Video call method based on satellite system and related equipment

Abstract

The invention provides a video call method based on a satellite system and related equipment, and relates to the technical field of wireless communication. The method comprises the following steps: a sending end obtains a call video of a first user, carries out information separation on the call video to obtain audio data and an image frame of a first frequency, and sends the audio data and the image frame of the first frequency to a satellite; the satellite processes the audio data and the image frame of the first frequency to obtain target data and issues the target data to a receiving end; the receiving end obtains a target call video according to the target data, and outputs the target call video to the second user; wherein the satellite or the receiving end is configured with an artificial intelligence model, and the artificial intelligence model takes the audio data and the image frame of the first frequency as input and takes the call video as output to generate a target call video matched with the call video. The problem that a satellite communication channel is narrow is effectively solved, and the satellite communication efficiency and safety are improved.

Description

Background Art

[0002] With the development of sixth-generation mobile communication technology (6G) services and users in the future, the spectrum resources of terrestrial communication networks will not be able to meet business needs. In the future, satellite networks and terrestrial communication networks will work together. Therefore, base stations can use satellite spectrum resources to improve the business rate and network capacity in hot spots.

[0003] However, although satellite communications have shown huge market potential and broad application prospects, the channel capacity and bandwidth of satellite communications are relatively limited, which leads to its limitations in large-scale data transmission and high network requirements. Especially under high data traffic demands, it is difficult to meet users' expectations for instant and efficient communication.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a video call method based on a satellite system and related equipment, which at least to a certain extent overcomes the problem of narrow channels in existing satellite communications.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a video call method based on a satellite system is provided, including: a transmitting end obtains a call video of a first user, separates information from the call video to obtain audio data and image frames of a first frequency, and sends the audio data and the image frames of the first frequency to a satellite; the satellite processes the audio data and the image frames of the first frequency to obtain target data and sends it to a receiving end; the receiving end obtains a target call video according to the target data, and outputs the target call video to a second user; wherein the satellite or the receiving end is configured with an artificial intelligence model, which takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video.

[0008] In one embodiment of the present disclosure, the method further includes: if the receiving end has the model deployment capability, the transmitting end configures the artificial intelligence model on the receiving end; if the receiving end does not have the model deployment capability, the transmitting end configures the artificial intelligence model on the satellite.

[0009] In one embodiment of the present disclosure, when the artificial intelligence model is configured on the satellite, the target data is the target call video; wherein, the satellite processes the audio data and the image frames of the first frequency to obtain the target data and sends it to the receiving end, including: the satellite inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video, and sends the target call video to the receiving end via the downlink of the satellite.

[0010] In one embodiment of the present disclosure, when the artificial intelligence model is configured at the receiving end, the target data is the audio data and the image frames of the first frequency; wherein the satellite processes the audio data and the image frames of the first frequency to obtain the target data and sends it to the receiving end, including: the satellite forwards the audio data and the image frames of the first frequency to the receiving end via the satellite's downlink; the receiving end obtains the target call video according to the target data, including: the receiving end inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video.

[0011] In one embodiment of the present disclosure, the method also includes: the sending end trains the artificial intelligence model in the following manner: obtaining historical call videos of historical users, and performing information separation on the historical call videos to obtain historical audio data and image frames with a preset frame rate; performing three-dimensional modeling on the image of the historical user to obtain a virtual image model of the historical user; using the historical audio data, image frames with a preset frame rate and the virtual image model of the historical user as input and the action expressions of the historical user in the historical call videos as output, training the artificial intelligence model to be trained to obtain an initial artificial intelligence model; adjusting the frame rate of the image frames, retraining the initial artificial intelligence model, and obtaining the trained artificial intelligence model.

[0012] In one embodiment of the present disclosure, the method also includes: the transmitting end receives a frequency adjustment instruction sent by the receiving end, and adjusts the frame rate of the image frame according to a second frequency in the frequency adjustment instruction, wherein the second frequency represents the adjusted frame rate, and the second frequency is not equal to the first frequency.

[0013] In one embodiment of the present disclosure, the method also includes: the receiving end obtains the second user's attention level value for the video call and / or the service level selected by the second user; the receiving end determines the second frequency based on the second user's attention level value for the video call and / or the service level selected by the second user.

[0014] According to another aspect of the present disclosure, a video call system based on a satellite system is provided, the system comprising a transmitting end, a satellite and a receiving end, wherein: the transmitting end is used to obtain a call video of a first user, perform information separation on the call video, obtain audio data and image frames of a first frequency, and send the audio data and the image frames of the first frequency to the satellite; the satellite is used to process the audio data and the image frames of the first frequency to obtain target data and send it to the receiving end; the receiving end is used to obtain a target call video according to the target data, and output the target call video to a second user; wherein the satellite or the receiving end is configured with an artificial intelligence model, the artificial intelligence model is used to generate the target call video with the audio data and the image frames of the first frequency as input and the call video as output.

[0015] According to another aspect of the present disclosure, an electronic device is provided, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned satellite system-based video call method by executing the executable instructions.

[0016] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the satellite system-based video calling method is implemented.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program or a computer instruction, wherein the computer program or the computer instruction is loaded and executed by a processor so as to enable a computer to implement any of the above-mentioned video call methods based on a satellite system.

[0018] In the implementation manner of the present disclosure, the transmitting end obtains the call video of the first user, separates the information of the call video, obtains audio data and image frames of the first frequency, and sends the audio data and image frames of the first frequency to the satellite; the satellite processes the audio data and the image frames of the first frequency to obtain the target data and sends it to the receiving end; the receiving end obtains the target call video according to the target data, and outputs the target call video to the second user; the satellite or the receiving end is configured with an artificial intelligence model, and the artificial intelligence model uses the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video. On the one hand, the transmitting end of the present disclosure compresses the call video to the voice level through information separation, and the artificial intelligence model, as a semantic communication, can automatically filter redundant information and generate the target call video through intelligent analysis and generation technology, effectively solving the problem of narrow satellite communication channels and improving the efficiency and security of satellite communications. On the other hand, configuring the artificial intelligence model on the satellite or the receiving end can achieve compatibility with the receiving end, increasing the compatibility of satellite system video calls.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0021] Figure 1 A schematic diagram showing a system architecture provided by an embodiment of the present disclosure;

[0022] Figure 2 A flow chart of a video calling method based on a satellite system provided by an embodiment of the present disclosure is shown;

[0023] Figure 3 A flowchart of another video calling method based on a satellite system provided by an embodiment of the present disclosure is shown;

[0024] Figure 4 A flowchart of another video calling method based on a satellite system provided by an embodiment of the present disclosure is shown;

[0025] Figure 5 A flow chart of another video calling method based on a satellite system provided by an embodiment of the present disclosure is shown;

[0026] Figure 6A flow chart of another video calling method based on a satellite system provided by an embodiment of the present disclosure is shown;

[0027] Figure 7 A flowchart showing an example of a video calling method based on a satellite system provided by an embodiment of the present disclosure;

[0028] Figure 8 A schematic diagram showing a video call system based on a satellite system provided by an embodiment of the present disclosure;

[0029] Fig. 9 A schematic diagram showing the structure of a receiving end provided by an embodiment of the present disclosure is shown;

[0030] Fig.10 A structural block diagram of an electronic device provided by an embodiment of the present disclosure is shown;

[0031] Fig.11 A schematic diagram of a computer-readable storage medium provided in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0033] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0034] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.

[0035] Figure 1 A schematic diagram showing an exemplary system architecture of a satellite system-based video calling method that can be applied to an embodiment of the present disclosure is shown.

[0036] like Figure 1As shown, the system architecture 100 may include a terminal device 150, a ground base station 110, a core network 120, a ground gateway 130 and a satellite 140, wherein the core network 120 is used to establish a network connection between the ground base station and the ground gateway 130, and the network may be a wired network or a wireless network.

[0037] Optionally, the wireless network or wired network described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0038] The communication system may adopt different communication technologies, such as Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency-division Multiple Access (OFDMA), Single Carrier FDMA (SC-FDMA), and Carrier Sense Multiple Access with Collision Avoidance. According to the capacity, rate, delay and other factors of different networks, the network can be divided into 2G (generation) network, 3G network, 4G network or future evolution network, such as 5G network, which is referred to as network or system for short. In the present disclosure, the network includes network equipment, which may be, for example, a wireless access network node; the core network includes core network equipment. Among them, the wireless access network node may also be a ground base station 110.

[0039] The ground base station 110 can communicate with the core network device via wire and provide communication services to the terminal device 150. The core network device is, for example, a device in the core network of the 5G network. The core network 120 provides an interface to the data network as a bearer network, provides communication connection, authentication, management, policy control and data service bearing for the terminal device 150. The core network device may include: Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Policy Control Function (PCF), User Plane Function (UPF) and other network elements.

[0040] The terminal device 150, which can be called user equipment, mobile terminal, terminal, mobile station, etc., is a device that provides voice and / or digital connectivity to users. The terminal device 150 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.

[0041] Optionally, the client of the application installed in different terminal devices 150 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0042] Non-terrestrial communication networks such as video calls based on satellite systems have significant advantages such as global coverage, long-distance transmission, flexible networking, convenient deployment, and no geographical restrictions. They can provide services for both fixed terminals and various mobile terminals. Non-terrestrial communication networks are introduced into terrestrial networks to provide seamless coverage for terminal devices 150 by deploying base stations or part of base station functions on high-altitude platforms or satellites.

[0043] The ground gateway 130 is used to forward signaling and service data between the satellite base station and the core network 120. The ground gateway 130 can communicate with the core network equipment by wire; the ground gateway 130 can communicate with the satellite 140 by wireless.

[0044] The video call method based on a satellite system provided by the embodiment of the present disclosure can be applied to scenarios of video calls between other ground communication systems and satellite systems. In the video call scenario, the terminal device used by the first user and the terminal device used by the second user can access the network through the corresponding ground base station 110 and connect to the core network 120 through a wireless link, or the terminal device accesses the network through the 5G new air interface technology, and the satellite serves as a 5G base station and is connected to the ground core network 120 through a wireless link, thereby realizing a scenario of video calls between the ground communication system and the satellite system.

[0045] In the video call scenario, the terminal device used by the first user collects the call video of the first user and sends it to the satellite 140 via an uplink. The satellite 140 sends the call video to the terminal device used by the second user via a downlink.

[0046] In recent years, the satellite communication industry has developed rapidly and is widely used in military communications, aerospace, marine exploration, oil extraction, weather forecasting and even in emerging fields such as the Internet of Things, telemedicine, and intelligent transportation in the civilian market. Globally, the construction of ground-orbit satellite networks has become a consensus, and the era of satellite Internet as a new infrastructure for information infrastructure has arrived.

[0047] Although satellite communications have shown huge market potential and broad application prospects, they still face many challenges in their development, with narrow channels being a particularly prominent problem.

[0048] The channel capacity and bandwidth of satellite communications are relatively limited, which limits the performance of satellite communications in large-scale data transmission and high-speed network requirements. Especially in scenarios with high data traffic requirements, such as high-definition video transmission and large file sharing, the communication technologies in related technologies are difficult to meet users' expectations for instant and efficient communication.

[0049] In addition, satellite communication frequency band resources are also becoming increasingly advanced. Low-frequency band resources are close to saturation, while high-frequency band resources are still in their infancy and require more R&D investment and technological innovation to achieve breakthroughs.

[0050] Therefore, solving the problem of narrow satellite communication channels has become the key to promoting the further development of satellite communications.

[0051] In order to solve at least some of the above technical problems, the present disclosure provides a video call method based on a satellite system, wherein the sending end obtains the call video of the first user, separates the information of the call video, obtains audio data and image frames of the first frequency, and sends the audio data and image frames of the first frequency to the satellite; the satellite processes the audio data and the image frames of the first frequency to obtain the target data and sends it to the receiving end; the receiving end obtains the target call video according to the target data and outputs the target call video to the second user; the satellite or the receiving end is configured with an artificial intelligence model, which takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video. On the one hand, the sending end of the present disclosure compresses the call video to the voice level through information separation, and the artificial intelligence model, as a semantic communication, can automatically filter redundant information and generate the target call video through intelligent parsing and generation technology, effectively solving the problem of narrow satellite communication channels and improving the efficiency and security of satellite communications. On the other hand, configuring the artificial intelligence model on the satellite or the receiving end can achieve compatibility with the receiving end, thereby increasing the compatibility of satellite system video calls.

[0052] The present exemplary implementation is described in detail below with reference to the accompanying drawings and embodiments.

[0053] First, the embodiment of the present disclosure provides a video call method based on a satellite system, which can be executed by any electronic device with computing and processing capabilities. For example, the method can be executed by a transmitting end, such as a terminal device used by a first user; it can also be executed by a satellite, or it can also be executed by a receiving end, such as a terminal device used by a second user.

[0054] Figure 2FIG. 2 shows a flow chart of a video call method based on a satellite system provided by an embodiment of the present disclosure. Figure 2 As shown, the video call method based on the satellite system provided in the embodiment of the present disclosure mainly includes the following steps:

[0055] S202: The transmitting end obtains the call video of the first user, separates the information of the call video to obtain audio data and image frames of the first frequency, and sends the audio data and the image frames of the first frequency to the satellite.

[0056] In one embodiment, the sender refers to the sender of the call video, and the first user refers to the user of the terminal device using the sender, that is, the party of the video call. During the video call, the sender can collect the call video of the first user through the built-in camera of the terminal device.

[0057] It should be noted that the call video includes audio data, which includes the sound emitted by the first user, background sound and noise in the environment where the first user is located, etc. The call video also includes image frames containing the first user and the environment where the first user is located.

[0058] The call video of the first user is a technology that captures, records, processes, stores, transmits and reproduces a series of static image frames in the form of electrical signals. When the image frame changes more than 24 frames per second, the human eye cannot distinguish a single static picture, forming a smooth and continuous visual effect.

[0059] Information separation of a call video refers to separating the image and voice data in the call video, and downsampling the image and converting it into an image frame of the first frequency, thereby reducing network overhead.

[0060] In one embodiment, the sending end can call video editing software, online tools or video players installed on the terminal device to implement video separation. Online tools such as Kapwing or Clideo, etc., and video players such as VLC media player.

[0061] In one embodiment, the first frequency is also called the frame rate, which refers to the number of frames displayed per second. The first frequency is closely related to the video fluency. The higher the value of the first frequency, the better the video fluency. The lower the value of the first frequency, the worse the video fluency. The first frequency is greater than 24fps. The first frequency can be determined according to actual needs. Different first frequencies correspond to different video fluency, which is expressed in FPS (Frames Per Second).

[0062] For example, in the early stage of a video call, the first frequency can be set to 30fps to ensure the minimum acceptable video fluency; after the video call connection is stable, the value of the first frequency can be adjusted according to actual needs. For example, the frame rate can be increased to 60fps to provide a smooth visual experience.

[0063] In one embodiment, after the transmitting end separates the call video of the first user to obtain audio data and image frames of the first frequency, the transmitting end can send the audio data and the image frames of the first frequency to the gateway via a satellite uplink, and the gateway then sends the audio data and the image frames of the first frequency to the satellite.

[0064] In one embodiment, the transmitting end may also perform data escort on the audio data and the image frames of the first frequency, so as to further reduce the occupation of the communication bandwidth.

[0065] S204: The satellite processes the audio data and the image frames of the first frequency to obtain target data and sends the target data to the receiving end.

[0066] The receiving end refers to the receiving end of the call video, which is opposite to the sending end in S202. In some cases, the functions of the sending end and the receiving end can be switched.

[0067] In S204, the manner in which the satellite processes the audio data and the image frames of the first frequency varies according to the configuration location of the artificial intelligence model.

[0068] When the artificial intelligence model is configured on the satellite, the satellite processes the audio data and the image frames of the first frequency in that the satellite inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain target data, and the target data is the target call video output by the artificial intelligence model.

[0069] When the artificial intelligence model is configured at the receiving end, the satellite processes the audio data and the image frames of the first frequency by data forwarding, and the target data is the audio and the image frames of the first frequency, that is, the satellite sends the audio and the image frames of the first frequency to the receiving end via the satellite downlink.

[0070] S206. The receiving end obtains the target call video according to the target data, and outputs the target call video to the second user; wherein the satellite or the receiving end is configured with an artificial intelligence model, which takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video.

[0071] The second user refers to the user using the terminal device at the receiving end, that is, the other party of the video call.

[0072] When the artificial intelligence model is configured on the satellite, the target data received by the receiving end is the target call video. At this time, the receiving end directly outputs the target call video to the second user.

[0073] When the artificial intelligence model is configured at the receiving end, the target data received by the receiving end is audio data and image frames of the first frequency. At this time, the receiving end inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video and output the target call video to the second user.

[0074] In one embodiment, the artificial intelligence model may adopt a 3D convolutional neural network (3D CNN), a recursive neural network (RNN), a transformer model, etc. 3D CNN can effectively capture the spatiotemporal features in the video by introducing the convolution operation of the time dimension in the convolution layer. RNN processes sequence data through a cyclic structure and can effectively capture information in the time series. Transformer can effectively process long sequence data through the self-attention mechanism, and can process the spatiotemporal features of the call video and capture long-distance dependencies.

[0075] In one embodiment, the artificial intelligence model can represent the mapping relationship between the audio data and the image frames of the first frequency and the call video. The call video is the output of the artificial intelligence model.

[0076] In one embodiment, the method further includes: if the receiving end has the model deployment capability, configuring the artificial intelligence model at the receiving end; if the receiving end does not have the model deployment capability, configuring the artificial intelligence model on the satellite.

[0077] Model deployment capability refers to whether the receiving end has the ability to deploy the artificial intelligence model, such as the storage space and running memory for deploying the artificial intelligence model.

[0078] Exemplarily, when the receiving end used by the second user is an old version terminal device, the receiving end does not have the model deployment capability. When the receiving end is a new version terminal device, the receiving end has the model deployment capability, thereby making satellite communications fully compatible with terminal devices of different versions, making full use of the characteristics of the satellite's narrow uplink channel and wide downlink channel, and increasing the compatibility of satellite communications.

[0079] In the embodiment of the present disclosure, the transmitting end obtains the call video of the first user, separates the information of the call video, obtains audio data and image frames of the first frequency, and sends the audio data and image frames of the first frequency to the satellite; the satellite processes the audio data and the image frames of the first frequency to obtain target data and sends it to the receiving end; the receiving end obtains the target call video according to the target data, and outputs the target call video to the second user; the satellite or the receiving end is configured with an artificial intelligence model, and the artificial intelligence model uses the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video. On the one hand, the artificial intelligence model of the present disclosure, as a semantic communication, can automatically filter redundant information through intelligent analysis and generation technology, effectively solve the problem of narrow satellite communication channels, and improve the efficiency and security of satellite communications. On the other hand, configuring the artificial intelligence model on the satellite or the receiving end can achieve compatibility with the receiving end, increasing the compatibility of satellite system video calls.

[0080] Figure 3 FIG. 2 shows another flow chart of a video call method based on a satellite system provided by an embodiment of the present disclosure. Figure 3 As shown, in one embodiment, when the artificial intelligence model is configured on a satellite, the target data is a target call video;

[0081] The S204 satellite processes the audio data and the image frame of the first frequency to obtain the target data and sends it to the receiving end, including:

[0082] S2042: The satellite inputs the audio data and the image frame of the first frequency into the artificial intelligence model to obtain a target call video, and sends the target call video to a receiving end through a downlink of the satellite;

[0083] S206 The receiving end obtains a target call video according to the target data, and outputs the target call video to the second user, including:

[0084] S2062. The receiving end receives the target call video and outputs the target call video to the second user.

[0085] In one embodiment, when the artificial intelligence model is configured on a satellite, the satellite inputs audio data and image frames of a first frequency into the artificial intelligence model, outputs the actions and expressions of the first user, and generates a target call video based on the virtual image model of the first user and the actions and expressions of the first user.

[0086] It should be noted that the target call video is the video predicted by the artificial intelligence model, and there may be certain differences between it and the call video of the first user, as long as the difference between the two is within an acceptable range.

[0087] The virtual image model of the first user may be obtained by three-dimensional modeling. The virtual image model may be a two-dimensional image or a three-dimensional image, and the present disclosure does not make any specific limitation on this.

[0088] The satellite's downlink may include a gateway, satellite signal transceiver antenna equipment, etc.

[0089] In S2062, the receiving end directly outputs the target call video after receiving it.

[0090] In the disclosed embodiment, by configuring the artificial intelligence model on the satellite, the satellite restores the audio data and the image frames of the first frequency into the target call video, thereby effectively solving the problem of the narrow satellite uplink channel, making full use of the specific wide satellite downlink channel, being fully compatible with old terminal equipment, and improving the compatibility of satellite communications.

[0091] Figure 4 FIG. 2 shows another flow chart of a video call method based on a satellite system provided by an embodiment of the present disclosure. Figure 4 As shown, in one embodiment, when the artificial intelligence model is configured at the receiving end, the target data is audio data and an image frame of a first frequency;

[0092] The S204 satellite processes the audio data and the image frame of the first frequency to obtain the target data and sends it to the receiving end, including:

[0093] S2042. The satellite forwards the audio data and the image frame of the first frequency to the receiving end through a downlink of the satellite;

[0094] S206 The receiving end obtains the target call video according to the target data, including:

[0095] S2062. The receiving end inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video.

[0096] In one embodiment, when the artificial intelligence model is configured at the receiving end, after the satellite receives the audio data of the first user and the image frames of the first frequency, the audio data and the image frames of the first frequency are sent to the receiving end via a satellite downlink.

[0097] After the receiving end receives the audio data of the first user and the image frames of the first frequency, it inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video, and outputs the target call video to the second user.

[0098] It should be noted that the method of obtaining the target call video is similar when the artificial intelligence model is deployed at the receiving end and deployed on the satellite, and the similarities will not be repeated here.

[0099] In the disclosed embodiment, the artificial intelligence model is configured at the receiving end, and the satellite is used to forward audio data and image frames of the first frequency. The receiving end inputs the audio data and image frames of the first frequency into the artificial intelligence model to obtain the target call video, which can effectively improve the data transmission efficiency.

[0100] In one embodiment, the method further includes: the sending end trains the artificial intelligence model in the following manner:

[0101] Obtain the historical call videos of historical users, and separate the information of the historical call videos to obtain historical audio data and image frames with a preset frame rate;

[0102] Perform three-dimensional modeling on the image of the historical user to obtain the virtual image model of the historical user, and extract the action and expression labels of the historical user in each image frame;

[0103] Taking historical audio data, image frames at a preset frame rate, and virtual image models of historical users as inputs, and taking the movements and expressions of historical users in historical call videos as outputs, the artificial intelligence model to be trained is trained to obtain an initial artificial intelligence model;

[0104] The frame rate of the image frames is adjusted, and the initial artificial intelligence model is retrained to obtain a trained artificial intelligence model.

[0105] In one embodiment, a data set is constructed based on historical call videos of historical users, historical audio data, image frames of a preset frame rate, and action expression labels of historical users for training an artificial intelligence model.

[0106] The artificial intelligence model to be trained is the initially constructed artificial intelligence model.

[0107] The artificial intelligence model takes historical audio data, image frames with a preset frame rate, and the virtual image model of historical users as input, and takes the movements and expressions of historical users in historical call videos as output. The artificial intelligence model is trained, and the loss function value is calculated based on the predicted movement and expression values ​​of historical users output by the artificial intelligence model and the movement and expression labels of historical users. The loss function can be a root mean square loss function, a mean absolute error loss function, etc.

[0108] When the loss function value is less than the preset loss function threshold, the training of the artificial intelligence model to be trained is completed and the initial artificial intelligence model is obtained; when the loss function value is greater than or equal to the preset loss function threshold, the model parameters of the artificial intelligence model to be trained are adjusted and iterative training is performed until the loss function value is less than the preset loss function threshold.

[0109] The value of the preset loss function threshold can be determined according to actual needs, and this disclosure does not make any specific limitations on this.

[0110] It should be noted that when the trained artificial intelligence model converges, the training duration and number of training times can also be used as judgment criteria for model convergence.

[0111] In one embodiment, the frame rate of the image frame can be adjusted by setting a series of different frame rate values ​​based on the preset frame rate. For example, when the preset frame rate is 40fps, it can be set to 24fps, 30fps, 35fps, 45fps, 50fps, 60fps, etc., and the initial artificial intelligence model can be retrained to obtain a trained artificial intelligence model.

[0112] It should be noted that an artificial intelligence model can also be trained based on the frame rate of an image frame.

[0113] In the disclosed embodiment, the training process of the artificial intelligence model is completed at the sending end, which effectively avoids the frequent transmission of data and improves the efficiency of model training.

[0114] Figure 5 FIG. 2 is a flowchart of another video call method based on a satellite system provided by an embodiment of the present disclosure. Figure 5 As shown, after S206, S208 is added to adjust the frame rate according to user needs. Figure 5 As shown, in one embodiment, the method further includes:

[0115] S208. The transmitting end receives the frequency adjustment instruction sent by the receiving end, and adjusts the frame rate of the image frame according to the second frequency in the frequency adjustment instruction, where the second frequency represents the adjusted transmitting frequency, and the second frequency is not equal to the first frequency.

[0116] After the receiving end outputs the target call video to the second user, the frame rate of the image frame, that is, the second frequency, can be determined according to the needs of the second user.

[0117] The frequency adjustment instruction is used to instruct the transmitting end to adjust the frame rate of the image frame according to the second frequency.

[0118] In the disclosed embodiment, when the call video data is compressed to the voice level, the frame rate of the transmitted image frames is dynamically adjusted to achieve the purpose of compression and improve the user service quality.

[0119] Figure 6 FIG. 2 is a flowchart of another video call method based on a satellite system provided by an embodiment of the present disclosure. Figure 6 As shown, in one embodiment, before the transmitting end receives the frequency adjustment instruction sent by the receiving end in S208, the method further includes:

[0120] S207. The receiving end obtains the second user's attention level value for the video call and / or the service level selected by the second user, and determines the second frequency according to the second user's attention level value for the video call and / or the service level selected by the second user.

[0121] In one embodiment, the receiving end may determine the attention level of the second user to the video call through a gaze level monitoring module.

[0122] For example, the attention level value can be determined by the length of time the second user stares at the display of the terminal device. The length of time the second user stares at the display is directly proportional to the attention level value, that is, the longer the staring time is, the greater the attention level value is, and the shorter the time is, the smaller the attention level value is.

[0123] For example, the attention level value may also be determined through other user behaviors, such as information such as the second user adjusting the sound tone change of the terminal device to determine the attention level value.

[0124] The receiving end can also determine the service level selected by the second user through the service quality determination module, and different service levels correspond to different service qualities, and different service levels correspond to different image frame rates. For example, the second user can select the service level through a button or a drop-down menu set on the display interface of the terminal device, thereby determining the second frequency according to the service level.

[0125] It should be noted that the method of determining the second frequency according to the second user's attention level to the video call and the method of determining the second frequency according to the service level selected by the second user can be performed separately or in combination.

[0126] For example, for the above-mentioned combined method of determining the second frequency, after determining the service level, the second frequency can be fine-tuned in combination with the attention level value.

[0127] It should be noted that the receiving end can send the second frequency to the sending end, and can also send the second user's attention level value for the video call and / or the service level selected by the second user to the sending end, so that the sending end determines the second frequency value based on the second user's attention level value for the video call and / or the service level selected by the second user.

[0128] In the embodiment of the present disclosure, the second frequency is determined by the second user's attention level to the video call and / or the service level selected by the second user, thereby improving the user experience and satisfying the user service quality.

[0129] In order to deepen the understanding of the embodiments of the present disclosure, Figure 7 Provide detailed explanation.

[0130] like Figure 7As shown, the video calling method based on the satellite system includes the following steps:

[0131] S701, the sending end captures the call video of the first user;

[0132] S702: The transmitting end splits the call video of the first user into audio data and image frames of a first frequency;

[0133] S703, the transmitting end sends the audio data and the image frame of the first frequency to the satellite;

[0134] S704, the satellite sends data according to the needs of the receiving end;

[0135] S705: Whether the receiving end has the ability to restore the video by combining the image frame and the voice data, if yes, execute S706; if no, execute S707;

[0136] S706, the satellite forwards the audio data and the image frame of the first frequency to the receiving end;

[0137] S707: The receiving end uses the artificial intelligence model to restore the audio data and the image frames of the first frequency into the target call video, and executes S709;

[0138] S708, the satellite uses the artificial intelligence model to restore the audio data and the image frame of the first frequency into the target call video, sends it to the receiving end, and executes S709;

[0139] S709, the receiving end determines whether the second user adjusts the service quality, if so, executes S710, if not, maintains the video call until the video call ends;

[0140] S710: Obtain a service level selected by a second user, determine a second frequency according to the service level, the second frequency being the adjusted frame rate of the image frame, and send the second frequency to a transmitting end.

[0141] The receiving end can also determine the service level selected by the second user through the service quality determination module, and different service levels correspond to different service qualities, and different service levels correspond to different image frame rates. For example, the second user can select the service level through a button or a drop-down menu set on the display interface of the terminal device, thereby determining the second frequency according to the service level.

[0142] In S707 and S708, in one embodiment, the artificial intelligence model can characterize the mapping relationship between the audio data and the image frames of the first frequency and the call video.

[0143] It should be noted that the above examples are only provided to illustrate the embodiments of the present disclosure and should not be regarded as limiting the scope of protection of the present disclosure. The above steps can also be adjusted in order according to actual needs, and this application does not make specific limitations.

[0144] Based on the same inventive concept, the embodiments of the present disclosure also provide a video call system based on a satellite system, as described in the following embodiments. Since the principle of solving the problem in the system embodiment is similar to that in the above method embodiment, the implementation of this embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0145] Figure 8 FIG. 2 is a schematic diagram of a satellite-based video call system provided by an embodiment of the present disclosure. Figure 8 As shown, a video call system based on a satellite system in this embodiment includes a transmitting end 810, a satellite 130 and a receiving end 820, wherein:

[0146] The transmitting end 810 is used to obtain the call video of the first user, separate the information of the call video to obtain audio data and image frames of the first frequency, and send the audio data and the image frames of the first frequency to the satellite 130;

[0147] The satellite 130 is used to process the audio data and the image frame of the first frequency to obtain the target data and send it to the receiving end 820;

[0148] The receiving end 820 is used to obtain a target call video according to the target data, and output the target call video to the second user;

[0149] The satellite 130 or the receiving end 820 is configured with an artificial intelligence model, which is used to generate a target call video using audio data and image frames of a first frequency as input and a call video as output.

[0150] In one embodiment, the transmitting end 810 is also used to configure the artificial intelligence model on the receiving end 820 if the receiving end 820 has the model deployment capability; if the receiving end 820 does not have the model deployment capability, the artificial intelligence model is configured on the satellite 130.

[0151] In one embodiment, when the artificial intelligence model is configured on the satellite 130, the target data is a target call video; the satellite 130 is used to input the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video, and send the target call video to the receiving end 820 via the downlink of the satellite 130.

[0152] In one embodiment, when the artificial intelligence model is configured at the receiving end 820, the target data is audio data and image frames of a first frequency; the satellite 130 is used to forward the audio data and image frames of the first frequency to the receiving end 820 via a downlink of the satellite 130; the receiving end 820 is used to input the audio data and image frames of the first frequency into the artificial intelligence model to obtain a call video.

[0153] In one embodiment, the transmitting end 810 is used to train the artificial intelligence model in the following manner: obtain historical call videos of historical users, and separate information from the historical call videos to obtain historical audio data and image frames with a preset frame rate; perform three-dimensional modeling on the image of the historical user to obtain a virtual image model of the historical user; use the historical audio data, image frames with a preset frame rate and the virtual image model of the historical user as input and the action expressions of the historical user in the historical call videos as output to train the artificial intelligence model to obtain an initial artificial intelligence model; adjust the frame rate of the image frames, retrain the initial artificial intelligence model, and obtain a trained artificial intelligence model.

[0154] In one embodiment, the transmitting end 810 is used to receive a frequency adjustment instruction sent by the receiving end 820, and adjust the frame rate of the image frame according to a second frequency in the frequency adjustment instruction, where the second frequency represents the adjusted frame rate and is not equal to the first frequency.

[0155] In one embodiment, the receiving end 820 is used to obtain the second user's attention level to the video call and / or the service level selected by the second user; and determine the second frequency according to the second user's attention level to the video call and / or the service level selected by the second user.

[0156] like Fig. 9 As shown, in one embodiment, the receiving end 820 includes a gaze monitoring module 821. The gaze monitoring module 821 is used to determine the attention level of the second user to the video call.

[0157] For example, the attention level value can be determined by the length of time the second user stares at the display of the terminal device. The length of time the second user stares at the display is directly proportional to the attention level value, that is, the longer the staring time is, the greater the attention level value is, and the shorter the time is, the smaller the attention level value is.

[0158] For example, the attention level value may also be determined through other user behaviors, such as information such as the second user adjusting the sound tone change of the terminal device to determine the attention level value.

[0159] Continue to refer Fig. 9In one embodiment, the receiving end 820 may further include a service quality determination module 822, which is used to determine the service level selected by the second user, where different service levels correspond to different service qualities, and different service levels correspond to different image frame rates. For example, the second user may select a service level through a button or a drop-down menu set on a display interface of the terminal device, thereby determining the second frequency according to the service level.

[0160] It should be noted that the method of determining the second frequency according to the second user's attention level to the video call and the method of determining the second frequency according to the service level selected by the second user can be performed separately or in combination.

[0161] For example, for the above-mentioned combined method of determining the second frequency, after determining the service level, the second frequency can be fine-tuned in combination with the attention level value.

[0162] In the embodiment of the present disclosure, the transmitting end 810 obtains the call video of the first user, separates the information of the call video, obtains audio data and image frames of the first frequency, and sends the audio data and image frames of the first frequency to the satellite 130; the satellite 130 processes the audio data and the image frames of the first frequency to obtain the target data and sends it to the receiving end 820; the receiving end 820 obtains the target call video according to the target data, and outputs the target call video to the second user; the satellite 130 or the receiving end 820 is configured with an artificial intelligence model, and the artificial intelligence model takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video. On the one hand, the artificial intelligence model of the present disclosure, as a semantic communication, can automatically filter redundant information through intelligent analysis and generation technology, effectively solve the problem of narrow satellite communication channels, and improve the efficiency and security of satellite communications. On the other hand, configuring the artificial intelligence model on the satellite or the receiving end can achieve compatibility with the receiving end, which increases the compatibility of satellite system video calls.

[0163] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0164] Refer to the following Fig.10 The electronic device 1000 according to this embodiment of the present disclosure is described. Fig.10 The electronic device 1000 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0165] like Fig.10 As shown, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 may include but are not limited to: the at least one processing unit 1010, the at least one storage unit 1020, and a bus 1030 connecting different system components (including the storage unit 1020 and the processing unit 1010).

[0166] The storage unit stores a program code, which can be executed by the processing unit 1010, so that the processing unit 1010 executes the steps described in the "Exemplary Method" section of the specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 1010 can execute the following steps of the above method embodiment: the transmitting end obtains the call video of the first user, separates the information of the call video, obtains audio data and image frames of the first frequency, and sends the audio data and image frames of the first frequency to the satellite; the satellite processes the audio data and the image frames of the first frequency to obtain target data and sends it to the receiving end; the receiving end obtains the target call video according to the target data, and outputs the target call video to the second user; wherein the satellite or the receiving end is configured with an artificial intelligence model, which takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video.

[0167] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 10201 and / or a cache storage unit 10202 , and may further include a read-only storage unit (ROM) 10203 .

[0168] The storage unit 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0169] Bus 1030 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0170] The electronic device 1000 may also communicate with one or more external devices 1040 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 1000, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 1050. Furthermore, the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1060. Fig.10 As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 via the bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0171] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0172] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is further provided, which may be a readable signal medium or a readable storage medium. Fig.11 A schematic diagram of a computer-readable storage medium provided in an embodiment of the present disclosure is shown. Fig.11 As shown, a program product capable of implementing the above method of the present disclosure is stored on the computer-readable storage medium 1100. In an exemplary embodiment of the present disclosure, a computer program product is also provided, the computer program product includes a computer program or a computer instruction, and the computer program or the computer instruction is loaded and executed by a processor to enable a computer to implement any of the above video call methods based on a satellite system.

[0173] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0174] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0175] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0176] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0177] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0178] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0179] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0180] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope of the present disclosure is indicated by the appended claims.

Claims

1. A video calling method based on a satellite system, characterized in that: include: The transmitting end obtains a call video of the first user, separates information from the call video to obtain audio data and image frames of a first frequency, and sends the audio data and the image frames of the first frequency to the satellite; The satellite processes the audio data and the image frame of the first frequency to obtain target data and sends the target data to a receiving end; The receiving end obtains a target call video according to the target data, and outputs the target call video to the second user; The satellite or the receiving end is configured with an artificial intelligence model, which takes the audio data and the image frames of the first frequency as input and the call video as output to generate a target call video that matches the call video.

2. The satellite-based video calling method according to claim 1, characterized in that: The method further comprises: If the receiving end has model deployment capability, the sending end configures the artificial intelligence model on the receiving end; If the receiving end does not have the model deployment capability, the sending end configures the artificial intelligence model on the satellite.

3. The satellite system-based video calling method according to claim 1 or 2, characterized in that: When the artificial intelligence model is configured on the satellite, the target data is the target call video; The satellite processes the audio data and the image frame of the first frequency to obtain target data and sends the target data to the receiving end, including: The satellite inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video, and sends the target call video to the receiving end via the downlink of the satellite.

4. The satellite system-based video calling method according to claim 1 or 2, characterized in that: When the artificial intelligence model is configured at the receiving end, the target data is the audio data and the image frame of the first frequency; The satellite processes the audio data and the image frame of the first frequency to obtain target data and sends the target data to the receiving end, including: The satellite forwards the audio data and the image frame of the first frequency to the receiving end via a downlink of the satellite; The receiving end obtains the target call video according to the target data, including: The receiving end inputs the audio data and the image frames of the first frequency into the artificial intelligence model to obtain the target call video.

5. The satellite-based video calling method according to claim 1, characterized in that: The method further includes: the sending end trains the artificial intelligence model in the following manner: Obtain historical call videos of historical users, and separate information from the historical call videos to obtain historical audio data and image frames at a preset frame rate; Performing three-dimensional modeling on the image of the historical user to obtain a virtual image model of the historical user; Taking the historical audio data, the image frames at a preset frame rate and the virtual image model of the historical user as input, and taking the action and expression of the historical user in the historical call video as output, the artificial intelligence model to be trained is trained to obtain an initial artificial intelligence model; The frame rate of the image frame is adjusted, and the initial artificial intelligence model is retrained to obtain the trained artificial intelligence model.

6. The satellite-based video calling method according to claim 1, characterized in that: The method further comprises: The transmitting end receives the frequency adjustment instruction sent by the receiving end, and adjusts the frame rate of the image frame according to a second frequency in the frequency adjustment instruction, where the second frequency represents the adjusted frame rate, and the second frequency is not equal to the first frequency.

7. The satellite-based video calling method according to claim 6, characterized in that: The method further comprises: The receiving end obtains the second user's attention level value for the video call and / or the service level selected by the second user; and determines the second frequency according to the second user's attention level value for the video call and / or the service level selected by the second user.

8. A video call system based on a satellite system, characterized in that: The system comprises a transmitting end, a satellite and a receiving end, wherein: The transmitting end is used to obtain a call video of the first user, separate information from the call video to obtain audio data and image frames of a first frequency, and send the audio data and the image frames of the first frequency to the satellite; The satellite is used to process the audio data and the image frame of the first frequency to obtain target data and send it to the receiving end; The receiving end is used to obtain a target call video according to the target data, and output the target call video to the second user; The satellite or the receiving end is configured with an artificial intelligence model, which is used to generate the target call video using the audio data and the image frames of the first frequency as input and the call video as output.

9. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory is used to store executable instructions of the processor; wherein the processor is configured to execute the satellite system-based video calling method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the satellite system-based video calling method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that It comprises a computer program or a computer instruction, and the computer program or the computer instruction is loaded and executed by a processor so that a computer implements the video calling method based on a satellite system as claimed in any one of claims 1 to 7.

Images