arranged on the outer side surface 16 of the cover plate on the cover plate 15, and one side of the hand-pulling ring 18 is in contact with the top side of the voice interaction equipment body 1, so that the cover plate 15 is driven to rotate by pulling the hand-pulling ring 18.

According to the utility model, the opening fixing holes 21 and the storage fixing holes 22 are formed in one side of each of the two telescopic rods 12, the threaded rods 20 are matched with the opening fixing holes 21 and the storage fixing holes 22, one ends of the threaded rods 20 movably penetrate through the opening fixing holes 21, when writing is required, a user can rotate the cross rotating blocks to drive the threaded rods 20 to rotate, the threaded rods 20 can be separated from the storage fixing holes 22 after rotating, the cover plates 15 are lifted upwards to drive the telescopic rods 12 to move upwards, and after moving to a certain height, the threaded rods 20 are rotated reversely again to drive the threaded rods 20 to move into the opening fixing holes 21.

According to the utility model, the partition plate 10 is placed in the placing groove 9, the partition plate 10 is arranged in a cross shape, and the partition plate 10 can partition the space in the placing groove 9, so that the interaction equipment can be placed in order.

In the utility model, one end of the threaded rod 20 is fixedly provided with the cross-shaped rotating block, the cross-shaped rotating block is sleeved with the protective sleeve, and the threaded rod 20 can be driven to rotate by rotating the cross-shaped rotating block.

According to the voice interaction equipment, the loudspeaker 5 is arranged on one side of the voice interaction equipment body 1, the mounting groove 6 is formed in the top side of the voice interaction equipment body 1, the operating keyboard 7 is placed in the mounting groove 6, the interactive display screen 2, the camera 3, the loudspeaker 5 and the operating keyboard 7 are arranged on the voice interaction equipment body 1, and therefore better voice interaction of users can be facilitated.

This practical theory of operation:

in the utility model, when voice interaction is carried out with a voice interaction equipment body 1, some interaction equipment needs to be used, a placing box 8 is arranged on one side of the voice interaction equipment body 1, a partition plate 10 is arranged in the placing box 8, the partition plate 10 can partition the space in a placing groove 9, the interaction equipment is convenient to place in order, an interaction display screen 2, a camera 3, a loudspeaker 5 and an operation keyboard 7 are arranged on the voice interaction equipment body 1, better voice interaction can be facilitated for a user, when the user needs to write in the process of using the voice interaction equipment body 1, the user can rotate a cross rotating block to drive a threaded rod 20 to rotate, the threaded rod 20 can be separated from a containing fixed hole 22 after rotating, a cover plate 15 is lifted upwards to drive a telescopic rod 12 to move upwards, and the threaded rod 20 is reversely rotated again after moving to a certain height, can drive threaded rod 20 and remove to opening in the fixed orifices 21, then stimulate hand power ring 18, after rotating half a circle, one side of hand power ring 18 contacts with the top side of pronunciation interactive device body 1, carry out a support to the apron 15 after opening, make apron medial surface 17 on the apron 15 be the level setting, convenient to use personnel place books or notes above, take notes and write, in pronunciation interactive, can also write, the interactive effect of pronunciation has been strengthened, when not, can accomodate, high durability and convenient use.

The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and equivalent alternatives or modifications according to the technical solution of the present invention and the inventive concept thereof should be covered by the scope of the present invention.

Claims

1. The utility model provides a pronunciation interactive installation based on degree of depth study, includes pronunciation interactive equipment body (1), be equipped with interactive display screen (2), camera (3) on pronunciation interactive equipment body (1), the top side of pronunciation interactive equipment body (1) is equipped with controller (4), its characterized in that: one side of the voice interaction equipment body (1) is fixedly provided with a placing box (8), the top side of the placing box (8) is provided with a placing groove (9), the top side of the placing box (8) is provided with two telescopic grooves (11), telescopic rods (12) are movably arranged in the two telescopic grooves (11), the top ends of the two telescopic rods (12) extend out of the telescopic grooves (11) and are respectively rotatably provided with a rotating support rod (14), one side of the two rotating support rods (14) is fixedly provided with a same cover plate (15), the cover plate (15) is matched with the placing box (8), the cover plate (15) is provided with a cover plate outer side surface (16) and a cover plate inner side surface (17), one side of the placing box (8) is provided with a threaded hole (19), the threaded hole (19) is communicated with the two telescopic grooves (11), and a threaded rod (20) is arranged in the threaded hole (19), one end of the threaded rod (20) is movably arranged on the two telescopic rods (12).

2. The deep learning based speech interaction device of claim 1, wherein: the top side of the telescopic rod (12) is provided with a rotating groove (13), and one end of the rotating support rod (14) is rotatably arranged in the rotating groove (13).

3. The deep learning based speech interaction device of claim 1, wherein: a hand pull ring (18) is fixedly mounted on the outer side face (16) of the cover plate on the cover plate (15), and one side of the hand pull ring (18) is in contact with the top side of the voice interaction equipment body (1).

4. The deep learning based speech interaction device of claim 1, wherein: open fixed orifices (21) and accomodate fixed orifices (22) have all been seted up to one side of two telescopic links (12), and threaded rod (20) all with open fixed orifices (21) and accomodate fixed orifices (22) looks adaptation, the one end activity of threaded rod (20) is run through and is opened fixed orifices (21).

5. The deep learning based speech interaction device of claim 1, wherein: the partition board (10) is placed in the placing groove (9), and the partition board (10) is arranged in a cross shape.

6. The deep learning based speech interaction device of claim 1, wherein: one end of the threaded rod (20) is fixedly provided with a cross rotating block, and a protective sleeve is sleeved on the cross rotating block.

7. The deep learning based speech interaction device of claim 1, wherein: one side of voice interaction equipment body (1) is equipped with megaphone (5), and mounting groove (6) have been seted up to the top side of voice interaction equipment body (1), have placed operating keyboard (7) in mounting groove (6).