Emergency communication method for unmanned aerial vehicle satellite base station and unmanned aerial vehicle satellite base station

Abstract

The application provides an emergency communication method for a UAV satellite base station and the UAV satellite base station, and belongs to the technical field of wireless communication. The emergency communication method comprises the following steps: obtaining and storing at least one first artificial intelligence model related to target cell preset information before the UAV satellite base station takes off; after reaching a preset working position, sending a first message to a terminal device in a target cell and receiving a second message fed back by the terminal device; determining a second artificial intelligence model from the at least one first artificial intelligence model based on the second message; determining target configuration information based on the second artificial intelligence model, and communicating with the terminal device according to the target configuration information. The application realizes differentiated communication configuration for the terminal device by introducing terminal-side artificial intelligence model processing capability feedback and matching selection in combination with a pre-stored model, thereby improving the wireless resource scheduling efficiency under the condition that backhaul resources are limited, and reducing unnecessary channel measurement and reporting overhead.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to an emergency communication method for unmanned aerial vehicle (UAV) satellite base stations and an UAV satellite base station. Background Technology

[0002] Following major natural disasters such as earthquakes, floods, and typhoons, ground communication infrastructure is easily damaged to varying degrees. In particular, the interruption of fiber optic backhaul links, power outages at ground base stations, or equipment damage can lead to a significant reduction or even complete paralysis of communication capabilities in localized areas. To improve emergency communication support capabilities, in recent years, the use of unmanned helicopters to carry base station equipment has been increasingly adopted. These temporary aerial base stations are deployed over disaster-stricken areas to provide wireless communication services to user equipment via wireless access and to connect to the core network via satellite links.

[0003] Compared to fixed terrestrial base stations, aerial base stations differ significantly in their operating environment, link conditions, and user distribution characteristics. On one hand, aerial base stations typically rely on satellite links for backhaul, which have relatively limited bandwidth and higher transmission latency, making overall network resources more strained. On the other hand, the number of users, service types, and service priorities in disaster areas exhibit highly dynamic changes, potentially leading to a surge in terminal device access within a short period or scenarios with concurrent voice, video, and data services. In related technologies, aerial base stations mostly employ traditional cellular system scheduling and resource management mechanisms, using fixed rules or real-time measurement-based methods for channel quality assessment and resource allocation. This approach typically relies on terminal devices frequently performing channel measurements and reporting relevant information to support base station-side scheduling decisions. However, under conditions of limited backhaul resources and drastic environmental changes, excessive measurement and reporting not only increases the burden on radio signaling but also consumes valuable transmission resources and may lead to increased power consumption of terminal devices, which is detrimental to ensuring continuous communication in disaster scenarios.

[0004] Therefore, in emergency communication applications of airborne base stations, how to improve the efficiency of wireless resource scheduling and reduce unnecessary channel measurement and signaling overhead under the condition of limited backhaul resources has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides an emergency communication method and a UAV satellite base station for use with UAV satellite base stations, in order to solve the problems of low efficiency of wireless resource scheduling, frequent channel measurement and reporting by terminal equipment, and large signaling overhead in the emergency communication application of existing airborne base stations under the condition of limited backhaul resources.

[0006] In a first aspect, this application provides an emergency communication method for a UAV satellite base station, the method comprising: Before the drone takes off from the satellite base station, at least one first artificial intelligence model is acquired and stored. The first artificial intelligence model is related to the preset information of the target cell. The preset information includes the regional type information, population distribution information, service area distribution information and / or service time information of the target cell. After the UAV satellite base station reaches the preset working position, it sends a first message to a first terminal device in the target cell. The first message is used to indicate the artificial intelligence model processing capability information of the UAV satellite base station; wherein, the first terminal device is any terminal device in the target cell. The second terminal device receives a second message in response to the first message, the second message being used to indicate the artificial intelligence model processing capability information of the second terminal device; wherein, the second terminal device is any of the first terminal devices that successfully received the first message and fed back the second message to the UAV satellite base station; Based on the second message, a second artificial intelligence model is determined from the at least one first artificial intelligence model; Based on the second artificial intelligence model, target configuration information is determined; wherein, the target configuration information includes the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information of the UAV satellite base station for the second terminal device; Based on the target configuration information, communication is established with the second terminal device.

[0007] In one possible design, the first message includes a first parameter, which indicates whether the UAV satellite base station has artificial intelligence model processing capabilities; and / or, The first message includes type information or identification information of the at least one first artificial intelligence model.

[0008] In one possible design, the first message further includes feedback request information, which is used to instruct the second terminal device to send target information back to the UAV satellite base station; The target information includes whether the second terminal device supports at least one of an artificial intelligence model, a third artificial intelligence model, and a fourth artificial intelligence model; the third artificial intelligence model is the first artificial intelligence model supported by the second terminal device, and the fourth artificial intelligence model is the artificial intelligence model recommended by the second terminal device.

[0009] In one possible design, when the target information includes the fourth artificial intelligence model, the total number of the fourth artificial intelligence models fed back by the second terminal device to the UAV satellite base station is less than a first preset number.

[0010] In one possible design, the second message includes the target information; When the target information includes the fourth artificial intelligence model, the second message also includes matching information, which includes the matching degree between the fourth artificial intelligence model and each of the first artificial intelligence models.

[0011] In one possible design, determining the second artificial intelligence model from the at least one first artificial intelligence model based on the second message includes: When the target information includes the third artificial intelligence model, the third artificial intelligence model is identified as the second artificial intelligence model; When the target information includes the fourth artificial intelligence model and the target information does not include the third artificial intelligence model, based on the matching information, the first artificial intelligence model with the highest matching degree with the fourth artificial intelligence model is determined as the second artificial intelligence model.

[0012] In one possible design, after sending the first message to the first terminal device within the target cell, the method further includes: The first message is stopped from being sent if a preset stopping condition is met. The preset stop condition includes at least one of the following: The first message has been sent for a preset duration. The number of the second terminal devices reaches the second preset number.

[0013] In one possible design, the method further includes: Send a model update request to the core network control element, wherein the model update request is used to request an update of the at least one first artificial intelligence model; Receive a response message sent by the core network control element based on the model update request, the response message including multiple updated first artificial intelligence models; Based on the response message, the at least one first artificial intelligence model is updated to obtain multiple updated first artificial intelligence models; The multiple updated first artificial intelligence models are determined as at least one first artificial intelligence model, and the step of sending the first message to the first terminal device in the target cell is repeated.

[0014] Secondly, this application provides a drone satellite base station, including: a module for performing the aforementioned method embodiment of the first aspect.

[0015] Thirdly, this application provides a UAV satellite base station, including: a memory and at least one processor; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method described in the first aspect or various possible designs of the first aspect.

[0016] Fourthly, this application provides an emergency communication method, including the unmanned aerial vehicle (UAV) satellite base station described in the first or second aspect above.

[0017] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed, implement the method described in the first aspect or various possible designs of the first aspect.

[0018] Sixthly, this application provides a computer program product including computer program code, which, when run on a computer, causes the computer to implement the method described in the first aspect or various possible designs of the first aspect.

[0019] This application provides an emergency communication method and a UAV satellite base station for use with UAV satellite base stations. The communication method acquires and stores multiple first artificial intelligence models related to preset information of the target cell before the UAV satellite base station takes off, enabling the UAV satellite base station to pre-configure model selection for different target cell scenarios. After the UAV satellite base station reaches a preset working position, it sends a first message to a first terminal device within the target cell and receives a second message from a second terminal device responding to the first message. The second terminal device is the first terminal device that successfully received the first message, thereby acquiring the artificial intelligence model processing capability information of the second terminal device. Further, based on the second message, it retrieves information from at least one first artificial intelligence model... The first application determines a second artificial intelligence model that is compatible with the processing capabilities of the second terminal device's artificial intelligence model. Based on this, target configuration information is determined based on the second artificial intelligence model. The target configuration information includes the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information of the UAV satellite base station for the second terminal device. Therefore, this application can communicate with the second terminal device using the target configuration information that matches the pre-stored first artificial intelligence model and the artificial intelligence model processing capability information fed back by the second terminal device. This improves the wireless resource scheduling efficiency of the UAV satellite base station under the condition of limited backhaul resources and reduces unnecessary channel measurement and reporting and the resulting signaling overhead. Attached Figure Description

[0020] Figure 1 A schematic diagram of the network structure of an existing wireless communication system; Figure 2 This is a schematic diagram of the structure of a satellite communication system applicable to the embodiments of this application; Figure 3 A flowchart illustrating an emergency communication method for a UAV satellite base station provided in an embodiment of this application; Figure 4 A flowchart illustrating another emergency communication method for a UAV satellite base station provided in this application embodiment; Figure 5 A flowchart illustrating another emergency communication method for a UAV satellite base station provided in this application embodiment; Figure 6 This is a schematic diagram of the structure of a UAV satellite base station provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims and drawings of this application are intended to cover non-exclusive inclusion.

[0023] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0024] In this article, the term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists, A and B can exist simultaneously, and B exists. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0025] Furthermore, the terms "first," "second," etc., in the specification and claims of this application or in the aforementioned drawings are used to distinguish different objects rather than to describe a specific order, and may explicitly or implicitly include one or more of the features.

[0026] In the description of this application, unless otherwise stated, "multiple" and "at least two" mean two or more (including two), and similarly, "multiple groups" and "at least two groups" mean two or more (including two groups).

[0027] In the description of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, "connected" or "linked" can refer not only to a physical connection, but also to an electrical connection or a signal connection. For instance, it can be a direct connection, i.e., a physical connection, or an indirect connection through at least one intermediate component, as long as the circuit is connected. It can also refer to the internal connection between two components. A signal connection can refer not only to a signal connection through a circuit, but also to a signal connection through a medium, such as radio waves. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, different technical features in this application can be combined with each other.

[0029] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0030] A drone satellite base station refers to a type of mobile base station that mounts a backpack base station on a drone platform and transmits data back via a satellite link. A backpack base station is a portable / mobile base station (also called a "portable backpack base station" or "mobile backpack base station") that relies on high-throughput satellites as transmission carriers to provide communication between user equipment and the satellite. The backpack base station communicates with the core network of the communication network via satellite. The mobile communication system can be a Wideband Code Division Multiple Access (WCDMA) system, a Frequency Division Multiple Access (FDMA) system, an Orthogonal Frequency Division Multiple Access (OFDMA) system, a General Packet Radio Service (GPRS) system, a Long Term Evolution (LTE) system, or a 5th Generation Mobile Communication Technology (5G) system, as well as other similar communication systems.

[0031] Terminal equipment can be a wireless terminal, which can be a device that provides voice and / or other service data connectivity to a user, a handheld device with wireless connectivity, or other processing device connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a Radio Access Network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, which exchanges voice and / or data with the radio access network.

[0032] The following section introduces the implementation background of the technical solutions provided in the embodiments of this application.

[0033] Figure 1 This is a schematic diagram of the network architecture of an existing wireless communication system. (Example:) Figure 1As shown, the UE connects to the base station via a wireless interface, and the base station connects to the core network via a fiber optic interface. However, in the event of natural disasters such as earthquakes or floods, the fiber optic interface is easily damaged, leading to an interruption of the connection between the base station and the core network, thus creating a temporary communication island where the UE cannot communicate normally. Furthermore, in naturally formed temporary communication islands such as deserts or open oceans, although there may be multiple terminal devices with communication needs within a small area, traditional solutions are ineffective due to the difficulty and high cost of laying fiber optic cables.

[0034] To address these issues, drone satellite base stations have emerged. Figure 2 This is a schematic diagram of the structure of a satellite communication system applicable to an embodiment of this application. Figure 2 As shown, the UAV satellite base station connects to the satellite via a wireless interface, and the satellite then connects to the core network elements on the ground via a wireless interface, enabling terminal devices within the coverage area of ​​the UAV satellite base station to communicate normally. Even when traditional communication infrastructure is damaged or difficult to build, reliable communication services can still be provided.

[0035] In related technologies, most airborne base stations adopt the scheduling and resource management mechanisms of traditional cellular systems, using fixed rules or real-time measurement-based methods to assess channel quality and allocate resources. This approach typically relies on terminal devices frequently performing channel measurements and reporting relevant information to support scheduling decisions on the base station side. However, under conditions of limited backhaul resources and drastic environmental changes, excessive measurement and reporting not only increases the burden on radio signaling but also consumes valuable transmission resources and may lead to increased power consumption of terminal devices, which is detrimental to ensuring continuous communication in disaster scenarios.

[0036] Therefore, in emergency communication applications of airborne base stations, how to improve the efficiency of wireless resource scheduling and reduce unnecessary channel measurement and signaling overhead under the condition of limited backhaul resources has become an urgent problem to be solved.

[0037] Addressing the problems of related technologies, this application pre-acquires and stores multiple first artificial intelligence models related to pre-set information of the target cell before the UAV satellite base station takes off, enabling the base station to select models for different application scenarios. After the UAV satellite base station arrives at the target area, it obtains the artificial intelligence model processing capability information of the terminal device by sending a first message to the terminal device in the target cell and receiving a second message from the terminal device. Furthermore, based on the second message from the terminal device, it selects a second artificial intelligence model that is compatible with the current terminal device from multiple pre-stored first artificial intelligence models, and determines the target configuration information for the terminal device based on the second artificial intelligence model. The target configuration information includes wireless resource scheduling configuration information and / or channel measurement and reporting configuration information. This transforms the scheduling decision process, which originally relied on frequent measurement and reporting, into a decision process based on artificial intelligence model matching and configuration generation. This enables the UAV satellite base station to perform resource scheduling more effectively and reduce unnecessary channel measurement and signaling interactions under conditions of limited backhaul resources, thereby effectively solving the problems of insufficient wireless resource scheduling efficiency and large channel measurement and signaling overhead in related technologies.

[0038] Next, through some specific embodiments and accompanying drawings, we will describe in detail how this application solves the problems of low efficiency of wireless resource scheduling, frequent channel measurement and reporting by terminal equipment, and large signaling overhead in emergency communication applications of airborne base stations under the condition of limited backhaul resources.

[0039] Figure 3 This is a flowchart illustrating an emergency communication method for a UAV satellite base station, provided as an embodiment of this application. Figure 3 As shown, the emergency communication method provided in this application embodiment specifically includes S301 to S306, and S301 to S306 will be described in detail below.

[0040] It should be noted that the emergency communication method provided in this application embodiment is implemented by a UAV satellite base station.

[0041] A drone satellite base station is an airborne base station mounted on a drone platform. This airborne base station possesses wireless access capabilities, model storage capabilities, message sending and receiving capabilities, and resource scheduling and communication control capabilities. The drone satellite base station can establish a communication connection with the core network via a satellite link and, after temporary deployment over the target area, provides wireless communication services to terminal devices within the target cell.

[0042] S301. Before the drone takes off from the satellite base station, acquire and store at least one first artificial intelligence model.

[0043] It should be noted that "before takeoff" for the drone satellite base station refers to the preparation phase before the drone satellite base station leaves its ground deployment point and heads to the target area to perform emergency communication tasks.

[0044] During the preparation phase, the UAV satellite base station can obtain at least one first artificial intelligence model from local storage units, ground maintenance equipment, model management platforms, control centers, or model management nodes associated with the core network, and save at least one first artificial intelligence model to the UAV satellite base station's onboard memory for subsequent retrieval during emergency communication missions.

[0045] It should be noted that the target area is the region where the UAV satellite base station performs emergency communication support tasks, the target cell is the target service area corresponding to the target area, and the preset working position is a pre-planned or determined aerial stationing position for providing wireless communication coverage to the target cell. The preset working position is set to correspond to the target cell, enabling the UAV satellite base station to provide wireless coverage to the target cell and communicate with terminal devices within the target cell after arriving at the preset working position.

[0046] The first artificial intelligence model is related to the pre-set information of the target community.

[0047] It should be noted that the first artificial intelligence model is not randomly configured, but is acquired and stored in association with the pre-set information of the target cell, so that the drone satellite base station has the ability to select the appropriate model for different scenarios before entering the target area.

[0048] The first artificial intelligence model can be a model used to assist in determining resource scheduling strategies, a model used to assist in determining channel measurement and reporting configurations, or a comprehensive model used for both resource scheduling strategies and channel measurement and reporting configuration determination.

[0049] Furthermore, in practical use, different artificial intelligence models have different model identifiers. In addition, each artificial intelligence model can also have a model type label, a model parameter scale label, or an applicable scenario label, so that the UAV satellite base station can establish a correspondence between different artificial intelligence models and different target cell characteristics, thereby selecting and storing the first artificial intelligence model that matches the target cell according to the preset information of the target cell before takeoff.

[0050] For example, for target communities with dense populations and concentrated data services, AI models biased towards data scheduling strategies can be pre-stored; for target communities with a high proportion of voice services, AI models biased towards voice service assurance can be pre-stored; and for target communities with frequent service changes, AI models that respond more flexibly to feedback information from terminal devices can be pre-stored.

[0051] By completing the preparation and storage of the first artificial intelligence model before takeoff, the large-scale model acquisition by the drone satellite base station can be avoided after the drone reaches the target area, thus enabling it to quickly carry out emergency communication work after entering the target area.

[0052] The preset information includes the target community's regional type information, population distribution information, service area distribution information, and / or service time information.

[0053] It should be noted that the area type information is used to characterize the scene category to which the target community belongs, such as business district, residential area, rural area, industrial area, school area, transportation hub area, etc.

[0054] Population distribution information is used to characterize at least one of the following in the target community: number of users, user density, population concentration location, and time-varying population changes.

[0055] Service area distribution information is used to characterize the service usage characteristics of the target cell, such as areas with high voice service usage, areas with high video service usage, areas with high data service usage, and areas with concentrated emergency command services.

[0056] Service time information is used to characterize the communication service demand characteristics of the target cell in different time periods, such as higher service load during the day, lower service load at night, and sudden service peaks during specific periods.

[0057] The drone satellite base station can determine one or more first artificial intelligence models that match the target cell scene based on pre-set information, and store one or more first artificial intelligence models.

[0058] Furthermore, before takeoff, the drone satellite base station can not only select at least one primary artificial intelligence model based on the target cell's regional type information, population distribution information, business area distribution information, and / or service time information, but also configure and store at least one primary artificial intelligence model in a targeted manner based on the disaster type.

[0059] Specifically, for different target communities, due to differences in their regional type, population distribution, and business area distribution information, the corresponding applicable first artificial intelligence model may also be different.

[0060] For example, if the target cell is located in a city business district, the business area distribution information of the target cell is usually characterized by a high proportion of file transfer services, as well as voice calls, video streaming and other service types. Therefore, the drone satellite base station can prioritize storing the first artificial intelligence model that is biased towards data service scheduling and file transfer guarantee.

[0061] For example, if the target community is located in a residential area, the service area distribution information of the target community is usually characterized by a high proportion of voice call services, accompanied by other service types such as emergency calls. Therefore, the drone satellite base station can prioritize storing the first artificial intelligence model that is biased towards voice service protection.

[0062] For example, if the target community is located in a rural area, the population distribution information and service time information of the target community usually have strong time-varying characteristics. For example, during the day, most of the population is distributed in areas such as factories and office buildings, while at night they are mainly distributed in village residential areas. Therefore, the drone satellite base station can prioritize storing the first artificial intelligence model that is suitable for responding to the time-varying characteristics of population distribution.

[0063] Furthermore, the type of disaster is also one of the factors influencing the selection of the first artificial intelligence model.

[0064] Specifically, if a flood occurs in the target area, the services in the near-ground area are usually of a higher urgency. Therefore, the drone satellite base station can prioritize storing the first artificial intelligence model suitable for ensuring high-priority near-ground services. If a fire occurs in the target area, the services in high-rise buildings are usually of a higher urgency. Therefore, the drone satellite base station can prioritize storing the first artificial intelligence model suitable for ensuring emergency services in high-rise areas.

[0065] By combining the disaster types and operational urgency distribution characteristics of the target area, drone satellite base stations can further improve the targeting of selecting and storing at least one primary artificial intelligence model before takeoff.

[0066] Furthermore, to cater to different target cell scenarios and the needs of different terminal devices, the drone satellite base station can pre-store multiple sets of primary artificial intelligence (AI) models. The number of primary AI models stored can be determined based on the onboard storage capacity of the drone satellite base station. That is, when onboard storage capacity allows, the drone satellite base station can store more types of primary AI models to improve the flexibility of subsequent model matching and configuration for different terminal devices and scenarios. When onboard storage capacity is limited, the drone satellite base station can prioritize storing primary AI models that are highly relevant to the current emergency communication task, based on the main scenario characteristics of the target cell.

[0067] S302. After the UAV satellite base station reaches the preset working position, it sends a first message to the first terminal device in the target cell. Correspondingly, the first terminal device receives the first message.

[0068] It should be noted that after the UAV satellite base station reaches its preset working position, it can complete preparatory actions such as stabilizing its aerial position, enabling wireless access, establishing a communication link with the core network, and initializing the system broadcast function. After completing these preparatory actions, the UAV satellite base station can send the first message to the terminal devices in the target cell to initiate the subsequent information interaction process related to the artificial intelligence model's processing capabilities.

[0069] The first message indicates the artificial intelligence model processing capabilities of the drone satellite base station. The first terminal device is any terminal device within the target cell.

[0070] It should be noted that any terminal device located within the target cell and within range capable of receiving messages sent by the UAV satellite base station can be considered a first terminal device. Therefore, the first terminal device can be any terminal device within the target cell, or any terminal device within the target cell that is currently active, in a camped state, in an access state, or capable of receiving system messages.

[0071] By sending a first message to the first terminal device, the drone satellite base station enables the terminal device in the target cell to know that the base station has the corresponding artificial intelligence model processing capability, thus providing the prerequisite for the terminal device to subsequently provide information related to the artificial intelligence model processing capability.

[0072] In practical applications, UAV satellite base stations can send the first message to the first terminal device via broadcast or via a unified downlink notification method targeting terminal devices within the target cell.

[0073] Specifically, the first message can be carried in the form of system broadcast messages, system information, control signaling, or other downlink messages, as long as it enables the first terminal device in the target cell to know the artificial intelligence model processing capability information of the UAV satellite base station.

[0074] For example, drone satellite base stations can send the first message to the first terminal device in the target cell through emergency information notification processes such as the Earthquake and Tsunami Warning System (ETWS).

[0075] In some embodiments, in order to enable as many terminal devices as possible in the target cell to know that the UAV satellite base station has artificial intelligence model processing capabilities, the UAV satellite base station may repeatedly send the first message in the initial stage after arriving at the preset working position.

[0076] In other embodiments, the UAV satellite base station may also determine the number of times the first message is sent, the sending period, and the sending duration based on the reception status, feedback status, or preset sending strategy of the terminal devices in the target cell.

[0077] In this embodiment, after the UAV satellite base station forms wireless network coverage in the target cell, it can proactively initiate an information notification process related to the processing capabilities of the artificial intelligence model to the first terminal device in the target cell, providing a prerequisite for determining the second artificial intelligence model based on the second message sent by the second terminal device, and determining the target configuration information based on the second artificial intelligence model.

[0078] S303, Receive the second message from the second terminal device in response to the first message.

[0079] The second terminal device is any first terminal device that successfully receives the first message and sends the second message back to the UAV satellite base station.

[0080] The second message is used to indicate the processing capabilities of the artificial intelligence model of the second terminal device.

[0081] It should be noted that after successfully receiving the first message, the second terminal device generates a corresponding second message based on the AI ​​model processing capability information of the UAV satellite base station indicated in the first message and sends it to the UAV satellite base station. Thus, a two-way information exchange process can be established between the UAV satellite base station and the second terminal device, based on the AI ​​model processing capabilities.

[0082] In some embodiments, after receiving the first message, the second terminal device can parse the content of the first message and generate artificial intelligence model processing capability information carried in the second message based on its own storage resources, processing capabilities, protocol support capabilities, supported model processing methods, or other capability parameters. After receiving the second message, the drone satellite base station can parse the second message to obtain the artificial intelligence model processing capability information of the second terminal device contained therein.

[0083] The second message is used to provide feedback to the UAV satellite base station on whether the second terminal device has artificial intelligence model processing capabilities, whether the second terminal device supports processing procedures related to the artificial intelligence models stored by the UAV satellite base station, or whether the second terminal device can participate in subsequent configuration matching procedures related to artificial intelligence model processing capabilities. By receiving the second message, the UAV satellite base station can obtain capability information related to artificial intelligence model processing from the second terminal device, thereby providing input basis for subsequently determining the second artificial intelligence model from at least one first artificial intelligence model.

[0084] In practical applications, the second message can be carried in the form of an uplink message sent by the second terminal device to the UAV satellite base station. In different embodiments, the second message can adopt different message carrying formats.

[0085] For example, the second terminal device can send a second message during its access process, or it can send a second message after establishing a corresponding connection with the drone satellite base station.

[0086] In some embodiments, the second terminal device may also send a second message to the drone satellite base station via a dedicated random access code.

[0087] S304. Based on the second message, determine a second artificial intelligence model from at least one first artificial intelligence model.

[0088] It should be noted that the second artificial intelligence model is a model determined from at least one first artificial intelligence model, and the second artificial intelligence model is used to subsequently determine the target configuration information for the second terminal device.

[0089] In this embodiment, the UAV satellite base station filters at least one first artificial intelligence model based on the artificial intelligence model processing capability information of the second terminal device carried in the second message, so as to determine the second artificial intelligence model from at least one first artificial intelligence model.

[0090] S305. Based on the second artificial intelligence model, determine the target configuration information.

[0091] It should be noted that the target configuration information is used to characterize the communication configuration content adopted by the UAV satellite base station when communicating with the second terminal device. By determining the target configuration information, the second artificial intelligence model determined in S304 can be further applied to the actual communication process, thereby establishing the subsequent communication process between the UAV satellite base station and the second terminal device on the basis of the selected second artificial intelligence model.

[0092] The target configuration information includes the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information of the UAV satellite base station for the second terminal device.

[0093] It should be noted that the target configuration information may include only radio resource scheduling configuration information, only channel measurement and reporting configuration information, or both. This application does not impose specific limitations on this.

[0094] Among them, the wireless resource scheduling configuration information is used to characterize the configuration information used by the UAV satellite base station to allocate and schedule wireless resources for the second terminal device.

[0095] Specifically, the wireless resource scheduling configuration information may include resource allocation priority, resource scheduling period, resource block allocation parameters, uplink and downlink resource configuration parameters, scheduling parameters corresponding to different services, or other control information related to wireless resource scheduling. This application does not impose specific limitations on the specific parameter format of the wireless resource scheduling configuration information, as long as it can characterize the relevant configuration used by the UAV satellite base station when scheduling resources for the second terminal device.

[0096] Among them, the channel measurement and reporting configuration information is used to characterize the configuration information used by the UAV satellite base station when performing channel measurement control and measurement result reporting control for the second terminal equipment.

[0097] Specifically, the channel measurement and reporting configuration information may include whether channel measurement is performed, the execution cycle of channel measurement, the measurement object, the measurement accuracy requirements, the reporting cycle of measurement results, the reporting trigger conditions, the scope of reporting content, or other control information related to channel measurement and reporting. This application does not specifically limit the content of the channel measurement and reporting configuration information, as long as it can characterize the relevant configuration used by the UAV satellite base station when performing channel measurement and reporting control for the second terminal device.

[0098] It should be noted that the target configuration information is not pre-set or uniformly adopted across all terminal devices. Instead, it is a configuration result determined by the UAV satellite base station based on the determined second artificial intelligence model, combined with the processing capability information of the current second terminal device's artificial intelligence model, the characteristics of the target cell scene, and / or the current communication task requirements.

[0099] In practical applications, drone satellite base stations can determine different target configuration information for different second artificial intelligence models.

[0100] In this embodiment, different second terminal devices can correspond to different target configuration information. The UAV satellite base station can determine different target configuration information based on the artificial intelligence model processing capability information of different second terminal devices and the determined second artificial intelligence model, thereby realizing differentiated communication control for different second terminal devices. This avoids using a uniform and fixed communication configuration for all second terminal devices, thus improving the flexibility of the communication process.

[0101] S306. Based on the target configuration information, communicate with the second terminal device.

[0102] Communication between a drone satellite base station and a second terminal device refers to the process of data transmission and control interaction between the drone satellite base station and the second terminal device.

[0103] When the UAV satellite base station performs wireless resource allocation, scheduling control, channel measurement control, and measurement result reporting control, it can execute according to the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information contained in the target configuration information, thereby making the communication process correspond to the second artificial intelligence model.

[0104] In some embodiments, when the target configuration information includes wireless resource scheduling configuration information, the UAV satellite base station can perform wireless resource allocation and scheduling control on the second terminal device based on the wireless resource scheduling configuration information, for example, allocating corresponding wireless resources to the second terminal device according to preset resource allocation priority, scheduling period or resource configuration parameters.

[0105] In other embodiments, when the target configuration information includes channel measurement and reporting configuration information, the UAV satellite base station can control the second terminal device to perform corresponding channel measurements and report measurement results based on the channel measurement and reporting configuration information. For example, it can control whether the second terminal device performs channel measurements, at what period to perform the measurements, and in what way to report the measurement results.

[0106] In a further embodiment, when the target configuration information includes both wireless resource scheduling configuration information and channel measurement and reporting configuration information, the UAV satellite base station can simultaneously perform resource scheduling control and channel measurement and reporting control on the second terminal device based on both types of configuration information.

[0107] In actual communication, the UAV satellite base station can also dynamically adjust the target configuration information according to the operating status during the communication process. For example, when the service load in the target cell changes or the communication status of the second terminal device changes, the UAV satellite base station can update the target configuration information while keeping the second artificial intelligence model unchanged, or re-execute S304 and S305 to determine the new second artificial intelligence model and target configuration information. This application does not specify the dynamic adjustment method of the target configuration information.

[0108] This application provides an emergency communication method for a UAV satellite base station. Before takeoff, the UAV satellite base station acquires and stores multiple first artificial intelligence models related to pre-set information of the target cell, enabling it to pre-select models for different target cell scenarios. After reaching a preset working position, the UAV satellite base station sends a first message to a first terminal device within the target cell and receives a second message from a second terminal device responding to the first message. The second terminal device is the first terminal device that successfully received the first message, thus acquiring its artificial intelligence model processing capability information. Further, based on the second message, a second artificial intelligence model adapted to the processing capability of the second terminal device is determined from at least one first artificial intelligence model. Based on this, target configuration information is determined based on the second artificial intelligence model. The target configuration information includes wireless resource scheduling configuration information and / or channel measurement and reporting configuration information for the second terminal device from the UAV satellite base station. Therefore, this application can communicate with the second terminal device using matching target configuration information based on at least one pre-stored first artificial intelligence model and the artificial intelligence model processing capability information fed back by the second terminal device, thereby improving the wireless resource scheduling efficiency of the UAV satellite base station under conditions of limited backhaul resources and reducing unnecessary channel measurement and reporting and the resulting signaling overhead.

[0109] In the above embodiments, the UAV satellite base station needs to send a first message to the first terminal device in the target cell. The content of one such first message will be described in detail below.

[0110] In one possible embodiment, the first message includes a first parameter, which is used to indicate whether the drone satellite base station has artificial intelligence model processing capabilities.

[0111] The first parameter can be used to explicitly indicate to the first terminal device in the target cell whether the drone satellite base station is currently equipped with an artificial intelligence model, so that the first terminal device can decide whether to participate in the subsequent information interaction process related to the processing capabilities of the artificial intelligence model based on the first message.

[0112] In some embodiments, the first parameter can be a Boolean variable, such as "AI exist". When the first parameter is TRUE, it indicates that the drone satellite base station is equipped with an artificial intelligence model; when the first parameter is FALSE, it indicates that the drone satellite base station is not equipped with an artificial intelligence model. In this way, the status of the drone satellite base station's artificial intelligence model processing capability can be transmitted to the first terminal device with low signaling overhead.

[0113] In other embodiments, the first parameter can also indicate whether the drone satellite base station has artificial intelligence model processing capabilities by its presence or absence.

[0114] Specifically, when the first message contains the first parameter, it indicates that the drone satellite base station is equipped with an artificial intelligence model; when the first message does not contain the first parameter, it indicates that the drone satellite base station is not equipped with an artificial intelligence model. In this way, the processing capabilities of the artificial intelligence model can be indicated without adding extra parameter value fields.

[0115] In this embodiment of the application, by setting a first parameter in the first message to indicate whether the UAV satellite base station has artificial intelligence model processing capability, the terminal device in the target cell can promptly know whether the UAV satellite base station has artificial intelligence model processing capability after receiving the first message. This provides a basis for the second terminal device to subsequently provide information related to artificial intelligence model processing capability, thereby improving the clarity of information interaction between the UAV satellite base station and the terminal device regarding artificial intelligence model processing capability.

[0116] This application does not specifically limit the form of the first parameter. As long as it can be used to indicate whether the UAV satellite base station has artificial intelligence model processing capabilities, it will fall within the protection scope of this application.

[0117] In the above embodiment, the UAV satellite base station needs to send a first message to the first terminal device in the target cell. Next, the content of another type of first message will be described in detail.

[0118] In another embodiment, the first message includes type information or identification information of at least one first artificial intelligence model.

[0119] Among them, type information is used to characterize the model category to which the artificial intelligence model belongs, and identification information is used to characterize the unique identifier corresponding to the artificial intelligence model.

[0120] It should be noted that the type information in the first message is used to further indicate to the first terminal device in the target cell the specific category of at least one first artificial intelligence model stored by the UAV satellite base station, and the identification information in the first message is used to further indicate to the first terminal device in the target cell the specific identity of at least one first artificial intelligence model stored by the UAV satellite base station, so that the first terminal device, based on knowing that the UAV satellite base station has the ability to process artificial intelligence models, can further determine whether it has stored an artificial intelligence model corresponding to at least one first artificial intelligence model.

[0121] In some embodiments, the type information or identification information of the first artificial intelligence model may be predefined by the operator or by the communication protocol. This application does not specifically limit the specific encoding form, field length, or value acquisition method of the type information or identification information of the first artificial intelligence model. As long as the first terminal device can identify the type or specific identification of the artificial intelligence model stored by the UAV satellite base station, it falls within the protection scope of this application.

[0122] After receiving the first message, the first terminal device determines whether it has stored an artificial intelligence model of the same type or an artificial intelligence model with the same identifier. When the first terminal device determines that it has stored an artificial intelligence model corresponding to at least one first artificial intelligence model, the first terminal device can provide corresponding information in a subsequent second message sent to the UAV satellite base station, so that the UAV satellite base station can determine the communication configuration or scheduling strategy for the first terminal device (second terminal device) based on the second message.

[0123] This application embodiment enables the second terminal device to further identify the type or specific identifier of the artificial intelligence model stored by the UAV satellite base station by carrying at least one type or identifier of the first artificial intelligence model in the first message, and to determine whether it has stored the corresponding artificial intelligence model. This provides a basis for the second terminal device to feed back more specific artificial intelligence model-related information to the UAV satellite base station, which is beneficial for the UAV satellite base station to determine the communication configuration for the second terminal device based on the second message fed back by the second terminal device.

[0124] In this embodiment, the first message may include only the first parameter, or only the type information or identification information of at least one first artificial intelligence model, or it may include both the first parameter and the type information or identification information of at least one first artificial intelligence model. This embodiment does not specifically limit this.

[0125] In the above embodiment, the UAV satellite base station needs to send a first message to the first terminal device in the target cell. The other contents carried by the first message will be described in detail below.

[0126] In one possible embodiment, the first message further includes feedback request information, which instructs the second terminal device to send target information back to the UAV satellite base station.

[0127] It should be noted that the feedback request information is used to indicate whether the terminal device in the target cell needs to provide information feedback to the drone satellite base station, and if feedback is required, the type of information content that the terminal device needs to provide.

[0128] The target information includes whether the second terminal device supports at least one of the following: an artificial intelligence model, a third artificial intelligence model, and a fourth artificial intelligence model.

[0129] The third artificial intelligence model is the first artificial intelligence model supported by the second terminal device, and the fourth artificial intelligence model is the artificial intelligence model recommended to be used by the second terminal device.

[0130] It should be noted that the feedback request information can instruct the second terminal device to provide feedback on whether it supports an artificial intelligence model; it can also instruct the second terminal device to provide feedback on whether it supports an artificial intelligence model, and if the second terminal device supports an artificial intelligence model, a third artificial intelligence model that is supported; it can also instruct the second terminal device to provide feedback on whether it supports an artificial intelligence model, and if the second terminal device supports an artificial intelligence model, a fourth artificial intelligence model that is suggested to be used; it can also instruct the second terminal device to provide feedback on whether it supports an artificial intelligence model, and if the second terminal device supports an artificial intelligence model, a third artificial intelligence model that is supported and a suggested fourth artificial intelligence model.

[0131] This embodiment does not specifically limit the specific representation of the feedback request information or the specific field format of the target information. As long as it can be used to instruct the terminal device to provide feedback information related to the artificial intelligence model, it will fall within the protection scope of this application.

[0132] By carrying a third artificial intelligence model in the target information, the UAV satellite base station can directly know the compatibility relationship between the second terminal device and the first artificial intelligence model stored by the UAV satellite base station. In the subsequent selection process of the second artificial intelligence model, the first artificial intelligence model supported by the second terminal device is given priority. This avoids the UAV satellite base station selecting the first artificial intelligence model that the second terminal device cannot support, reduces the uncertainty in the model matching process, and helps to reduce the complexity of the subsequent communication configuration process.

[0133] Based on its own usage scenarios, business needs, or historical usage experience, the second terminal device has a certain ability to judge suitable artificial intelligence models. By carrying a fourth artificial intelligence model in the target information, it can feed back the fourth artificial intelligence model suggested by the second terminal device to the drone satellite base station, providing the drone satellite base station with additional reference information. The drone satellite base station can combine the information of the fourth artificial intelligence model to match and filter at least one first artificial intelligence model, thereby improving the flexibility and adaptability of model selection.

[0134] This application embodiment sets feedback request information in the first message, enabling the UAV satellite base station to actively instruct the second terminal device whether to provide feedback and the target information content to be fed back. This allows the second terminal device to provide targeted feedback to the UAV satellite base station on whether it supports an artificial intelligence model, the first supported artificial intelligence model, or the fourth recommended artificial intelligence model. This provides a basis for the UAV satellite base station to determine the second artificial intelligence model based on the target information fed back by the second terminal device, which helps to improve the targeting of the UAV satellite base station in model selection and communication configuration determination.

[0135] In the above embodiments, the target information may include a fourth artificial intelligence model. Next, the limitations when the target information includes a fourth artificial intelligence model will be described in detail.

[0136] In one possible embodiment, when the target information includes a fourth artificial intelligence model, the total number of fourth artificial intelligence models fed back by the second terminal device to the drone satellite base station is less than a first preset number.

[0137] When the second terminal device receives the first message and generates target information based on the feedback request information in the first message, the second terminal device can provide feedback on the fourth artificial intelligence model it suggests to use. In this case, in order to avoid the second terminal device providing too many fourth artificial intelligence models, which would lead to redundant target information, increased signaling overhead, or an overly complex subsequent model selection process, it is necessary to limit the total number of fourth artificial intelligence models provided by the second terminal device.

[0138] The first preset number can be pre-set by the drone satellite base station, or it can be pre-specified by the operator, control center, or protocol rules.

[0139] This application does not specify the exact value of the first preset quantity, which can be set according to the processing capacity of the UAV satellite base station, the communication load of the target area, the onboard storage resources, and the complexity requirements of subsequent model screening.

[0140] For example, the first preset quantity is 10.

[0141] By limiting the total number of feedback from the fourth artificial intelligence model, the second terminal device can have a clear quantity boundary when providing feedback suggestions, thereby avoiding the second terminal device reporting too many fourth artificial intelligence models at once. On the one hand, this can control the scale of target information carried in the second message, and on the other hand, it is also beneficial for the UAV satellite base station to perform subsequent matching, filtering and processing of the fourth artificial intelligence model after receiving the second message.

[0142] In practical applications, when the number of AI models suggested by the second terminal device exceeds the first preset number, the second terminal device can select a portion of the AI ​​models that are less than the first preset number as the fourth AI model for feedback, according to preset priority, matching degree, historical usage, or other selection rules.

[0143] This application embodiment limits the total number of fourth artificial intelligence models fed back by the second terminal device, giving the second terminal device a clear quantity boundary when feeding back the fourth artificial intelligence models. This avoids increased signaling overhead caused by excessive feedback information and increased complexity of subsequent model selection by the UAV satellite base station. It is beneficial to improve the processing efficiency of UAV satellite base station in model matching and model selection while ensuring the effectiveness of the model suggestion information of the second terminal device.

[0144] In the above embodiments, the target information may include a fourth artificial intelligence model. Next, when the target information includes a fourth artificial intelligence model, the specific content included in the second message will be described in detail.

[0145] In one possible embodiment, the second message includes target information. When the target information includes a fourth artificial intelligence model, the second message also includes matching information, which includes the degree of matching between the fourth artificial intelligence model and each of the first artificial intelligence models.

[0146] When the target information includes a fourth artificial intelligence model, it indicates that the second terminal device not only provides feedback on whether it supports an artificial intelligence model or the first artificial intelligence model it supports (the third artificial intelligence model), but also provides feedback on the artificial intelligence model it suggests to use (the fourth artificial intelligence model). In this case, to enable the drone satellite base station to further determine the degree of correlation between the fourth artificial intelligence model and at least one pre-stored first artificial intelligence model, the second message may further include matching information.

[0147] It should be noted that while the second terminal device provides feedback on the fourth artificial intelligence model, it also provides feedback on the degree of matching between the fourth artificial intelligence model and each of the first artificial intelligence models, so that the drone satellite base station can identify the first artificial intelligence model with the highest degree of correlation with the fourth artificial intelligence model among at least one first artificial intelligence model.

[0148] Among them, the matching degree is used to characterize the degree of similarity between the fourth artificial intelligence model and each of the first artificial intelligence models in terms of model type, model function, model purpose, model support capability, or other dimensions.

[0149] In some embodiments, the second terminal device may determine the matching degree between the fourth artificial intelligence model and each of the first artificial intelligence models based on the model information, model type information, model identification information, preset mapping relationship or other model association rules stored locally, and send the matching degree as matching information in the second message to the UAV satellite base station.

[0150] This application does not impose specific limitations on the calculation method, representation form, and value range of the matching degree, as long as it can characterize the degree of matching between the fourth artificial intelligence model and each of the first artificial intelligence models.

[0151] In this embodiment of the application, by carrying matching information in the second message, the UAV satellite base station, upon receiving the second message, can not only learn the fourth artificial intelligence model suggested by the second terminal device, but also further learn the matching relationship between the fourth artificial intelligence model and at least one first artificial intelligence model, thereby providing a basis for subsequently determining the second artificial intelligence model from at least one first artificial intelligence model.

[0152] In the above embodiments, the drone satellite base station needs to determine a second artificial intelligence model from at least one first artificial intelligence model based on the second message. The specific process by which the drone satellite base station determines the second artificial intelligence model from at least one first artificial intelligence model based on the second message will be described in detail below.

[0153] Figure 4 This is a flowchart illustrating another emergency communication method for a UAV satellite base station provided in an embodiment of this application. Figure 4 As shown, in one possible embodiment, the method steps shown in S304 can be implemented by S3041 to S3045, which are described in detail below.

[0154] S3041. Determine whether the target information includes a third artificial intelligence model.

[0155] After the drone satellite base station receives the second message sent by the second terminal device, it parses the target information carried in the second message to determine whether the target information includes the third artificial intelligence model.

[0156] If the target information includes a third artificial intelligence model, it means that the second terminal device has explicitly provided feedback on the first artificial intelligence model it supports. In this case, the UAV satellite base station executes the method steps shown in S3042. If the target information does not include a third artificial intelligence model, it means that the second terminal device has not directly provided feedback on the first artificial intelligence model it supports. In this case, the UAV satellite base station executes the method steps shown in S3043.

[0157] S3042. The third artificial intelligence model is determined as the second artificial intelligence model.

[0158] When the target information includes a third artificial intelligence model, the UAV satellite base station no longer needs to perform additional screening or matching on at least one first artificial intelligence model. It can directly adopt the third artificial intelligence model as the second artificial intelligence model for determining the target configuration information, thereby improving the directness of the second artificial intelligence model determination process and providing a clear model basis for the subsequent determination of target configuration information.

[0159] S3043. Determine whether the target information includes the fourth artificial intelligence model.

[0160] If the target information does not include a third artificial intelligence model, the drone satellite base station can further evaluate the target information to determine whether a fourth artificial intelligence model is included in the target information.

[0161] If the target information includes a fourth artificial intelligence model, it means that although the second terminal device did not explicitly provide feedback on the first artificial intelligence model (third artificial intelligence model) it supports, it provided its suggested fourth artificial intelligence model. In this case, the UAV satellite base station executes the method steps shown in S3044. If the target information does not include a fourth artificial intelligence model, it means that the second terminal device neither provides feedback on the first artificial intelligence model it supports nor provides feedback on the suggested fourth artificial intelligence model. In this case, the UAV satellite base station executes the method steps shown in S3045.

[0162] S3044. Based on the matching information, the first artificial intelligence model with the highest matching degree with the fourth artificial intelligence model is determined as the second artificial intelligence model.

[0163] When the target information includes a fourth AI model, the second message also includes matching information between the fourth AI model and each of the first AI models. Therefore, the UAV satellite base station can compare the matching degree between the fourth AI model and at least one first AI model based on the matching information, and determine the first AI model with the highest matching degree among the at least one first AI model as the second AI model. This allows the UAV satellite base station to select the second AI model based on the suggested model information provided by the second terminal device, even when the second terminal device does not directly support a specific first AI model.

[0164] S3045. Based on the preset information of the target cell, determine a second artificial intelligence model from at least one first artificial intelligence model.

[0165] When the target information does not include either the third artificial intelligence model or the fourth artificial intelligence model, the UAV satellite base station reverts to the model selection method based on the target cell's pre-set information. Based on the target cell's regional type information, population distribution information, service area distribution information, and / or service time information involved in S301, a second artificial intelligence model is determined from at least one first artificial intelligence model to realize the determination of subsequent target configuration information and ensure the continuity of the communication process.

[0166] In some embodiments, the drone satellite base station may also perform matching and scoring on at least one first artificial intelligence model based on the target cell’s regional type information, population distribution information, service area distribution information and / or service time information, and determine the first artificial intelligence model with the highest matching score as the second artificial intelligence model.

[0167] This application embodiment improves the flexibility and completeness of the second artificial intelligence model selection process by employing multiple model determination methods—direct determination, selection based on matching information, or selection based on preset information of the target cell—depending on whether the target information fed back by the second terminal device includes a third or fourth artificial intelligence model during the determination process of the second artificial intelligence model. This enables the UAV satellite base station to complete the determination of the second artificial intelligence model under different information completeness levels.

[0168] In the above embodiment, the UAV satellite base station needs to send a first message to a first terminal device in the target cell. Next, the method steps that may be performed after the UAV satellite base station sends the first message to the first terminal device in the target cell will be described in detail.

[0169] In one possible embodiment, after the method step shown in S302, the method further includes Sa.

[0170] Sa: Stop sending the first message if the preset stop conditions are met.

[0171] In practical use, to ensure that more terminal devices within the target cell can receive the first message, the UAV satellite base station can repeatedly transmit the first message within a certain time period. However, if the first message is transmitted continuously for too long, or if a sufficient number of terminal devices have already successfully received the first message, continuing to transmit the first message may lead to unnecessary signaling overhead. Therefore, in this embodiment, the UAV satellite base station can stop transmitting the first message when a preset stopping condition is met.

[0172] The preset stopping conditions include at least one of the following: the sending duration of the first message reaches the preset sending duration; the number of second terminal devices reaches the second preset number.

[0173] It should be noted that the preset transmission duration can be pre-set by the UAV satellite base station, or it can be pre-defined by the operator, control center, or protocol rules. This application does not make any specific restrictions on this.

[0174] For example, the preset sending time is 1 minute.

[0175] When the duration of continuous transmission of the first message by the drone satellite base station has reached the preset transmission time, the drone satellite base station can stop transmitting the first message even if some terminal devices in the target cell have not yet responded with the second message.

[0176] It should be noted that the second preset quantity can be set according to the number of terminal devices in the target cell, the processing capacity of the UAV satellite base station, the emergency communication needs of the target area, or other conditions. This application does not make specific limitations in this regard.

[0177] For example, the second preset quantity is 100.

[0178] When the number of second terminal devices reaches a second preset number, it indicates that a sufficient number of terminal devices have completed information exchange with the drone satellite base station regarding the processing capabilities of the artificial intelligence model. In this case, the drone satellite base station can also stop sending the first message.

[0179] This application embodiment sets a preset stop condition after sending the first message, and stops sending the first message when the preset stop condition is met. This allows the UAV satellite base station to avoid continuous retransmission of the first message while ensuring that the terminal devices in the target cell fully receive the first message. This reduces unnecessary signaling overhead and allows more system resources to be used for subsequent second message reception and model selection processing.

[0180] Figure 5 This is a flowchart illustrating another emergency communication method for a UAV satellite base station provided in an embodiment of this application. Figure 5 As shown, in one possible embodiment, the method further includes S501 to S504, which are described in detail below.

[0181] S501. Send a model update request to the core network control element. The model update request is used to request the update of at least one first artificial intelligence model.

[0182] It should be noted that during emergency communication missions performed by UAV satellite base stations, changes in service demands within the target cell, the distribution of terminal devices, and the communication environment may render at least one pre-stored initial artificial intelligence model no longer fully applicable to the current scenario. In such cases, the UAV satellite base station can send a model update request to the core network control element to obtain a new artificial intelligence model.

[0183] Specifically, the model update request can be used to instruct the UAV satellite base station to update at least one stored first artificial intelligence model. The model update request may include the identification information of the UAV satellite base station, relevant information of the current target cell, information of the currently used artificial intelligence model, or other relevant information used to assist in the model update, which is not specifically limited in this application.

[0184] By sending a model update request, the UAV satellite base station can proactively trigger the model update process with the core network control elements.

[0185] S502, Receive the response message sent by the core network control element based on the model update request. The response message includes multiple updated first artificial intelligence models.

[0186] It should be noted that after the core network control element receives the model update request, it returns a response message to the UAV satellite base station based on the target area where the UAV satellite base station is currently located, the network operation status, and the model management strategy. The response message includes multiple updated first artificial intelligence models.

[0187] Specifically, the updated first artificial intelligence model can be an optimized version of the original first artificial intelligence model, or it can be a model that is reselected or generated for the current target cell scenario.

[0188] This application does not impose specific limitations on the source, generation method, or specific form of the updated first artificial intelligence model, as long as it can be used to replace the original first artificial intelligence model stored in the drone satellite base station.

[0189] S503. Based on the response message, update at least one first artificial intelligence model to obtain multiple updated first artificial intelligence models.

[0190] It should be noted that after the drone satellite base station receives the response message, it processes the multiple updated first artificial intelligence models carried in the response message to complete the update of the original first artificial intelligence model.

[0191] Specifically, the drone satellite base station can write the updated first artificial intelligence model into the onboard memory, and replace, delete or retain the original first artificial intelligence model as needed, thereby obtaining multiple updated first artificial intelligence models.

[0192] In some embodiments, the drone satellite base station may adopt a full update approach, that is, replace all the original first artificial intelligence models with at least one updated first artificial intelligence model.

[0193] In other embodiments, the drone satellite base station may also adopt an incremental update method, that is, only update part of the first artificial intelligence model, while retaining the unupdated model.

[0194] S504. Determine at least one first artificial intelligence model from among the multiple updated first artificial intelligence models, and repeat the steps shown in S302.

[0195] After completing the model update, the drone satellite base station can re-execute the steps shown in S302, that is, resend the first message to the terminal devices in the target cell to inform the terminal devices of the current processing capability information of the drone satellite base station's artificial intelligence model. This allows the terminal devices in the target cell to re-participate in subsequent information interaction processes based on multiple updated first artificial intelligence models.

[0196] This application embodiment introduces a model update mechanism during emergency communication by a UAV satellite base station. This enables the UAV satellite base station to dynamically update at least one pre-stored first artificial intelligence model according to changes in the current communication environment and service requirements. After the update, the interaction process with the terminal device is re-executed, which helps to improve the UAV satellite base station's model adaptability and communication assurance capabilities in dynamic environments.

[0197] In addition, after the drone satellite base station ends its emergency communication mission and returns to the ground, ground maintenance personnel can manually update at least one primary artificial intelligence model.

[0198] Figure 6 This is a schematic diagram of the structure of a UAV satellite base station provided in an embodiment of this application. Figure 6 As shown, the UAV satellite base station 600 provided in this embodiment can exist independently and is used to implement the operations corresponding to the UAV satellite base station in the above method embodiment.

[0199] The UAV satellite base station 600 may include a transceiver module 601 and a processing module 602. The processing module 602 is used for data processing, and the transceiver module 601 can implement corresponding communication functions. The transceiver module 601 may also be referred to as a communication interface or a communication unit.

[0200] Optionally, the UAV satellite base station 600 may further include a storage unit, which can be used to store instructions and / or data. The processing module 602 can read the instructions and / or data in the storage unit so that the UAV satellite base station 600 can implement the steps implemented by the UAV satellite base station in the aforementioned method embodiments.

[0201] The transceiver module 601 is used to perform the receiving-related operations of the UAV satellite base station in the method embodiment above, and the processing module 602 is used to perform the processing-related operations of the UAV satellite base station in the method embodiment above.

[0202] Optionally, the transceiver module 601 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0203] It should be noted that the UAV satellite base station 600 may include a transmitting module but not a receiving module. Alternatively, the UAV satellite base station 600 may include a receiving module but not a transmitting module. This depends on whether the above-described scheme executed by the UAV satellite base station 600 includes both transmitting and receiving actions.

[0204] As an example, the drone satellite base station 600 is used to perform the aforementioned... Figure 3 The actions performed by the drone satellite base station in the illustrated embodiment.

[0205] The UAV satellite base station 600 may include a transceiver module 601 and a processing module 602.

[0206] The processing module 602 is used to acquire and store at least one first artificial intelligence model before the UAV takes off from the satellite base station. The first artificial intelligence model is related to the preset information of the target cell. The preset information includes the regional type information, population distribution information, service area distribution information and / or service time information of the target cell.

[0207] The transceiver module 601 is used to send a first message to a first terminal device in the target cell after the UAV satellite base station reaches the preset working position. The first message is used to indicate the artificial intelligence model processing capability information of the UAV satellite base station. The first terminal device can be any terminal device in the target cell.

[0208] The transceiver module 601 is further configured to receive a second message sent by the second terminal device in response to the first message, the second message being used to indicate the artificial intelligence model processing capability information of the second terminal device; wherein, the second terminal device is the first terminal device that successfully received the first message.

[0209] The processing module 602 is further configured to determine a second artificial intelligence model from the at least one first artificial intelligence model based on the second message.

[0210] The processing module 602 is further configured to determine target configuration information based on the second artificial intelligence model; wherein the target configuration information includes the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information of the UAV satellite base station for the second terminal device.

[0211] The processing module 602 is also used to communicate with the second terminal device based on the target configuration information.

[0212] It should be understood that the corresponding processes performed by each module have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0213] The processing module 602 in the preceding embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver module 601 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 601 can also be referred to as a communication unit or communication interface. The storage unit can be implemented by at least one memory.

[0214] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 700 provided in this embodiment includes a memory 701 and a processor 702.

[0215] The memory 701 can be a separate physical unit, connected to the processor 702 via a bus 703. Alternatively, the memory 701 and processor 702 can be integrated and implemented in hardware. The memory 701 stores program instructions, which the processor 702 calls to execute the operations performed by the UAV satellite base station in any of the above method embodiments.

[0216] Optionally, when some or all of the methods in the above embodiments are implemented by software, the electronic device 700 may also include only the processor 702. A memory 701 for storing programs is located outside the electronic device 700, and the processor 702 is connected to the memory via circuits / wires to read and execute the programs stored in the memory. The processor 702 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP. The processor 702 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0217] The memory 701 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory may also include a combination of the above types of memory.

[0218] For example, this application provides a chip including: an interface circuit and a logic circuit. The interface circuit is used to receive signals from other chips outside the chip and transmit them to the logic circuit, or to send signals from the logic circuit to other chips outside the chip. The logic circuit is used to perform the operations performed by the UAV satellite base station in the above method embodiments.

[0219] For example, this application provides a computer-readable storage medium storing computer program instructions thereon, which are executed by the processor of an electronic device to cause the electronic device to perform the operations performed by the UAV satellite base station in the above method embodiments.

[0220] For example, this application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the operations performed by the UAV satellite base station in the above method embodiments.

[0221] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An emergency communication method for unmanned aerial vehicle (UAV) satellite base stations, characterized in that, The method includes: Before the drone takes off from the satellite base station, at least one first artificial intelligence model is acquired and stored. The first artificial intelligence model is related to the preset information of the target cell. The preset information includes the regional type information, population distribution information, service area distribution information and / or service time information of the target cell. After the UAV satellite base station reaches the preset working position, it sends a first message to a first terminal device in the target cell. The first message is used to indicate the artificial intelligence model processing capability information of the UAV satellite base station; wherein, the first terminal device is any terminal device in the target cell. The second terminal device receives a second message in response to the first message, the second message being used to indicate the artificial intelligence model processing capability information of the second terminal device; wherein, the second terminal device is any of the first terminal devices that successfully received the first message and fed back the second message to the UAV satellite base station; Based on the second message, a second artificial intelligence model is determined from the at least one first artificial intelligence model; Based on the second artificial intelligence model, target configuration information is determined; wherein, the target configuration information includes the wireless resource scheduling configuration information and / or channel measurement and reporting configuration information of the UAV satellite base station for the second terminal device; Based on the target configuration information, communication is established with the second terminal device.

2. The method according to claim 1, characterized in that, The first message includes a first parameter, which indicates whether the UAV satellite base station has artificial intelligence model processing capabilities; and / or, The first message includes type information or identification information of the at least one first artificial intelligence model.

3. The method according to claim 2, characterized in that, The first message also includes feedback request information, which is used to instruct the second terminal device to send target information back to the UAV satellite base station; The target information includes whether the second terminal device supports at least one of an artificial intelligence model, a third artificial intelligence model, and a fourth artificial intelligence model; the third artificial intelligence model is the first artificial intelligence model supported by the second terminal device, and the fourth artificial intelligence model is the artificial intelligence model recommended by the second terminal device.

4. The method according to claim 3, characterized in that, When the target information includes the fourth artificial intelligence model, the total number of the fourth artificial intelligence models fed back by the second terminal device to the UAV satellite base station is less than the first preset number.

5. The method according to claim 3, characterized in that, The second message includes the target information; When the target information includes the fourth artificial intelligence model, the second message also includes matching information, which includes the matching degree between the fourth artificial intelligence model and each of the first artificial intelligence models.

6. The method according to claim 5, characterized in that, The step of determining the second artificial intelligence model from the at least one first artificial intelligence model based on the second message includes: When the target information includes the third artificial intelligence model, the third artificial intelligence model is identified as the second artificial intelligence model; When the target information includes the fourth artificial intelligence model and the target information does not include the third artificial intelligence model, based on the matching information, the first artificial intelligence model with the highest matching degree with the fourth artificial intelligence model is determined as the second artificial intelligence model.

7. The method according to claim 1, characterized in that, After sending the first message to the first terminal device in the target cell, the method further includes: The first message is stopped from being sent if a preset stopping condition is met. The preset stop condition includes at least one of the following: The first message has been sent for a preset duration. The number of the second terminal devices reaches the second preset number.

8. The method according to claim 1, characterized in that, The method further includes: Send a model update request to the core network control element, wherein the model update request is used to request an update of the at least one first artificial intelligence model; Receive a response message sent by the core network control element based on the model update request, the response message including multiple updated first artificial intelligence models; Based on the response message, the at least one first artificial intelligence model is updated to obtain multiple updated first artificial intelligence models; The multiple updated first artificial intelligence models are determined as at least one first artificial intelligence model, and the step of sending the first message to the first terminal device in the target cell is repeated.

9. A satellite base station for unmanned aerial vehicles (UAVs), characterized in that, include: Memory and at least one processor; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method as described in any one of claims 1 to 8.

10. An emergency communication system, characterized in that, Including the unmanned aerial vehicle (UAV) satellite base station as described in claim 9.

Images