WO2020228349A1

WO2020228349A1 - Virtual news anchor system based on air imaging and implementation method therefor

Info

Publication number: WO2020228349A1
Application number: PCT/CN2019/129947
Authority: WO
Inventors: 李新福
Original assignee: 广东康云科技有限公司
Priority date: 2019-05-14
Filing date: 2019-12-30
Publication date: 2020-11-19
Also published as: CN110309470A

Abstract

A virtual news anchor system based on air imaging and an implementation method therefor. The system comprises a signal detection device, a control device, a display device and a broadcasting device, wherein the signal detection device is used for detecting an input signal; the control device is used for generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content; the display device is used for receiving the three-dimensional model generated by the control device, and then displaying same in the air by means of air imaging; and the broadcasting device is used for playing the audio signal. A three-dimensional model of a virtual news anchor is displayed by means of air imaging, and the virtual news anchor is displayed in the air in the three-dimensional mode without the help of a display screen, which can preferably simulate the broadcasting effect of the real news anchor, thereby greatly enhancing the usage experience of the virtual news anchor.

Description

A virtual news anchor system based on air imaging and its realization method

Technical field

The invention relates to the technical field of virtual anchors, in particular to a virtual news anchor system based on air imaging and an implementation method thereof.

Background technique

The virtual news anchor is a technology that broadcasts news by simulating the image of a real person through a display screen. In the prior art, the virtual news anchor is displayed through a medium such as a liquid crystal display screen, and the virtual news anchor is limited to the plane where the display screen is located, lacks a three-dimensional effect, and appears rigid and not friendly enough.

Summary of the invention

In order to solve the above technical problems, the purpose of the present invention is to provide a virtual news anchor system based on air imaging and an implementation method thereof.

On the one hand, the embodiment of the present invention includes a virtual news anchor system based on air imaging, including:

A signal detection device for detecting an input signal, the input signal includes at least one of a gesture signal, a somatosensory signal, a brain wave signal, an eye movement signal, a voice signal, a touch signal, and a facial expression signal;

The control device is used to generate a three-dimensional model and search for broadcast content according to the input signal, and then generate an audio signal according to the broadcast content;

The display device is used to receive the three-dimensional model generated by the control device, and then display it in the air through air imaging;

The broadcasting device is used to receive the audio signal generated by the control device, and then play it through audio mode.

Further, a local knowledge base is stored in the control device, and the knowledge contained in the local knowledge base is used to determine the correspondence between the question and the answer; the air imaging-based virtual news anchor system also includes a server, so The server is used to generate new knowledge and update the local knowledge base stored in the control device, so that when the control device receives the input signal, it can analyze the problem contained in the input signal and follow the local knowledge The library, the server, and the Internet retrieve the answer corresponding to the question in order of priority, thereby generating an audio signal based on the answer.

Further, the input signal includes a gesture signal, and the control device includes:

A sign language recognition unit for recognizing sign language information from the gesture signal;

The keyword extraction unit is used to extract keywords from the sign language information;

The news information retrieval unit is used to retrieve and obtain news information according to the keywords;

A broadcast content generating unit, configured to generate broadcast content according to the news message retrieved by the news message retrieval unit;

3D model generating unit, used to generate 3D model;

The audio signal generating unit is configured to generate an audio signal according to the broadcast content.

Further, the input signal includes a facial expression signal, and the control device includes:

The facial expression recognition unit is used to obtain the facial expression and recognize the emotional state corresponding to the facial expression; the emotional state includes seriousness, joy, sadness, and excitement;

The news information retrieval unit is used to retrieve and obtain news information according to the emotional state;

3D model generating unit, used to generate 3D model;

Further, the news message retrieval unit is specifically configured to:

When the emotional state is serious, retrieve and obtain political and economic news;

When the emotional state is joy, retrieve and obtain livelihood news;

When the emotional state is sad, retrieve and obtain entertainment news information;

When the emotional state is excitement, search and obtain humanities news.

On the other hand, the embodiment of the present invention also includes a method for implementing a virtual news anchor based on air imaging, including the following steps:

Detecting an input signal, where the input signal includes at least one of a gesture signal, a somatosensory signal, a brain wave signal, an eye movement signal, a voice signal, a touch signal, and a facial expression signal;

Generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content;

Receive the three-dimensional model generated by the control device, and then display it in the air through air imaging;

Receive the audio signal generated by the control device, and then play it through audio mode.

Further, the method for implementing a virtual news anchor based on air imaging further includes the following steps:

Generate new knowledge and update the local knowledge base; the knowledge is used to determine the correspondence between the question and the answer;

When receiving the input signal, analyze the problem contained in the input signal;

Retrieve the answer corresponding to the question according to the priority order of local knowledge base, server and Internet;

An audio signal is generated based on the answer.

Further, the input signal includes a gesture signal, and the step of generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content specifically includes:

Identifying sign language information from the gesture signal;

Extract keywords from the sign language information;

Search and obtain news information according to the keywords;

Generating broadcast content according to the news information retrieved by the news information retrieval unit;

Generating a three-dimensional model according to the broadcast content;

An audio signal is generated according to the broadcast content.

Further, the input signal includes a facial expression signal, and the step of generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content specifically includes:

Acquiring the facial expression and identifying the emotional state corresponding to the facial expression; the emotional state includes seriousness, joy, sadness, and excitement;

Retrieve and obtain news information according to the emotional state;

Generating a three-dimensional model according to the broadcast content;

An audio signal is generated according to the broadcast content.

Further, the step of retrieving and obtaining news information according to the emotional state specifically includes:

When the emotional state is joy, retrieve and obtain livelihood news;

When the emotional state is excitement, search and obtain humanities news.

The beneficial effect of the present invention is that the virtual news anchor system and its implementation method in the embodiment of the present invention can display the three-dimensional model of the virtual news anchor in the air imaging mode, and the virtual news anchor can be displayed in the air without the help of a display screen. Displayed in three-dimensional medium, can bring a huge visual shock experience, and the mouth shape, eye movements and facial expressions of the virtual news anchor can cooperate with the news message played by the broadcasting device to move, which has a strong sense of reality and can be very good The broadcast effect of the live news anchor is simulated, which greatly enhances the experience of the virtual news anchor.

Description of the drawings

Figure 1 is a structural block diagram of a specific implementation of the virtual news anchor system of the method of the present invention;

2 is a structural block diagram of another specific implementation of the virtual news anchor system of the method of the present invention;

Fig. 3 is a flowchart of a specific implementation manner of a virtual news anchor realization method according to the present invention.

Detailed ways

Example 1

A virtual news anchor system based on air imaging in this embodiment, referring to Figure 1 or Figure 2, includes:

In this embodiment, referring to FIG. 1 or FIG. 2, the signal detection device includes:

Somatosensory sensor, used to obtain the input somatosensory signal;

Gesture sensor, used to obtain the input gesture signal;

Eye tracker, used to obtain the input eye movement signal;

Touch module, used to obtain the input touch signal;

The voice collection module is used to obtain the input voice signal;

Brain wave acquisition device for acquiring input brain wave signals;

The camera is used to obtain the input image signal to recognize the user's facial expression.

The control device in this embodiment is a device with data storage capabilities and processing capabilities. For example, a personal computer can be used as the control device in this embodiment. The control device is connected to the Internet, and can retrieve the resources to be obtained on the Internet.

Users can interact with the virtual news anchor system by making somatosensory actions, making gestures, making eye movements, touching, making voices, making brain waves, and making facial expressions.

The control device is used to generate a three-dimensional model and search for broadcast content according to the input signal, and then generate an audio signal according to the broadcast content. The broadcast content refers to multimedia content capable of delivering current affairs news, such as a news release issued by a news agency. The control device converts the audio signal according to the text information of the broadcast content, and the audio signal can drive the broadcast device to emit sound effects, thereby reading the broadcast content. The control device converts the text information of the broadcast content to obtain a three-dimensional model. The three-dimensional model can be expressed as a male or female human announcer, or as a cartoon character such as a cat, dog, cow, and chicken. The three-dimensional model is Variable, mainly because the mouth shape, eye movements and facial expressions of the 3D model change synchronously with the audio signal, so that the mouth shape, eye movements and facial expressions of the 3D model can match the text corresponding to the sound effect emitted by the audio signal. stand up.

The display device in this embodiment is an air imager. 1 or 2, the display device includes a driving unit and a projection unit. The driving unit is used for receiving the three-dimensional model generated by the control device, and the projection unit is used for projecting the air under the driving of the driving unit to display the three-dimensional model. A corresponding decoding program and a driver program are installed on the driving unit, the decoding program is used to decode the received three-dimensional model generated by the control device, and the driver program drives the projection unit to project the air according to the decoding result Thus, the three-dimensional model is displayed.

The broadcasting device in this embodiment may be a speaker. 1 or 2, the broadcasting device includes a power amplifier unit and a speaker. The power amplifier unit is used for receiving and amplifying the audio signal generated by the control device, and the speaker is used for emitting corresponding sound effects under the driving of the power amplifier unit. The power amplifier unit is equipped with a corresponding decoding circuit, an amplifying circuit and a noise reduction circuit, the decoding circuit is used to decode the received audio signal generated by the control device, and the amplifying circuit amplifies the result of the decoding, The noise reduction circuit is used for reducing noise during the working process of the amplifying circuit.

The virtual news anchor system in this embodiment can display the three-dimensional model of the virtual news anchor through air imaging. The displayed virtual news anchor is three-dimensional, and the virtual news anchor’s mouth shape, eye movements, facial expressions, etc. It can act in conjunction with the news messages played by the broadcasting device, has a strong sense of reality, and can well simulate the broadcasting effect of a live news anchor, thereby greatly enhancing the experience of the virtual news anchor.

Further, a local knowledge base is stored in the control device, and the knowledge contained in the local knowledge base is used to determine the correspondence between various questions and answers, so that the corresponding answers can be found according to the questions. 1 and 2, the air imaging-based virtual news anchor system also includes a server, the server is used to generate new knowledge through AI program training and learning and update the local knowledge base, the local knowledge base is stored in the control In the installation. When the control device receives the input signal, it analyzes the question contained in the input signal through the voice recognition program, and searches for the answer corresponding to the question according to the priority order of the local knowledge base, the server and the Internet, thereby An audio signal is generated based on the answer. In other words, the control device first searches in the local knowledge base, if the answer is retrieved in the local knowledge base, it will generate an audio signal from the answer retrieved in the local knowledge base; if it is not retrieved in the local knowledge base When the answer is reached, it will be retrieved from the knowledge base stored on the server. If the answer is retrieved from the knowledge base stored on the server, an audio signal will be generated from the answer retrieved from the knowledge base stored on the server. Answers are retrieved from the stored knowledge base and connected to search engines such as Baidu for retrieval, so that the virtual news anchor system can retrieve matching answers and realize intelligent answers to questions raised by users.

Further as a preferred embodiment, the input signal includes a voice signal, and the control device includes:

A voice recognition unit for recognizing voice information from the gesture signal;

The keyword extraction unit is used to extract keywords from the voice information;

3D model generating unit, used to generate 3D model;

The voice recognition unit, keyword extraction unit, news information retrieval unit, broadcast content generation unit, three-dimensional model generation unit and audio signal generation unit are software modules with corresponding functions installed in the control device. Wherein, the voice recognition unit has a voice recognition program that can recognize the content contained in the gesture signal. For example, some voice recognition programs can convert the gesture signal into text. The keyword extraction unit may extract keywords from the content of the voice signal. The news information retrieval unit is connected to a news search engine on the Internet, searches using the keywords extracted by the keyword extraction unit, and obtains news information returned by the news search engine. The broadcast content generating unit processes news messages by deleting commercial advertisements and other irrelevant messages, rearranging the sequence, and extracting key paragraphs, etc., so as to generate broadcast content. The three-dimensional model generating unit is a three-dimensional modeling program, which can generate a three-dimensional model representing a male or female human announcer image or a cartoon image of a cat, dog, cow, chicken, etc. The mouth shape of the three-dimensional model is, Eye movements and facial expressions change with the pronunciation of each text when the broadcast content is played in time sequence. The audio signal generating unit is a text-to-speech conversion program that can convert each text to obtain a corresponding audio signal.

Through the voice recognition unit, the keyword extraction unit, the news message retrieval unit, the broadcast content generation unit, the three-dimensional model generation unit and the audio signal generation unit, the control device can recognize the voice signal and retrieve the corresponding news message from the Internet. Users can interact with virtual news anchors by voice to get the news they want.

Further as a preferred embodiment, the input signal includes a gesture signal. Referring to FIG. 1, the control device includes:

3D model generating unit, used to generate 3D model;

The sign language recognition unit, keyword extraction unit, news message retrieval unit, broadcast content generation unit, three-dimensional model generation unit and audio signal generation unit are software modules with corresponding functions installed in the control device. Wherein, the sign language recognition unit has a sign language recognition program that can recognize the content contained in the gesture signal. For example, some sign language recognition programs can convert the gesture signal into text. The keyword extraction unit may extract keywords from the content of the sign language signal. The news information retrieval unit is connected to a news search engine on the Internet, searches using the keywords extracted by the keyword extraction unit, and obtains news information returned by the news search engine. The broadcast content generating unit processes news messages by deleting commercial advertisements and other irrelevant messages, rearranging the sequence, and extracting key paragraphs, etc., to generate broadcast content. The three-dimensional model generating unit is a three-dimensional modeling program, which can generate a three-dimensional model representing a male or female human announcer image or a cartoon image of a cat, dog, cow, chicken, etc. The mouth shape of the three-dimensional model is, Eye movements and facial expressions change with the pronunciation of each text when the broadcast content is played in time sequence. The audio signal generating unit is a text-to-speech conversion program that can convert each text to obtain a corresponding audio signal.

Through the sign language recognition unit, the keyword extraction unit, the news message retrieval unit, the broadcast content generation unit, the three-dimensional model generation unit and the audio signal generation unit, the control device can recognize sign language signals and retrieve corresponding news messages from the Internet. The virtual news anchor system in this embodiment is very friendly to people who have difficulty in pronunciation. They only need to make sign language gestures to the virtual news anchor system, and the virtual news anchor system can recognize the sign language signal and retrieve the corresponding signal from the Internet. With news messages, people who have difficulty in pronunciation can also enjoy the convenience brought by the virtual news anchor system of the present invention.

As a further preferred embodiment, referring to FIG. 2, the input signal includes a facial expression signal, and the control device includes:

3D model generating unit, used to generate 3D model;

The facial expression recognition unit, news information retrieval unit, broadcast content generation unit, three-dimensional model generation unit and audio signal generation unit are software modules with corresponding functions installed in the control device.

Wherein, the facial expression recognition unit has a facial expression recognition program that can recognize the current emotional state of seriousness, joy, sadness, excitement, etc. corresponding to the facial expression of the user. The news message retrieval unit is connected to a news search engine on the Internet, searches for news messages of corresponding classifications according to the emotional state of the user, and obtains news messages returned by the news search engine. The broadcast content generating unit processes news messages by deleting commercial advertisements and other irrelevant messages, rearranging the sequence, and extracting key paragraphs, etc., so as to generate broadcast content. The three-dimensional model generating unit is a three-dimensional modeling program, which can generate a three-dimensional model representing a male or female human announcer image or a cartoon image of a cat, dog, cow, chicken, etc. The mouth shape of the three-dimensional model is, Eye movements and facial expressions change with the pronunciation of each text when the broadcast content is played in time sequence. The audio signal generating unit contains a text-to-speech conversion program, which can convert each text to obtain a corresponding audio signal.

As a further preferred embodiment, the news information retrieval unit is specifically configured to:

When the emotional state is joy, retrieve and obtain livelihood news;

When the emotional state is excitement, search and obtain humanities news.

When the user’s facial expression reflects that the user’s emotional state is serious, it indicates that the user is currently more rational. If you listen to political and economic news, you will get better results; when the user’s facial expression reflects the user When the emotional state of the user is joy, it indicates that the user is currently more emotional. If you listen to the news of people’s livelihood, you will get the effect of loving life more; when the user’s facial expression reflects the emotional state of the user is sad, it indicates that the user Need to receive mental treatment. If you listen to entertainment news, you will get better treatment. The entertainment news includes news related to TV series, movies, celebrities and funny; when the user’s facial expression reflects the use of When the emotional state of the user is excited, it indicates that the user needs to calm down quickly. At this time, the user can watch the humanities news related to history, art and society.

By performing the above settings on the news message retrieval unit, the virtual news anchor system in this embodiment can actively push different types of news messages according to different emotional states of users, thereby providing a better news experience.

Further as a preferred embodiment, referring to FIG. 1 or FIG. 2, the control device further includes:

The artificial intelligence unit is used to use artificial intelligence to train the three-dimensional model generated by the three-dimensional model generating unit.

The artificial intelligence unit trains the three-dimensional model through tools such as convolutional neural networks, which can make the mouth shape, eye movements and facial expressions of the three-dimensional model more natural, and can change different clothes, wear and makeup for the three-dimensional model. Shape, provide a better and more realistic news experience.

Example 2

In this embodiment, a method for implementing a virtual news anchor based on air imaging, referring to FIG. 3, includes the following steps:

S1. Detect an input signal, the input signal includes at least one of a gesture signal, a somatosensory signal, a brain wave signal, an eye movement signal, a voice signal, a touch signal, and a facial expression signal;

S2. Generate a three-dimensional model and search for the broadcast content according to the input signal, and then generate an audio signal according to the broadcast content;

S3. Receive the three-dimensional model generated by the control device, and then display it in the air through air imaging;

S4. Receive the audio signal generated by the control device, and then play it through audio mode.

Further as a preferred embodiment, the method for implementing a virtual news anchor based on air imaging further includes the following steps:

S5. Generate knowledge and update the local knowledge base; the knowledge is used to determine the correspondence between the question and the answer;

S6. When receiving the input signal, analyze the problem contained in the input signal;

S7. Retrieve the answer corresponding to the question according to the priority order of local knowledge base, server and Internet;

S8. Generate an audio signal according to the answer.

The steps S5-S8 can be executed by the server. The server is used to generate new knowledge and update the local knowledge base through the training and learning of the AI program, and the local knowledge base is stored in the control device. When the control device receives the input signal, it analyzes the question contained in the input signal through the voice recognition program, and searches for the answer corresponding to the question according to the priority order of the local knowledge base, the server and the Internet, thereby An audio signal is generated based on the answer. In other words, the control device first searches in the local knowledge base, if the answer is retrieved in the local knowledge base, it will generate an audio signal from the answer retrieved in the local knowledge base; if it is not retrieved in the local knowledge base When the answer is reached, it will be retrieved from the knowledge base stored on the server. If the answer is retrieved from the knowledge base stored on the server, an audio signal will be generated from the answer retrieved from the knowledge base stored on the server. Answers are retrieved from the stored knowledge base and connected to search engines such as Baidu for retrieval, so that the virtual news anchor system can retrieve matching answers and realize intelligent answers to questions raised by users.

Further as a preferred embodiment, the input signal includes a gesture signal, the step of generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content, namely step S2, specifically includes:

S201A. Recognizing sign language information from the gesture signal;

S202A. Extract keywords from the sign language information;

S203A. Search and obtain news information according to the keywords;

S204A. Generate broadcast content based on the news information retrieved by the news information retrieval unit;

S205A. Generate a three-dimensional model according to the broadcast content;

S206A. Generate an audio signal according to the broadcast content.

Further as a preferred embodiment, the input signal includes a facial expression signal, and the step of generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content, namely step S2, specifically includes :

S201B. Obtain the facial expression and identify the emotional state corresponding to the facial expression; the emotional state includes seriousness, joy, sadness, and excitement;

S202B. Retrieve and obtain news information according to the emotional state;

S203B. Generate broadcast content according to the news information retrieved by the news information retrieval unit;

S204B. Generate a three-dimensional model according to the broadcast content;

S205B. Generate an audio signal according to the broadcast content.

As a further preferred embodiment, the step of retrieving and obtaining news information according to the emotional state, namely step S202B, specifically includes:

S20201. When the emotional state is serious, retrieve and obtain political and economic news;

S20202. When the emotional state is joy, retrieve and obtain livelihood news;

S20203. When the emotional state is sad, retrieve and obtain entertainment news;

S20204. When the emotional state is excitement, retrieve and obtain humanities news.

Further as a preferred embodiment, the step of generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content, namely step S2, specifically further includes:

S207. Use artificial intelligence to train the three-dimensional model generated by the three-dimensional model generating unit.

The steps in this embodiment can be implemented using the corresponding devices or units in Embodiment 1, and the same beneficial effects as in Embodiment 1 can be achieved. Since each device or unit in Embodiment 1 uses the steps in this embodiment to implement corresponding functions, each step in this embodiment has been described in detail in Embodiment 1, and will not be repeated in this embodiment. .

It should be realized that the embodiments of the present invention can be realized or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method can be implemented in a computer program using standard programming techniques-including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured allows the computer to operate in a specific and predefined manner-according to the specific The methods and drawings described in the examples. Each program can be implemented in a high-level process or object-oriented programming language to communicate with the computer system. However, if necessary, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

In addition, the operations of the processes described herein may be performed in any suitable order, unless otherwise indicated herein or otherwise clearly contradictory to the context. The processes (or variants and/or combinations thereof) described herein can be executed under the control of one or more computer systems configured with executable instructions, and can be used as code (for example, , Executable instructions, one or more computer programs, or one or more applications), implemented by hardware or a combination thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computing platform, including but not limited to a personal computer, a mini computer, a main frame, a workstation, a network or a distributed computing environment, a separate or integrated computer Platform, or communication with charged particle tools or other imaging devices, etc. Aspects of the present invention can be implemented by machine-readable codes stored on non-transitory storage media or devices, whether removable or integrated into a computing platform, such as hard disks, optical reading and/or writing storage media, RAM, ROM, etc., so that they can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. In addition, the machine-readable code, or part thereof, can be transmitted through a wired or wireless network. When such a medium includes instructions or programs that implement the steps described above in combination with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programming according to the methods and techniques of the present invention, the present invention also includes the computer itself.

A computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data that is stored in non-volatile memory. The output information can also be applied to one or more output devices such as displays. In a preferred embodiment of the present invention, the converted data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

The above is a detailed description of the preferred implementation of the present invention, but the invention is not limited to the described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. These equivalent modifications or replacements are all included in the scope defined by the claims of this application.

Claims

A virtual news anchor system based on air imaging, characterized in that it comprises:

A signal detection device for detecting an input signal, the input signal includes at least one of a gesture signal, a somatosensory signal, a brain wave signal, an eye movement signal, a voice signal, a touch signal, and a facial expression signal;

The control device is used to generate a three-dimensional model and search for broadcast content according to the input signal, and then generate an audio signal according to the broadcast content;

The display device is used to receive the three-dimensional model generated by the control device, and then display it in the air through air imaging;

The broadcasting device is used to receive the audio signal generated by the control device, and then play it through audio mode.
The virtual news anchor system based on air imaging according to claim 1, wherein a local knowledge base is stored in the control device, and the knowledge contained in the local knowledge base is used to determine the relationship between the question and the answer. The corresponding relationship; the air imaging-based virtual news anchor system also includes a server, the server is used to generate new knowledge and update the local knowledge base stored in the control device, so that the control device receives input Analyze the question contained in the input signal, and retrieve the answer corresponding to the question according to the priority order of the local knowledge base, the server and the Internet, so as to generate an audio signal according to the answer.
A virtual news anchor system based on air imaging according to claim 1, wherein the input signal comprises a gesture signal, and the control device comprises:

A sign language recognition unit for recognizing sign language information from the gesture signal;

The keyword extraction unit is used to extract keywords from the sign language information;

The news information retrieval unit is used to retrieve and obtain news information according to the keywords;

A broadcast content generating unit, configured to generate broadcast content according to the news message retrieved by the news message retrieval unit;

3D model generating unit, used to generate 3D model;

The audio signal generating unit is configured to generate an audio signal according to the broadcast content.
A virtual news anchor system based on air imaging according to claim 1, wherein the input signal comprises a facial expression signal, and the control device comprises:

The facial expression recognition unit is used to obtain the facial expression and recognize the emotional state corresponding to the facial expression; the emotional state includes seriousness, joy, sadness, and excitement;

The news information retrieval unit is used to retrieve and obtain news information according to the emotional state;

A broadcast content generating unit, configured to generate broadcast content according to the news message retrieved by the news message retrieval unit;

3D model generating unit, used to generate 3D model;

The audio signal generating unit is configured to generate an audio signal according to the broadcast content.
The virtual news anchor system based on air imaging according to claim 4, wherein the news information retrieval unit is specifically configured to:

When the emotional state is serious, retrieve and obtain political and economic news;

When the emotional state is joy, retrieve and obtain livelihood news;

When the emotional state is sad, retrieve and obtain entertainment news information;

When the emotional state is excitement, search and obtain humanities news.
A method for realizing a virtual news anchor based on air imaging is characterized in that it comprises the following steps:

Detecting an input signal, where the input signal includes at least one of a gesture signal, a somatosensory signal, a brain wave signal, an eye movement signal, a voice signal, a touch signal, and a facial expression signal;

Generating a three-dimensional model and searching for broadcast content according to the input signal, and then generating an audio signal according to the broadcast content;

Receive the three-dimensional model generated by the control device, and then display it in the air through air imaging;

Receive the audio signal generated by the control device, and then play it through audio mode.
The method for realizing a virtual news anchor based on air imaging according to claim 6, characterized in that it further comprises the following steps:

Generate new knowledge and update the local knowledge base; the knowledge is used to determine the correspondence between the question and the answer;

When receiving the input signal, analyze the problem contained in the input signal;

Retrieve the answer corresponding to the question according to the priority order of local knowledge base, server and Internet;

An audio signal is generated based on the answer.
The method for realizing a virtual news anchor based on air imaging according to claim 6, wherein the input signal includes a gesture signal, and the three-dimensional model is generated and the broadcast content is searched according to the input signal, and then according to the The step of generating audio signal from broadcast content specifically includes:

Identifying sign language information from the gesture signal;

Extract keywords from the sign language information;

Search and obtain news information according to the keywords;

Generating broadcast content according to the news information retrieved by the news information retrieval unit;

Generating a three-dimensional model according to the broadcast content;

An audio signal is generated according to the broadcast content.
The method for realizing a virtual news anchor based on air imaging according to claim 6, wherein the input signal includes a facial expression signal, the three-dimensional model is generated and the broadcast content is searched according to the input signal, and then the broadcast content is searched according to the input signal. The step of generating audio signals from the broadcast content specifically includes:

Acquiring the facial expression and identifying the emotional state corresponding to the facial expression; the emotional state includes seriousness, joy, sadness, and excitement;

Retrieve and obtain news information according to the emotional state;

Generating broadcast content according to the news information retrieved by the news information retrieval unit;

Generating a three-dimensional model according to the broadcast content;

An audio signal is generated according to the broadcast content.
The method for realizing a virtual news anchor based on air imaging according to claim 9, wherein the step of retrieving and obtaining news information according to the emotional state specifically comprises:

When the emotional state is serious, retrieve and obtain political and economic news;

When the emotional state is joy, retrieve and obtain livelihood news;

When the emotional state is sad, retrieve and obtain entertainment news information;

When the emotional state is excitement, search and obtain humanities news.