AI intelligent dialogue device based on virtual digital human

Abstract

The AI intelligent dialogue device based on the virtual digital human comprises a machine body, an adjusting assembly, a dismounting assembly and a moving assembly, the adjusting assembly is arranged at the top end of the machine body, the dismounting assembly is arranged in the middle of the machine body, and the moving assembly is arranged at the bottom end of the machine body. The machine body comprises a cabinet body, a display screen, a protective layer, an infrared induction head, a loudspeaker and an induction piece, and the display screen is arranged in the middle of the cabinet body. According to the AI intelligent dialogue device based on the virtual digital human, a virtual digital human interface is displayed through the display screen, the machine head is connected with the cabinet body through the rotating shaft, so that the machine head can be adjusted in a self-adaptive mode, the binocular camera is arranged on the end face of the machine head, a human face is captured for recognition, and sufficient illumination conditions are provided in cooperation with the side light supplementing lamps; and the dustproof plates are arranged on the sides of the microphone and the loudspeaker, so that the integrity of the internal structure is ensured, a certain dustproof effect is achieved, and AI intelligent dialogue of the virtual digital human is facilitated.

Description

Technical Field

[0001] The utility model relates to the technical field of virtual digital dialogue, in particular to an AI intelligent dialogue device based on virtual digital humans. Background Art

[0002] A virtual digital human is a digital character image close to a human image created using digital technology, that is, a virtual character. Currently, AI-synthesized virtual character videos are a new field of application of artificial intelligence technology, which has realized customized virtual characters. With the rapid development of science and technology, the functions of smart devices have gradually improved. Existing dialogue devices have language learning and dialogue functions. After connecting to the network, virtual digital humans can conduct virtual dialogues with users. They can be used in conjunction with existing smart learning equipment, household appliances, etc. to provide convenience for people's lives. The functions of smart dialogue devices on the market are relatively complete and basically meet people's daily needs, but there are still certain problems.

[0003] The existing AI intelligent dialogue device based on virtual digital humans has low facial recognition accuracy during use. The outer surface is easily damaged by wind and sand friction and scratches after long-term use, which may cause the risk of breakage in the future and is prone to noise pollution problems. Therefore, we propose an AI intelligent dialogue device based on virtual digital humans. Utility Model Content

[0004] The purpose of the present invention is to provide an AI intelligent dialogue device based on a virtual digital human to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: an AI intelligent dialogue device based on a virtual digital human, comprising a body, an adjustment component, a disassembly component and a moving component, wherein the top of the body is provided with an adjustment component, the middle of the body is provided with a disassembly component, and the bottom of the body is provided with a moving component, the body comprises a cabinet, a display screen, a protective layer, an infrared sensor head, a speaker and a sensing element, and the middle of the cabinet is provided with a display screen, a protective layer is provided on the side of the display screen, the top of the display screen is provided with an infrared sensor head, the bottom of the display screen is provided with a speaker, and the bottom of the speaker is provided with a sensing element.

[0006] Furthermore, the display screen is fitted with the protective layer, and the sensing elements are symmetrically arranged along the cabinet.

[0007] Furthermore, the adjustment component includes a rotating shaft, a machine head, a binocular camera and a fill light, and the machine head is provided at the top of the rotating shaft, the binocular camera is provided in the middle of the machine head, and the fill light is provided on the side of the binocular camera.

[0008] Furthermore, the rotating shaft is connected to the head, and the head and the binocular camera are integrated.

[0009] Furthermore, the disassembly and assembly components include a dustproof plate, an elastic buckle and a rubber pad, and elastic buckles are provided at both ends of the dustproof plate, and rubber pads are provided on the sides of the dustproof plate.

[0010] Furthermore, the elastic buckles are symmetrically arranged along the dustproof plate, and the dustproof plate and the rubber pad are in contact with each other.

[0011] Furthermore, the moving component includes a base, rollers and a bottom plate, and rollers are provided on both sides of the bottom end of the base, and the bottom plate is provided in the middle of the bottom end of the base.

[0012] Compared with the existing technology, the beneficial effects of the present invention are: the virtual digital human interface is displayed through the display screen, the head is connected to the cabinet through a rotating shaft, so that the head can be adaptively adjusted, and the end face of the head is provided with a binocular camera to capture the human face for recognition, and the side fill light provides sufficient lighting conditions to make facial recognition more accurate, and dustproof plates are provided on the sides of the microphone and the speaker to ensure the integrity of the internal structure and have a certain dust-proof effect, which facilitates the AI ​​intelligent dialogue of the virtual digital person.

[0013] The machine head is connected to the cabinet through a rotating shaft, so that the machine head can be adjusted adaptively. A binocular camera is set on the end face of the machine head. The binocular camera consists of a visible light camera and an infrared camera. One camera collects visible light photos, while the other camera collects near-light photos. It captures human faces for recognition and accurately identifies and locates some key feature points such as eyes, ears, and nose. The side fill lights provide sufficient lighting conditions to make facial recognition more accurate, and the information is entered and displayed on the display screen to facilitate AI intelligent dialogue of virtual digital people.

[0014] The speaker is set below the display screen, and a dustproof plate is installed on the surface of the speaker. Elastic buckles are set on the left and right sides of the dustproof plate, and a rubber pad is set on the inner wall of the dustproof plate, which can protect the speaker from collision with external objects, ensure the integrity of the internal structure of the speaker, and have a certain dustproof effect, thereby extending the service life of the speaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the three-dimensional structure of the utility model;

[0016] Figure 2 This is a side view structural diagram of the mobile assembly of the utility model;

[0017] Figure 3 This is a rear view structural diagram of the disassembly and assembly components of the utility model.

[0018] In the figure: 1. Machine body; 101. Cabinet; 102. Display screen; 103. Protective layer; 104. Infrared sensor head; 105. Speaker; 106. Sensor; 2. Adjustment component; 201. Rotating shaft; 202. Machine head; 203. Binocular camera; 204. Fill light; 3. Disassembly and assembly components; 301. Dustproof plate; 302. Elastic buckle; 303. Rubber pad; 4. Moving component; 401. Base; 402. Roller; 403. Bottom plate. DETAILED DESCRIPTION

[0019] like Figure 1-2As shown, an AI intelligent dialogue device based on a virtual digital human includes a body 1, an adjustment component 2, a disassembly component 3 and a moving component 4. The adjustment component 2 is provided at the top of the body 1, the disassembly component 3 is provided in the middle of the body 1, and the moving component 4 is provided at the bottom of the body 1. The body 1 includes a cabinet 101, a display screen 102, a protective layer 103, an infrared sensor head 104, a speaker 105 and a sensing element 106. The display screen 102 is provided in the middle of the cabinet 101, the protective layer 103 is provided on the side of the display screen 102, the infrared sensor head 104 is provided at the top of the display screen 102, the speaker 105 is provided at the bottom of the display screen 102, and the sensing element is provided at the bottom of the speaker 105. 106, the display screen 102 and the protective layer 103 are fitted together, and the sensing element 106 is symmetrically arranged along the cabinet 101. The display screen 102 is arranged in the middle of the cabinet 101, and the virtual digital human interface is displayed on the display screen 102. The side of the display screen 102 is provided with a protective layer 103, which is a protective film. The outer surface is fitted with protection to improve wear resistance and prevent foreign objects from directly contacting the display screen 102 to cause scratches or damage, which affects the service life of the display screen 102. The AI ​​intelligent dialogue device is movable and moves through the bottom roller 402. It cooperates with the telescopic bottom plate 403 to tighten and limit the support firmly. The end face of the cabinet 101 is provided with an infrared sensor head 104 and a bottom The sensing element 106 assists in manipulating the bottom drive to move within the specified area and avoid obstacles, and the surrounding area is made of flexible rubber material, which can reduce the collision damage of the cabinet 101 during movement and improve protection. The adjustment component 2 includes a rotating shaft 201, a head 202, a binocular camera 203 and a fill light 204. The head 202 is set at the top of the rotating shaft 201, the binocular camera 203 is set in the middle of the head 202, and the fill light 204 is set on the side of the binocular camera 203. The rotating shaft 201 is connected to the head 202, and the head 202 and the binocular camera 203 are integrated. The head 202 is connected to the cabinet 101 through the rotating shaft 201, so that the head 202 can be adjusted adaptively. A binocular camera 203 is provided on the end face of the nose 202, and the binocular camera 203 consists of a visible light camera and an infrared camera. One camera collects visible light photos, and the other camera collects near-light photos, captures human faces for recognition, and accurately identifies and locates some key feature points such as eyes, ears, and nose. The side fill light 204 provides sufficient lighting conditions to make facial recognition more accurate, and its information is entered and displayed on the display screen 102 to facilitate AI intelligent dialogue of virtual digital people. The mobile component 4 includes a base 401, rollers 402 and a bottom plate 403, and rollers 402 are provided on both sides of the bottom end of the base 401, and a bottom plate 403 is provided in the middle of the bottom end of the base 401.

[0020] like Figure 3As shown, an AI intelligent dialogue device based on a virtual digital human, the disassembly and assembly component 3 includes a dustproof plate 301, an elastic buckle 302 and a rubber pad 303, and elastic buckles 302 are provided at both ends of the dustproof plate 301, and rubber pads 303 are provided on the sides of the dustproof plate 301. The elastic buckles 302 are symmetrically arranged along the dustproof plate 301, and the dustproof plate 301 and the rubber pad 303 are in contact with each other. The speaker 105 is arranged below the display screen 102, and the dustproof plate 301 is installed on the surface of the speaker 105, and elastic buckles 302 are provided on the left and right sides of the dustproof plate 301, and the inner wall of the dustproof plate 301 is provided with a rubber pad 303, which can protect the speaker 105 from collision with external objects, ensure the integrity of the internal structure of the speaker 105, and have a certain dustproof effect, so that the service life of the speaker 105 is extended.

[0021] Working principle: First, the display screen 102 is set in the middle of the cabinet 101, and the virtual digital human interface is displayed on the display screen 102. A protective layer 103 is set on the side of the display screen 102 to fit and protect the outer layer. The AI ​​intelligent dialogue device is movable and moves through the bottom roller 402, and cooperates with the retractable bottom plate 403 to tighten and limit the support.

[0022] The head 202 is then connected to the cabinet 101 via a rotating shaft 201, allowing the head 202 to be adaptively adjusted. A binocular camera 203 is provided on the end face of the head 202 to capture the face for recognition, accurately identifying and locating key feature points such as the eyes, ears, and nose. The side fill light 204 provides sufficient lighting conditions to make facial recognition more accurate.

[0023] The microphones are arranged on both sides of the top of the display screen 102, while the speakers 105 are arranged below the display screen 102. Dustproof plates 301 are installed on the surfaces of both to protect the microphones and speakers 105 from collisions with external objects, ensure the integrity of the internal structure, and have a certain dustproof effect.

[0024] Finally, the end face of the cabinet 101 is provided with an infrared sensor head 104 and a bottom sensor 106 to assist in controlling the bottom drive to move within the specified area and avoid obstacles. The surrounding area is made of flexible rubber material, which can reduce collision damage to the cabinet 101 during movement.

[0025] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An AI intelligent dialogue device based on a virtual digital human, comprising a body (1), an adjustment component (2), a disassembly component (3) and a moving component (4), wherein the top of the body (1) is provided with the adjustment component (2), the middle of the body (1) is provided with the disassembly component (3), and the bottom of the body (1) is provided with the moving component (4), the body (1) comprises a cabinet (101), a display screen (102), a protective layer (103), an infrared sensor head (104), a speaker (105) and a sensing element (106), wherein the middle of the cabinet (101) is provided with the display screen (102), the side of the display screen (102) is provided with the protective layer (103), the top of the display screen (102) is provided with the infrared sensor head (104), the bottom of the display screen (102) is provided with the speaker (105), and the bottom of the speaker (105) is provided with the sensing element (106).

2. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 1, characterized in that: The display screen (102) and the protective layer (103) are in contact with each other, and the sensing elements (106) are symmetrically arranged along the cabinet (101).

3. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 1, characterized in that: The adjustment component (2) comprises a rotating shaft (201), a machine head (202), a binocular camera (203) and a fill light (204), wherein the machine head (202) is provided at the top of the rotating shaft (201), the binocular camera (203) is provided in the middle of the machine head (202), and the fill light (204) is provided on the side of the binocular camera (203).

4. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 3, characterized in that: The rotating shaft (201) is connected to the machine head (202), and the machine head (202) and the binocular camera (203) are integrated.

5. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 1, characterized in that: The disassembly assembly (3) comprises a dustproof plate (301), an elastic buckle (302) and a rubber pad (303), wherein the two ends of the dustproof plate (301) are provided with the elastic buckle (302), and the side of the dustproof plate (301) is provided with the rubber pad (303).

6. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 5, characterized in that: The elastic buckles (302) are symmetrically arranged along the dustproof plate (301), and the dustproof plate (301) and the rubber pad (303) are in contact with each other.

7. The AI ​​intelligent dialogue device based on a virtual digital human according to claim 1, characterized in that: The moving assembly (4) comprises a base (401), rollers (402) and a bottom plate (403), wherein rollers (402) are provided on both sides of the bottom end of the base (401), and the bottom plate (403) is provided in the middle of the bottom end of the base (401).

Images