Method and apparatus for sharing knowledge

Abstract

Knowledge sharing methods and apparatuses are disclosed. Prior art does not consider unique characteristics of real world, such as existence of massive mobile participating clients covering large geographical areas, when designing appropriate knowledge sharing algorithms. In the present application, the real world is divided into at least one area, and a terminal can select a target area from the at least one area. The terminal always knows its own status, so the target area is always a suitable area for the terminal, and sharing knowledge in the suitable area will improve the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

Description

Technical Field

[0001] This application relates to the field of machine learning technology, and in particular to knowledge sharing methods and apparatus. Background Technology

[0002] Machine learning (ML) is a branch of artificial intelligence (AI) that focuses on learning from data in a way similar to human learning. Federated learning (FL) is a form of knowledge-sharing in machine learning that allows a group of participants to collaboratively train a model without sharing their private data. It addresses the fundamental challenges of data privacy and ownership.

[0003] In federated learning, each client trains its model locally using local data and uploads the discrepancies of its trained local model to another client (e.g., a service device). The service device then performs federated updates on the uploaded discrepancies of each client's trained local model to generate a new central model, which is then sent to the client. The client trains its model locally again based on the new model and uploads the trained models from multiple batches to the service device. After several repetitions of this process, the service device brings the central model to convergence, indicating that the federated learning is complete.

[0004] However, existing technologies do not take into account the unique characteristics of the real world when designing appropriate knowledge-sharing algorithms, such as the existence of a large number of mobile participating clients covering a large geographical area. Summary of the Invention

[0005] This application provides knowledge-sharing methods, apparatus, systems, computer-readable storage media, and computer program products to improve the efficiency of knowledge sharing.

[0006] In a first aspect, embodiments of this application provide a knowledge-sharing method, wherein the implementer of the method (i.e., a first device) may be a terminal or a chip applied to a terminal. In the following description, a terminal is an example of the first device and not a limitation thereof. The method includes: receiving first information, wherein the first information indicates at least one region for knowledge sharing; determining a target region from the at least one region; and initiating first knowledge sharing when the first device is located within the target region.

[0007] In this implementation, the real world is divided into at least one region, and the terminal can select a target region from these regions. Since the terminal is always aware of its own state, the target region is always a suitable region for it, and sharing knowledge within this suitable region improves the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0008] In an alternative implementation of the first aspect, determining the target region from the at least one region includes: determining the target region from the at least one region based on the state of the first device and / or the state of the target region.

[0009] For example, the state of the first device includes battery level; if the terminal is in low-battery mode, it can select a small area as the target area. Similarly, the state of the target area includes a knowledge-sharing format; if the format of the area matches the terminal's capabilities, the terminal can select that area as the target area. Determining the target area based on the state of the first device and / or the state of the target area will make the target area more suitable for the terminal's current conditions.

[0010] In an optional implementation of the first aspect, the state of the first device includes at least one of the following: storage resources, computing resources, data resources, communication resources, power, position relative to the target area, position relative to the charging area, and movement state; the state of the target area includes at least one of the following: knowledge sharing form, amount of data related to knowledge sharing, data type related to knowledge sharing, security requirements, and physical structure of the target area.

[0011] In one alternative implementation of the first aspect, initiating the first knowledge sharing includes: sending the first knowledge.

[0012] Sending the first knowledge refers to sending information about the first knowledge sharing, such as training data and / or a trained model of the first knowledge sharing. The terminal can send the first knowledge to other devices and receive knowledge from other devices; alternatively, the terminal can also send the first knowledge only to other devices. By sending the first knowledge, terminals with a large amount of knowledge to be shared can choose to pass through areas with less knowledge and can sell their own knowledge to devices within those areas. Therefore, the terminal can fully leverage its advantages. Furthermore, this also has advantages for navigation systems. By recommending terminals with a large amount of knowledge to pass through areas with less knowledge, a more balanced knowledge map will be created, which will help balance traffic on different routes.

[0013] In an optional implementation of the first aspect, the method further includes: receiving second knowledge when the first device is within the target area; and determining the first knowledge by learning the second knowledge.

[0014] By receiving the second knowledge, the terminal can determine the first knowledge based on the second knowledge, and then the terminal can send the first knowledge to improve the global model.

[0015] In one alternative implementation of the first aspect, initiating the first knowledge sharing includes: receiving third knowledge.

[0016] By receiving third knowledge, the terminal can learn the third knowledge to improve its own model and / or global model.

[0017] In an alternative implementation of the first aspect, the method further includes: receiving third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0018] Based on the type of the first knowledge sharing, the terminal executes the first knowledge sharing as instructed by the second device, enabling the second device to centrally schedule the knowledge sharing to ensure fairness to all participants. The order of the first knowledge sharing can be either the order in which the first knowledge sharing is started or the order in which the first knowledge sharing is stopped, thus the terminal can execute the first knowledge sharing according to the actual situation.

[0019] In an alternative implementation of the first aspect, the method further includes: sending fourth information, wherein the fourth information is used to acquire one or more knowledge-sharing regions on the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing regions on the trajectory of the first device.

[0020] For example, the terminal sends the fourth information indicating its own predicted trajectory, enabling the terminal to acquire one or more knowledge-sharing regions related to itself. Alternatively, the terminal can determine one or more knowledge-sharing regions on its own predicted trajectory, and then send the fourth information to suggest that the second device adopt it, thus also enabling the terminal to acquire one or more knowledge-sharing regions related to itself.

[0021] In an optional implementation of the first aspect, the method further includes: stopping the first knowledge sharing when the first device is located outside the target area, or when the first knowledge sharing is completed, or when a stopping criterion determined by the first device is met, or when a stopping criterion included in the received third information is met.

[0022] When one or more of the above conditions are met, continuing to perform the first knowledge sharing becomes meaningless, and stopping the first knowledge sharing can save resources for the terminal.

[0023] In one alternative implementation of the first aspect, the target region includes one or more regions.

[0024] Determining multiple regions at once can save communication resources for the terminal.

[0025] In a second aspect, embodiments of this application provide a knowledge-sharing method, wherein the implementer of the method (i.e., the second device) may be a base station (BS) or a chip applied to the BS. In the following description, the BS is an example of the second device and not a limitation thereof. The method includes: determining at least one area, wherein the at least one area is used for knowledge sharing; and sending first information, wherein the first information indicates the at least one area.

[0026] In this implementation, the real world is divided into at least one region. The BS sends first information indicating the at least one region, enabling the terminal receiving the first information to select a target region from the at least one region. Since the terminal is always aware of its own conditions, the target region is always a suitable region for the terminal. Sharing knowledge within the suitable region improves the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0027] In an optional implementation of the second aspect, the method further includes: acquiring second information, wherein the second information indicates the state and / or environmental state of at least one first device; determining at least one region includes: determining the at least one region based on the second information.

[0028] For example, the state of the first device includes battery level. If most terminals in the area are in low-battery mode, the BS can decide not to select that area as the at least one area. Similarly, the environmental state includes geographical location. If the geographical location is in the ocean, there is less data traffic available for terminals to process, and more resources are available at the terminals for knowledge sharing; the BS can then decide to select that area as the at least one area. Therefore, determining the at least one area based on the second information will make full use of the resources of the first device.

[0029] In an optional implementation of the second aspect, the state of the at least one first device includes at least one of the following: storage resources, computing resources, data resources, communication resources, power, trajectory, position relative to the charging area, and movement state; the environmental state includes at least one of the following: time, geographical location, position of the second device, communication quality, traffic location, type of knowledge data, and current knowledge quantity.

[0030] In an alternative implementation of the second aspect, the method further includes: sending third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0031] Based on the type of the first knowledge sharing, the terminal executes the first knowledge sharing as instructed by the second device, enabling the second device to centrally schedule the knowledge sharing to ensure fairness to all participants. The order of the first knowledge sharing can be either the order in which the first knowledge sharing is started or the order in which the first knowledge sharing is stopped, thus the terminal can execute the first knowledge sharing according to the actual situation.

[0032] In an optional implementation of the second aspect, the method further includes: receiving fourth information from a first device, wherein the fourth information is used to obtain one or more knowledge-sharing regions on the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing regions on the trajectory of the first device; sending first information includes: sending the first information according to the fourth information, wherein at least one region is the region on the trajectory of the first device.

[0033] For example, the fourth information indicates the terminal's predicted trajectory, and the terminal can acquire one or more knowledge-sharing regions related to its own predicted trajectory. Alternatively, the terminal can determine one or more knowledge-sharing regions on its own predicted trajectory, and then send the fourth information to suggest that the BS adopt it; thus, the terminal can also acquire one or more knowledge-sharing regions related to its own predicted trajectory.

[0034] In an optional implementation of the second aspect, the at least one region includes a target region, and the method further includes: receiving first knowledge from the first device when the first device is within the target region; and / or sending the first knowledge to a third device when the first device is within the target region.

[0035] The first knowledge refers to information about the sharing of the first knowledge, such as training data and / or trained models. The BS can send the first knowledge to other devices and receive knowledge from other devices. By sending the first knowledge, the terminal can improve its own model and / or global model based on the first knowledge. By receiving the first knowledge, the BS can improve its own model and / or global model based on the first knowledge. In scenarios where the first knowledge is received from a first device, a terminal with a large amount of knowledge to be shared (i.e., the first device) can choose to pass through areas with less knowledge and can sell its own knowledge to devices within those areas. Therefore, the terminal can fully leverage its advantages. Furthermore, this also has advantages for navigation systems. By recommending terminals with a large amount of knowledge to pass through areas with less knowledge, a more balanced knowledge map will be created, which will help balance traffic on different routes.

[0036] In a third aspect, embodiments of this application provide a knowledge-sharing method, wherein the implementer of the method (i.e., a first device) may be a terminal or a chip applied to a terminal. In the following description, a terminal is an example of the first device and not a limitation. The method includes: receiving first information, wherein the first information indicates at least one condition for knowledge sharing; determining a target condition from the at least one condition; and initiating first knowledge sharing when the target condition is met.

[0037] In this implementation, the real world is described as at least one condition, which can be a region or time, etc., and the terminal can select a target condition from the at least one condition. The terminal always knows its own state, therefore the target condition is always suitable for the terminal, and sharing knowledge under suitable conditions improves the efficiency of knowledge sharing. Furthermore, since the terminal decides when and where to share knowledge, other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0038] In one alternative implementation of the third aspect, determining the target condition from the at least one condition includes: determining the target condition from the at least one condition based on the state of the first device and / or the environmental state.

[0039] For example, the state of the first device includes battery level. If the terminal is in low battery mode, it can select "being in a small area" as the target condition and initiate first knowledge sharing when it is in a small area. As another example, the environmental state includes knowledge sharing format. The terminal can select "being in an area where its knowledge sharing format matches its capabilities" as the target condition, and the terminal will initiate first knowledge sharing when it is in an area with charging equipment. Determining the target condition based on the state of the first device and / or the environmental state will make the target condition more consistent with the current conditions of the terminal.

[0040] In one alternative implementation of the third aspect, the state of the first device includes at least one of the following: storage resources, computing resources, data resources, communication resources, power, position relative to the charging area, and movement state; the environmental state includes at least one of the following: knowledge sharing form, amount of data related to knowledge sharing, data type related to knowledge sharing, security requirements, physical structure of the area, time, geographical location, position of the second device, communication quality, traffic location, type of knowledge data, and current amount of knowledge.

[0041] In one alternative implementation of the third aspect, initiating the first knowledge sharing includes: sending the first knowledge.

[0042] Sending the first knowledge refers to sending information about the first knowledge sharing, such as training data and / or a trained model of the first knowledge sharing. The terminal can send the first knowledge to other devices and receive knowledge from other devices; alternatively, the terminal can also send the first knowledge only to other devices. By sending the first knowledge, terminals with a large amount of knowledge to be shared can choose to pass through areas with less knowledge and can sell their own knowledge to devices within those areas. Therefore, the terminal can fully leverage its advantages. Furthermore, this also has advantages for navigation systems. By recommending terminals with a large amount of knowledge to pass through areas with less knowledge, a more balanced knowledge map will be created, which will help balance traffic on different routes.

[0043] In an optional implementation of the third aspect, the method further includes: receiving second knowledge when the target condition is met; and determining the first knowledge by learning the second knowledge.

[0044] By receiving the second knowledge, the terminal can determine the first knowledge based on the second knowledge, and then the terminal can send the first knowledge to improve the global model.

[0045] In one alternative implementation of the third aspect, initiating the first knowledge sharing includes: receiving third knowledge.

[0046] By receiving third knowledge, the terminal can learn the third knowledge to improve its own model and / or global model.

[0047] In an alternative implementation of the third aspect, the method further includes: receiving third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0048] Based on the type of the first knowledge sharing, the terminal executes the first knowledge sharing as instructed by the second device, enabling the second device to centrally schedule the knowledge sharing to ensure fairness to all participants. The order of the first knowledge sharing can be either the order in which the first knowledge sharing is started or the order in which the first knowledge sharing is stopped, thus the terminal can execute the first knowledge sharing according to the actual situation.

[0049] In an alternative implementation of the third aspect, the method further includes: sending fourth information, wherein the fourth information is used to obtain one or more knowledge-sharing conditions related to the first device, or the fourth information is used to suggest one or more knowledge-sharing conditions related to the first device.

[0050] For example, the terminal sends the fourth information indicating its own predicted trajectory, enabling the terminal to acquire one or more knowledge-sharing conditions related to its own predicted trajectory. Alternatively, the terminal can determine one or more knowledge-sharing conditions related to its own predicted trajectory, and then send the fourth information to suggest that the second device adopt it; thus, the terminal can also acquire one or more knowledge-sharing conditions related to its own predicted trajectory.

[0051] In an optional implementation of the third aspect, the method further includes: stopping the first knowledge sharing when the target condition is not met, or when the first knowledge sharing is completed, or when the stopping criterion determined by the first device is met, or when the stopping criterion included in the received third information is met.

[0052] When one or more of the above conditions are met, continuing to perform the first knowledge sharing becomes meaningless, and stopping the first knowledge sharing can save resources for the terminal.

[0053] In a fourth aspect, embodiments of this application provide a knowledge-sharing method, wherein the implementer of the method (i.e., the second device) may be a BS or a chip applied to a BS. In the following description, a BS is an example of the second device and not a limitation. The method includes: determining at least one condition, wherein the at least one condition is for knowledge sharing; and sending first information, wherein the first information indicates the at least one condition.

[0054] In this implementation, the real world is described as at least one condition, which can be a region or time, etc. The BS sends first information indicating the at least one condition, enabling the terminal receiving the first information to select a target condition from the at least one condition. Since the terminal always knows its own state, the target condition is always suitable for the terminal, and sharing knowledge under suitable conditions improves the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0055] In an alternative implementation of the fourth aspect, the method further includes: acquiring second information, wherein the second information indicates the state and / or environmental state of at least one first device; determining at least one condition includes: determining the at least one condition based on the second information.

[0056] For example, the state of the first device includes battery level. If most terminals in area A are in low-battery mode, the BS can decide not to select "in area A" as the at least one condition. Similarly, the environmental state includes geographical location. If the geographical location is in the ocean, there is less data traffic available for the terminals, and more resources are available for knowledge sharing at the terminals; the BS can decide to select "in an ocean area" as the at least one condition. Therefore, determining the at least one condition based on the second information will make full use of the resources of the first device.

[0057] In one alternative implementation of the fourth aspect, the state of the at least one first device includes at least one of the following: storage resources, computing resources, data resources, communication resources, power, trajectory, position relative to the charging area, and movement state; the environmental state includes at least one of the following: time, geographical location, position of the second device, communication quality, traffic location, type of knowledge data, and current knowledge quantity.

[0058] In an alternative implementation of the fourth aspect, the method further includes: sending third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0059] Based on the type of the first knowledge sharing, the terminal executes the first knowledge sharing as instructed by the second device, enabling the second device to centrally schedule the knowledge sharing to ensure fairness to all participants. The order of the first knowledge sharing can be either the order in which the first knowledge sharing is started or the order in which the first knowledge sharing is stopped, thus the terminal can execute the first knowledge sharing according to the actual situation.

[0060] In an optional implementation of the fourth aspect, the method further includes: receiving fourth information from a first device, wherein the fourth information is used to obtain one or more knowledge-sharing conditions related to the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing conditions related to the trajectory of the first device; sending first information includes: sending the first information according to the fourth information, wherein at least one condition is the condition related to the trajectory of the first device.

[0061] For example, the fourth information indicates the terminal's predicted trajectory, and the BS can determine one or more knowledge-sharing conditions related to the terminal's predicted trajectory. Alternatively, the terminal can determine one or more knowledge-sharing conditions related to its own predicted trajectory, and then send the fourth information to suggest that the BS adopt it; therefore, the BS can also determine one or more knowledge-sharing conditions related to the terminal's predicted trajectory.

[0062] In an optional implementation of the fourth aspect, the at least one condition includes a target condition, and the method further includes: receiving first knowledge from the first device when the first device satisfies the target condition; and / or sending the first knowledge to a third device when the first device satisfies the target condition.

[0063] The first knowledge refers to information about the sharing of the first knowledge, such as training data and / or trained models. The BS can send the first knowledge to other devices and receive knowledge from other devices. By sending the first knowledge, the terminal can improve its own model and / or global model based on the first knowledge. By receiving the first knowledge, the BS can improve its own model and / or global model based on the first knowledge. In scenarios where the first knowledge is received from a first device, a terminal with a large amount of knowledge to be shared (i.e., the first device) can choose to pass through areas with less knowledge and can sell its own knowledge to devices within those areas. Therefore, the terminal can fully leverage its advantages. Furthermore, this also has advantages for navigation systems. By recommending terminals with a large amount of knowledge to pass through areas with less knowledge, a more balanced knowledge map will be created, which will help balance traffic on different routes.

[0064] In a fifth aspect, embodiments of this application provide a knowledge-sharing apparatus for performing any of the methods provided in the first or third aspect.

[0065] In one possible design, the device can be divided into functional modules according to any of the methods provided in the first aspect or the third aspect, each functional module being obtained by dividing based on a corresponding function, or two or more functions being integrated into one module.

[0066] For example, the device can be divided into receiving modules, processing modules, transmitting modules, etc., based on function. For a description of the possible technical solutions and their beneficial effects performed by the functional modules obtained through this division, refer to the methods provided in the first aspect and its alternative implementations, or the methods provided in the third aspect and its alternative implementations.

[0067] In a sixth aspect, embodiments of this application provide a knowledge-sharing apparatus for performing any of the methods provided in the second or fourth aspect.

[0068] In one possible design, the device can be divided into functional modules according to any of the methods provided in the first to fourth aspects, each functional module being obtained by dividing based on a corresponding function, or two or more functions being integrated into one module.

[0069] For example, the device can be divided into receiving modules, processing modules, transmitting modules, etc., based on function. For a description of the possible technical solutions and beneficial effects performed by the functional modules obtained through this division, see the methods provided in the second aspect and its alternative implementations, or the methods provided in the fourth aspect and its alternative implementations. Further details are omitted here.

[0070] In a seventh aspect, embodiments of this application provide a knowledge-sharing device, which may be a terminal or a chip applied to a terminal. The device may include a processor for executing any of the methods provided in the first aspect and its optional implementations, or any of the methods provided in the third aspect and its optional implementations.

[0071] Optionally, the device may further include a transceiver. When the device is a terminal, the transceiver may be a transceiver circuit, an antenna, etc. When the device is a chip applied to a terminal, the transceiver may be an input / output interface, pins, circuitry, etc.

[0072] Optionally, the device may further include a memory for storing computer programs or instructions, and the processor executes the computer programs or instructions stored in the memory to enable the device to perform: any of the methods provided in the first aspect and its optional implementations, or any of the methods provided in the third aspect and its optional implementations. When the device is a terminal, the memory may be a read-only memory, random access memory, etc. When the device is a chip applied to a terminal, the memory may be a register, cache, etc.

[0073] In an eighth aspect, embodiments of this application provide a knowledge-sharing apparatus, which may be a business unit (BS) or a chip applied to a BS. The apparatus may include a processor for executing any of the methods provided in the second aspect and its alternative implementations, or any of the methods provided in the fourth aspect and its alternative implementations.

[0074] Optionally, the device may further include a transceiver. When the device is a BS (Browser Base), the transceiver may be a transceiver circuit, an antenna, etc. When the device is a chip applied to a BS, the transceiver may be an input / output interface, pins, circuitry, etc.

[0075] Optionally, the device may further include a memory for storing computer programs or instructions, and the processor executes the computer programs or instructions stored in the memory to enable the device to perform: any of the methods provided in the second aspect and its optional implementations, or any of the methods provided in the fourth aspect and its optional implementations. When the device is a BS (Browser / Server), the memory may be a read-only memory, random access memory, etc. When the device is a chip applied to a BS, the memory may be a register, cache, etc.

[0076] In a ninth aspect, embodiments of this application provide a knowledge-sharing system, the system comprising: the apparatus provided in the fifth aspect and the apparatus provided in the sixth aspect, or the apparatus provided in the seventh aspect and the apparatus provided in the eighth aspect.

[0077] For example, the system is a communication system, including at least one terminal and at least one BS.

[0078] For example, the system is a chip system, including at least one processor used in a terminal and at least one processor used in a BS.

[0079] In a tenth aspect, embodiments of this application provide a computer-readable storage medium, such as a non-transitory computer-readable storage medium. The computer-readable storage medium stores a computer program or instructions. When the computer program or instructions are executed on a device, the device is enabled to perform: any method provided in the first aspect and its optional implementations, or any method provided in the second aspect and its optional implementations, or any method provided in the third aspect and its optional implementations, or any method provided in the fourth aspect and its optional implementations.

[0080] In an eleventh aspect, embodiments of this application provide a computer program product comprising computer program code or computer program instructions, wherein when executed by a device, the computer program code or the computer program instructions enable the device to perform: any method provided in the first aspect and its optional implementations, or any method provided in the second aspect and its optional implementations, or any method provided in the third aspect and its optional implementations, or any method provided in the fourth aspect and its optional implementations.

[0081] The apparatus, system, computer-readable storage medium, and computer program product provided in this application are all used to perform the corresponding methods provided above. Therefore, for the beneficial effects that the apparatus, system, computer-readable storage medium, and computer program product can achieve, refer to the beneficial effects of the corresponding methods provided above. Further details are omitted here. Attached Figure Description

[0082] Figure 1 This is a simplified diagram of a communication system; Figure 2 yes Figure 1 A block diagram of an exemplary communication system; Figure 3 Examples of exemplary electronic devices and base stations are shown; Figure 4 This shows the units or modules in the device; Figure 5 This is a simplified diagram of a centralized FL scene; Figure 6 This is a simplified diagram of a decentralized FL scenario; Figure 7 This is a diagram illustrating knowledge-sharing methods; Figure 8 This is a diagram illustrating another knowledge-sharing method; Figure 9 This is a simplified diagram illustrating knowledge sharing in satellite networks; Figure 10This is another simplified diagram illustrating knowledge sharing in satellite networks; Figure 11 This is another simplified diagram illustrating knowledge sharing in satellite networks; Figure 12 This is a simplified diagram illustrating knowledge sharing in a vehicle network. Figure 13 This is a diagram illustrating another knowledge-sharing method; Figure 14 This is a schematic diagram of the structure of a knowledge-sharing device; Figure 15 This is another schematic diagram of the structure of a knowledge-sharing device. Detailed Implementation

[0083] Figure 1 This is a schematic diagram of the communication system 100 used in the embodiments of this application. See also Figure 1 As a non-limiting illustrative example, a simplified schematic diagram of a communication system is provided. Communication system 100 (which may be a wireless system) includes a radio access network (RAN) 120. The RAN 120 may be a next-generation (e.g., 6th generation (6G) or higher) radio access network, or a traditional (e.g., 5th generation (5G), 4th generation (4G), 3rd generation (3G), or 2nd generation (2G)) radio access network. In some implementations, 6G radio access refers to the next-generation standard air interface, which may include terrestrial networks (TN) and non-terrestrial networks (NTN), further details of which will be described below. One or more electronic devices (EDs) 110a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, and 110j (collectively referred to as 110) may be interconnected with each other or connected to one or more network nodes (170a, 170b, collectively referred to as 170) in RAN 120. The core network (CN) 130 may be part of the communication system and may depend on or be independent of the radio access technology used in the communication system 100. The communication system 100 may also include a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160.

[0084] Typically, communication system 100 enables multiple wireless or wired components to transmit data and other content. Communication system 100 can provide voice, data, video, and / or text content through broadcasting, multicasting, unicasting, etc., and can provide a wide range of communication services and applications (e.g., earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery, and mobility). Services and / or applications may be mobile broadband (MBB) services, ultra-reliable low-latency communication (URLLC) services, or machine-type communication (MTC) services.

[0085] The communication system 100 can operate by sharing resources such as carrier spectrum bandwidth among its constituent components.

[0086] Communication system 100 may include terrestrial communication systems and / or non-terrestrial communication systems. Communication system 100 can provide high availability and robustness through the joint operation of terrestrial and non-terrestrial communication systems. For example, integrating a non-terrestrial communication system (or components thereof) into a terrestrial communication system can create a heterogeneous network that can be considered as having multiple layers. Heterogeneous networks can achieve better overall performance through efficient multi-link joint operation, more flexible function sharing, and faster physical layer link switching between terrestrial and non-terrestrial networks.

[0087] Terrestrial communication systems and non-terrestrial communication systems can be subsystems of a communication system.

[0088] Figure 2 A more detailed example of the communication system 100 is shown. (Compared to...) Figure 1 The example shown is the same, in Figure 2In the example shown, communication system 100 may include ED 110a, 110b, 110c, 110d (collectively referred to as ED 110) and RAN 120a, 120b. Additionally, communication system 100 may also include NTN 120c. Communication system 100 may also include one or more of CN 130, PSTN 140, Internet 150, and other networks 160. RAN 120a, 120b include corresponding network nodes 170a, 170b (e.g., base stations 170a, 170b), which may be collectively referred to as TN equipment or terrestrial transmit and receive points (T-TRP) 170a, 170b (collectively referred to as 170). T-TRP 170a, 170b are BSs attached to the ground (e.g., mounted on a building or tower). In one implementation, NTN 120c includes RAN nodes (e.g., base station 172), which can be collectively referred to as NTN equipment, non-terrestrial node, non-terrestrial network equipment, non-terrestrial base station, or non-terrestrial transmit and receive point (NT-TRP) 172. NT-TRP 172 is not attached to the ground. A flying base station is one example. A flying base station can be implemented using communication equipment supported or carried by flying equipment. Non-limiting examples of flying equipment include airborne platforms (e.g., small airships or spacecraft), balloons, quadcopters, and other aircraft. In some implementations, the flying base station can be supported or carried by an unmanned aerial system (UAS) or unmanned aerial vehicle (UAV) (e.g., a drone or quadcopter). The flying base station can be a mobile or portable base station capable of flexible deployment in different locations to meet network requirements. A satellite base station is another example of a non-terrestrial base station. A satellite base station can be implemented using communication equipment supported or carried by satellites. A satellite base station can also be referred to as an orbital base station. High-altitude platforms are another example of non-terrestrial base stations, including international mobile communication base stations.

[0089] Note that "TRP" as used herein may refer to either T-TRP or NT-TRP unless otherwise specified. T-TRP may alternatively be referred to as "TN TRP," and NT-TRP may alternatively be referred to as "NTN TRP." As can be inferred from the similarity in the reference numerals, NTN 120c may be considered a RAN, having the same operational aspects as RAN 120a and 120b. In another implementation, NTN 120c may include at least one non-terrestrial network device and at least one corresponding terrestrial network device, wherein the at least one non-terrestrial network device serves as a transport layer device, and the at least one corresponding terrestrial network device serves as a RAN node, which communicates with the ED via the non-terrestrial network device. Furthermore, an NTN gateway (i.e., referred to as a terrestrial network device) may also be present on the ground as a transport layer device communicating with the NTN device, and the RAN node communicates with the ED via the NTN device and the NTN gateway. In some implementations, the NTN gateway and the RAN node may reside in the same device. Base stations 170a and 170b, 172 can communicate with each other via one or more air interfaces 190e, 190f using wireless communication links (e.g., radio frequency (RF), microwave, infrared (IR), etc.). Air interfaces 190e, 190f can utilize any suitable wireless access technology and can be substantially similar to or substantially different from air interfaces 190a, 190c on which ED 110a to 110d communicate with one or more of TRP 170a and 170b, 172. For example, communication system 100 can implement one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or single-carrier FDMA (SC-FDMA).

[0090] In some implementations, TRPs (also known as base stations) 170a and 170b or 172 can use other names, such as base transceiver station (BTS), wireless base station, network node, network device, network-side device, transmit / receive node, NodeB, evolved NodeB (eNodeB or eNB), home eNodeB, next-generation NodeB (gNB), transmission point (TP), site controller, access point (AP), wireless router, relay station, ground node, ground network device, ground base station, positioning node, etc. T-TRP 170a and 170b can be macro base stations (BS), micro BS, relay nodes, host nodes, etc., or combinations thereof. The method of this application is applied to the TRP side, for example, it can be understood as applied to the TRP or the communication module in the TRP, the circuit or chip responsible for one or more communication functions in the TRP (e.g., modem chip, also known as baseband chip, system-on-a-chip including modem core, or system-in-package (SIP) chip).

[0091] ED 110a to 110d and TRP 170a, 170b, 172 are examples of communication devices that can be used to implement some or all of the operations and / or embodiments described herein. Figure 2In the example shown, site TRP170a forms part of RAN 120a, which may include other TRPs and / or other equipment. Similarly, TRP 170b forms part of RAN 120b, which may include other TRPs and / or equipment. Each TRP 170a, 170b transmits and / or receives radio signals within a specific geographic area (sometimes referred to as a "cell" or "coverage area"). TRPs 170a and 170b may be responsible for allocating / configuring resources and transmitting / receiving within the cell set. A cell is a radio network object that can be uniquely identified by a (cell) identifier broadcast across a geographic area from the base station associated with the cell. A cell can be in FDD or TDD mode. A cell can also refer to a carrier frequency within the DL / UL carrier bandwidth resources of a single independent carrier or component carrier in carrier aggregation mode. Cells can be further divided into cell sectors; for example, base stations 170a and 170b may employ multiple transceivers to provide services to multiple sectors. In some implementations, there may be established picocells or femtocells supported by radio access technologies. In some implementations, for example, multiple transceivers can be used for each cell via multiple-input multiple-output (MIMO) technology. The number of RANs 120a and 120b shown are merely exemplary. Any number of RANs can be considered when designing the communication system 100.

[0092] Any base station 170a and 170b can be a single element as shown in the figure, or multiple elements distributed in the corresponding RAN. In some implementations, multiple RAN nodes cooperate to assist ED 110 in achieving radio access, and different RAN nodes implement some functions of the base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CU-CP), a CU-user plane (CU-UP), or a radio unit (RU), etc. CU and DU can be set up separately or contained in the same element (i.e., a baseband unit (BBU)). RU can be contained in radio equipment or radio units (i.e., a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH)). In different systems, CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art will understand their meaning. For example, in an Open Radio Access Network (ORAN) system, a CU can also be called an Open CU (O-CU), a DU can also be called an Open DU (O-DU), and a CU-CP can also be called an Open CU-CP (O-CU-CP). A CU-UP can also be called an Open CU-UP (O-CU-UP), and a RU can also be called an Open RU (O-RU). Any one of the CU (or CU-CP, CU-UP), DU, and RU can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0093] Furthermore, in various embodiments of this application, one or more communications between different devices / apparatus can refer to direct communication between different devices / apparatus (i.e., without the need for forwarding by another device / apparatus), or it can refer to one or more communications between different devices / apparatus via another device / apparatus (i.e., requiring forwarding by another device / apparatus). Alternatively, it can refer to a functional unit within a device / apparatus communicating with another device / apparatus by using another functional unit. In other words, "sending information to... (ED or base station)" in this application can be understood as the destination of the information being an ED or base station. It can include sending information directly or indirectly to an ED or base station. "Receiving information from... (ED or base station)" can be understood as the source of the information being an ED or base station, and can include receiving information directly or indirectly from an ED or base station. Necessary processing, such as format conversion, digital-to-analog conversion, amplification, and filtering, can be performed between the source and destination. However, the destination can understand valid information from the source. Similar descriptions in this application can be understood in a similar manner, and will not be repeated here.

[0094] The ED 110 is used to connect people, objects, and machines. It can be widely used in various scenarios, including cellular communication, device-to-device (D2D), vehicle-to-everything (V2X), peer-to-peer (P2P), machine-to-machine (M2M), MTC, Internet of Things (IoT), virtual reality (VR), augmented reality (AR), mixed reality (MR), digital twins, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, and mobility.

[0095] Each ED 110 represents any end-user equipment suitable for wireless operation and may include (or be referred to as, but not limited to): user equipment / device (UE), wireless transmit / receive unit (WTRU), mobile station, fixed or mobile subscriber unit, cellular phone, station (STA), MTC device, personal digital assistant (PDA), smartphone, laptop, computer, tablet, wireless sensor, consumer electronics device, smartbook, vehicle, automobile, truck, bus, train, or IoT device, wearable device (e.g., watch, glasses, head-mounted device, etc.), industrial equipment, or devices that include or incorporate the aforementioned devices (e.g., communication module, modem, or chip), etc. Next-generation Ed 110 may be referred to using other terms. The methods of this application applied to the ED side can be understood as applied to the ED or a communication module within the ED, or a circuit or chip responsible for one or more communication functions within the ED (e.g., a modem chip, also known as a baseband chip, a system-on-a-chip including a modem core, or a SIP chip).

[0096] Each ED 110 connected to TRP 170a and 170b and / or TRP 172 can be dynamically or semi-statically started (i.e., established, activated, or enabled), shut down (i.e., released, deactivated, or disabled), and / or configured in response to one or more of connectivity availability and connectivity necessity.

[0097] Alternatively or additionally, any ED 110 can be used to access, connect to, or communicate with any TRP 170a, 170b, and 172, the Internet 150, the core network 130, the PSTN 140, other networks 160, or any combination thereof. In some examples, ED 110a can communicate with base station 170a via uplink (UL) and / or downlink (DL) transmissions through terrestrial air interface 190a. In some examples, ED 110a, 110b, 110c, and 110d can also communicate directly with each other via one or more sidelink (SL) air interfaces 190b. In some examples, ED 110d can communicate with base station 172 via non-terrestrial air interface 190c.

[0098] An air interface (e.g., 190a, 190b, 190c) typically includes multiple components and associated parameters that collectively specify how transmissions are sent and / or received over a wireless communication link between two or more communication devices (e.g., EDs and base stations). For example, an air interface may include one or more waveforms, one or more frame structures, one or more multiple access schemes, one or more protocols, one or more coding schemes, and / or one or more modulation schemes that define the transmission of information (e.g., data) over the wireless communication link. The wireless communication link may support a link between a radio access network (e.g., RAN 120) and ED 110 (e.g., a "Uu" link), and / or a link between ED 110a and ED 110b (e.g., SL), and / or a link between an NTN (e.g., RAN 120c) and ED 110d. Below are some examples of the components described above.

[0099] Waveform components can specify the shape and form of the transmitted signal. Waveform options can include orthogonal multiple access (OFDM) and non-orthogonal multiple access (NMA) waveforms. Non-limiting examples of such waveform options include orthogonal frequency division multiplexing (OFDM), Discrete Fourier Transform spread OFDM (DFT-OFDM), filtered OFDM (f-OFDM), time-domain windowed OFDM, filter bank multicarrier (FBMC), universal filtered multicarrier (UFMC), generalized frequency division multiplexing (GFDM), wavelet packet modulation (WPM), faster than Nyquist (FTN) waveforms, and low peak-to-average power ratio (PAPR) waveforms (WF).

[0100] The frame structure component can specify the configuration of a frame or a group of frames. The frame structure component can indicate one or more of the following parameters: time, frequency, pilot signature, code, subcarrier spacing, cyclic prefix length, or other parameters. The frame structure will be discussed in detail below.

[0101] Multiple access scheme components can specify multiple access technology options, including technologies that define how communication devices share a common physical channel, such as: code division multiple access (CDMA), space division multiple access (SDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single-carrier FDMA (SC-FDMA) (also known as discrete Fourier transform spread OFDMA (DFT-s-OFDMA)), low-density signature multicarrier CDMA (LDS-MC-CDMA), non-orthogonal multiple access (NOMA), pattern division multiple access (PDMA), lattice partition multiple access (LPMA), resource spread multiple access (RSMA), and sparse code multiple access (SCMA). In addition, multiple access technology options can include: scheduled access and unscheduled access, also known as unlicensed access; non-orthogonal multiple access and orthogonal multiple access, such as through dedicated channel resources (e.g., not shared between multiple communication devices); contention-based shared channel resources and non-contention-based shared channel resources; and cognitive-based radio access. Air Interface 190a and 190b can employ other higher-dimensional signal spaces, which may involve combinations of orthogonal and / orthogonal dimensions.

[0102] Encoding and modulation components specify how the information being transmitted can be encoded / decoded and modulated / demodulated for transmission / reception purposes. Encoding can refer to methods of error detection and forward error correction. Non-limiting examples of encoding options include turbine trellis codes, turbine product codes, fountain codes, low-density parity-check codes, and polar codes. Modulation can simply refer to a constellation (e.g., including modulation techniques and orders), or more specifically to various types of advanced modulation methods, such as layered modulation and low peak-to-average power ratio (PAPR) modulation.

[0103] The 190a and 190b air interfaces can use similar communication technologies, such as any suitable wireless access technology.

[0104] The non-terrestrial air interface 190c enables communication between the ED 110d and one or more NT-TRP 172s via a wireless link or simply through a link. In some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection for multicast transmission between a group of ED 110s and one or more NT-TRP 172s.

[0105] RANs 120a and 120b communicate with core network 130 to provide various services, such as voice, data, and other services, to EDs 110a, 110b, and 110c. RANs 120a and 120b and / or core network 130 may communicate directly or indirectly with one or more other RANs (not shown), which may or may not be directly served by core network 130 and may or may not use the same radio access technology as RANs 120a, RAN 120b, or both. Core network 130 may also serve as a gateway access between (i) RANs 120a and 120b, or EDs 110a, 110b, and 110c, or both, and (ii) other networks (e.g., PSTN 140, Internet 150, and other networks 160). Furthermore, some or all of EDs 110a, 110b, and 110c may include the ability to communicate with different wireless networks via different radio links using different radio technologies and / or protocols. Instead of wireless communication (or other than wireless communication), ED 110a, 110b, and 110c can also communicate with service providers or exchanges (not shown) via wired communication channels and with the Internet 150. PSTN 140 may include a circuit-switched telephone network for providing plain old telephone service (POTS). The Internet 150 may include a network of computers and subnets (internal networks) or both, incorporating protocols such as Internet Protocol (IP), Transmission Control Protocol (TCP), and User Datagram Protocol (UDP). ED 110a, 110b, and 110c may be multimode devices capable of operating under various wireless access technologies and include multiple transceivers required to support these technologies.

[0106] Furthermore, the communication system 100 may include a sensing agent (not shown) to manage sensing data from ED 110 and / or any of TRPs 170a and 170b, 172. In one implementation, the sensing agent is located in any of TRPs 170a and 170b, 172. In another implementation, the sensing agent is a separate node with an interface for communicating with core network 130 and / or RAN 120 (e.g., any of TRPs 170a and 170b, 172).

[0107] Figure 3An example of a device 310 is shown in a communication system (e.g., communication system 100) that wirelessly communicates with at least one of two devices (e.g., devices 320a and 320b, referred to as device 320) according to one embodiment. Device 310 may be Figure 2 ED 110 in the middle. Device 320a can be a terrestrial network device (e.g., such as ED 110). Figure 2 The T-TRP170 shown), device 320b can be a non-terrestrial network device (e.g., such as...). Figure 2 (NT-TRP 172 shown). However, this is not a necessary condition. For example, according to the invention, device 320a can be NT-TRP, device 320b can be T-TRP, and both devices 320a and 320b can be either T-TRP or NT-TRP. Although in Figure 3 There may be only one device 310, one device 320a, and one device 320b. However, please note that the number of devices 310 may be one or more, and the number of devices 320a and / or 320b may be one or more. For example, an ED 110 may be served by only one T-TRP 170 (or one NT-TRP 172), or by more than one T-TRP 170, or by more than one NT-TRP 172, or by one or more T-TRP 170 and one or more NT-TRP 172.

[0108] like Figure 3 As shown, device 310 includes at least one processor 210. Only one processor 210 is shown in the figure to avoid congestion. Device 310 may also include a transmitter 201 and a receiver 203 coupled to one or more antennas 204. Only one antenna 204 is shown in the figure to avoid congestion. Alternatively, one, part or all of the antennas 204 may be panels. The transmitter 201 and receiver 203 may, for example, be integrated as a transceiver. The transceiver is used to modulate data or other content for transmission by at least one antenna 204 or a network interface controller (NIC). The transceiver is also used to demodulate data or other content received through at least one antenna 204. Each transceiver includes any suitable structure for generating signals for wireless or wired transmission and / or processing signals received wirelessly or wiredly. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals. Device 310 may include at least one memory 208. For simplicity, only transmitter 201, receiver 203, processor 210, memory 208 and antenna 204 are shown, but device 310 may include one or more other components.

[0109] Memory 208 stores at least a portion of the instructions for performing the operations described herein. Memory 208 may also store data used, generated, or collected by device 310. For example, memory 208 may store software instructions or modules executable by one or more processing units (e.g., processor 210) for implementing some or all of the functionality and / or embodiments described herein. Each memory 208 includes any suitable volatile and / or non-volatile storage and retrieval device. Any suitable type of memory may be used, such as random access memory (RAM), read-only memory (ROM), hard disk, optical disk, subscriber identity module (SIM) card, memory stick, secure digital (SD) memory card, and on-processor cache, etc.

[0110] The device 310 may also include one or more input / output devices (not shown) or interfaces. The input / output devices or interfaces support interaction with users or other devices in the network. Each input / output device or interface includes any suitable structure for providing or receiving information from the user, and / or for network interface communication. Suitable structures include, for example, speakers, microphones, keypads, keyboards, displays, touchscreens, etc.

[0111] Processor 210 performs (or control device 310 performs) operations described herein as being performed by device 310, as shown below and elsewhere in the invention. For example, processor 210 performs or control device 310 performs the following operations: receiving a transport block (TB), using resources to decode one of the received TBs, releasing resources to decode another of the received TBs, and / or receiving configuration information for configuring resources. Specifically, these operations may include those related to preparing to send an uplink transmission to device 320a and / or device 320b; those related to processing downlink transmissions received from device 320a and / or device 320b; and those related to processing SL transmissions to and from another device 310. Processing operations related to preparing for uplink transmissions may include operations such as encoding, modulation, transmitting beamforming, and generating symbols for transmission. Processing operations related to processing downlink transmissions may include operations such as receiving beamforming, demodulating, and decoding received symbols. Processing operations related to handling SL transmissions may include transmit / receive beamforming, modulation / demodulation, and encoding / decoding symbols. According to embodiments, downlink transmissions may be received by receiver 203 using receive beamforming, and processor 210 may extract signaling from the downlink transmissions (e.g., by detecting and / or decoding signaling). Examples of signaling may be reference signals transmitted by devices 320a and / or 320b. In some implementations, processor 210 performs transmit beamforming and / or receive beamforming based on beam direction indications (e.g., beam angle information (BAI)) received from device 320a. In some implementations, processor 210 may perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as operations related to detecting synchronization sequences, decoding, and acquiring system information. In some implementations, processor 210 may perform channel estimation, for example, using reference signals received from device 320a and / or device 320b.

[0112] Although not shown, processor 210 may be part of transmitter 201 and / or receiver 203. Although not shown, memory 208 may be part of processor 210.

[0113] The processing components of processor 210, transmitter 201, and receiver 203 may each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 208). Alternatively, some or all of the processing components of processor 210, transmitter 201, and receiver 203 may be implemented using dedicated circuitry such as a programmable field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), or hardware accelerator (e.g., a graphics processing unit (GPU) or artificial intelligence (AI) accelerator).

[0114] In some implementations, device 310 may be a communication module in the ED, a circuit or chip responsible for one or more communication functions in the ED (e.g., a modem chip, also known as a baseband chip, a system-on-a-chip including a modem core, or a SIP chip). It includes at least one processor 210, an interface, or at least one pin. In this scenario, transmitter 201 and receiver 203 may be replaced by an interface or at least one pin, wherein the interface or at least one pin connects a device (e.g., a chip) and other devices (e.g., a chip, memory, or bus). Accordingly, sending information to device 320a, device 320b, and / or other device 310 may be referred to as sending information to an interface or at least one pin, or sending information to device 320a, device 320b, and / or other device 310 via an interface or at least one pin. Receiving information from device 320a, device 320b, and / or other device 310 may be referred to as receiving information from an interface or at least one pin, or receiving information from device 320a, device 320b, and / or other device 310 via an interface or at least one pin. The information may include control signaling and / or data. Similar rules can also be applied to other nodes / entities in this invention.

[0115] like Figure 3As shown, device 320a includes at least one processor 260. Only one processor 260 is shown in the figure to avoid congestion. Device 320a may also include at least one transmitter 252 and at least one receiver 254 coupled to one or more antennas 256. Only one antenna 256 is shown in the figure to avoid congestion. Alternatively, one, some, or all of the antennas 256 may be panels. The transmitter 252 and receiver 254 may be integrated as a transceiver. Device 320a may also include at least one memory 258. Device 320a may also include a scheduler 253. For simplicity, only the transmitter 252, receiver 254, processor 260, memory 258, antenna 256, and scheduler 253 are shown, but device 320a may include one or more other components.

[0116] In some implementations, the various parts of device 320a may be distributed. For example, some of the modules of device 320a may be located at a remote end of the device housing antenna 256 of device 320a, and may be coupled to the device housing antenna 256 via a communication link (not shown) sometimes referred to as a fronthaul (e.g., Common Public Radio Interface, CPRI). Therefore, in some implementations, the term device 320a may also refer to network-side modules that perform processing operations such as determining the location of device 310, resource allocation (scheduling), message generation, and encoding / decoding; these modules are not necessarily part of the device housing antenna 256 of device 320a. These modules may also be coupled to other devices 320a. In some implementations, device 320a may actually be multiple devices 320a that work together, for example, by using coordinated multicast to serve device 310.

[0117] Processor 260 performs operations including those related to: preparing to send downlink transmissions to device 310; processing uplink transmissions received from device 310; preparing to send backhaul transmissions to devices 320a and / or 320b; and processing transmissions received from devices 320a and / or 320b via backhaul. Processing operations related to preparing to send downlink or backhaul transmissions may include operations such as encoding, modulation, precoding (e.g., MIMO precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing transmissions received in the uplink or via backhaul may include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. Processor 260 may also perform operations related to network access (e.g., initial access) and / or downlink synchronization, such as generating the contents of a synchronization signal block (SSB) and generating system information. In some implementations, processor 260 also generates beam direction indications, such as BAI, which can be scheduled for transmission by scheduler 253. Processor 260 performs other network-side processing operations described herein, such as determining the location of device 310 and determining the location of deployment device 320b. In some implementations, processor 260 may generate signaling, for example, for configuring one or more parameters of device 310 and / or one or more parameters of device 320b. Any signaling generated by processor 260 is transmitted by transmitter 252.

[0118] Scheduler 253 may be coupled to or integrated into processor 260. Scheduler 253 may be included within device 320a or may operate separately from the device. Scheduler 253 may schedule uplink, downlink, SL, and / or backhaul transmissions, including issuing scheduling authorizations and / or configuring scheduling-free (e.g., "configuration authorization") resources.

[0119] The device 320a may also include a memory 258 that stores at least a portion of instructions for performing the operations described herein, as well as optional data used, generated, or collected by the device 320a. For example, the memory 258 may store software instructions or modules executed by the processor 260 for implementing some or all of the functionality and / or embodiments described herein.

[0120] Although not shown, processor 260 may be part of transmitter 252 and / or receiver 254. Furthermore, although not shown, processor 260 may implement scheduler 253. Although not shown, memory 258 may be part of processor 260.

[0121] Processor 260, scheduler 253, the processing components of transmitter 252, and receiver 254 may each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 258). Alternatively, some or all of the processing components of processor 260, scheduler 253, transmitter 252, and receiver 254 may be implemented using dedicated circuitry such as a programmed FPGA, hardware accelerator (e.g., GPU or AI accelerator), or ASIC.

[0122] In some implementations, device 320a may be a communication module in the TRP, a circuit or chip responsible for one or more communication functions in the TRP (e.g., a modem chip, also known as a baseband chip, a system-on-a-chip including a modem core, or a SIP chip). It includes at least one processor, an interface, or at least one pin. In this scenario, transmitter 252 and receiver 254 may be replaced by an interface or at least one pin, wherein the interface or at least one pin connects a device (e.g., a chip) and other devices (e.g., a chip, memory, or a bus). Therefore, sending information to device 320b and / or device 320a and / or device 310 can be referred to as sending information to an interface or at least one pin. Receiving information from device 320b and / or device 320a and / or device 310 can be referred to as receiving information from an interface or at least one pin. The information may include control signaling and / or data.

[0123] like Figure 3 As shown, device 320b includes at least one processor 276. Only one processor 276 is shown in the figure to avoid congestion. Device 320b may include a transmitter 272 and a receiver 274 coupled to one or more antennas 280. Only one antenna 280 is shown in the figure to avoid congestion. One, some, or all of the antennas may be panels. Transmitter 272 and receiver 274 may be integrated as a transceiver. Device 320b may also include at least one memory 278. Device 320b may also include a scheduler. For simplicity, only transmitter 272, receiver 274, processor 276, memory 278, and antenna 280 are shown in the figure, but NT-TRP may include one or more other components.

[0124] Apparatus 320b includes a processor 276 for performing operations including those related to: preparing to transmit downlink transmissions to apparatus 310; processing uplink transmissions received from apparatus 310; preparing to transmit backhaul transmissions to apparatus 320a and / or another apparatus 320b; and processing transmissions received via backhaul from apparatus 320a and / or another apparatus 320b. Processing operations related to preparing to transmit downlink or backhaul transmissions may include operations such as encoding, modulation, precoding (e.g., MIMO precoding), transmit beamforming, and generating symbols for transmission. Processing operations related to processing transmissions received in the uplink or via backhaul may include operations such as receive beamforming, demodulating received symbols, and decoding received symbols. In some implementations, processor 276 performs transmit beamforming and / or receive beamforming based on beam direction information (e.g., BAI) received from apparatus 320a. In some implementations, processor 276 may generate signaling, for example, for configuring one or more parameters of apparatus 310. In some implementations, device 320b performs physical layer processing but does not perform higher-level functions such as medium access control (MAC) or radio link control (RLC) layer functions. Since this is only an example, in general, device 320b may implement higher-level functions in addition to physical layer processing.

[0125] The device 320b may also include a memory 278 that stores at least a portion of instructions for performing the operations described herein, as well as optional data used, generated, or collected by the device 320b. For example, the memory 278 may store software instructions or modules executed by the processor 276 for implementing some or all of the functionality and / or embodiments described herein.

[0126] Although not shown, processor 276 may be part of transmitter 272 and / or receiver 274. Although not shown, memory 278 may be part of processor 276.

[0127] The processing components of processor 276, transmitter 272, and receiver 274 may each be implemented by the same or different one or more processors for executing instructions stored in memory (e.g., memory 278). Alternatively, some or all of the processing components of processor 276, transmitter 272, and receiver 274 may be implemented using dedicated circuitry such as a programmed FPGA, hardware accelerator (e.g., GPU or AI accelerator), or ASIC. In some implementations, device 320b may actually be multiple devices 320b that work together, for example, through coordinated multipoint transmissions, to serve device 310.

[0128] In some implementations, device 320b may be a communication module in the TRP, a circuit or chip responsible for one or more communication functions in the TRP (e.g., a modem chip, also known as a baseband chip, a system-on-a-chip including a modem core, or a SIP chip). It includes at least one processor, an interface, or at least one pin. In this scenario, transmitter 272 and receiver 257 may be replaced by an interface or at least one pin, wherein the interface or at least one pin connects a device (e.g., a chip) and other devices (e.g., a chip, memory, or a bus). Therefore, sending information to device 320a and / or another device 320b and / or device 310 can be referred to as sending information to an interface or at least one pin. Receiving information from device 320a and / or another device 320b and / or device 310 can be referred to as receiving information from an interface or at least one pin. The information may include control signaling and / or data.

[0129] Devices 320a, 320b and / or 310 may include other components, but for clarity these components have been omitted.

[0130] It should be noted that, for simplicity, the term "signaling" used in this document can also be referred to as control signaling, control message, control information, or message. Signaling between a BS (e.g., network node 170) and a terminal or sensing device (e.g., ED 110), or between different terminals or sensing devices (e.g., between ED 110i and ED 110j), can be carried in physical layer signaling (also known as dynamic signaling), which is transmitted in the physical layer control channel. For the downlink, physical layer signaling can be referred to as downlink control information (DCI) transmitted in the physical downlink control channel (PDCCH). For the uplink, physical layer signaling can be referred to as uplink control information (UCI) transmitted in the physical uplink control channel (PUCCH). For SL (Signaling over Linked Modules), signaling between different terminals or sensing devices (e.g., between ED110i and ED 110j) can be referred to as SL control information (SCI), which is transmitted in the physical sidelink control channel (PSCCH). Signaling can be carried in higher-layer (e.g., above the physical layer) signaling, which is transmitted in physical layer data channels. For example, downlink signaling is transmitted in the physical downlink shared channel (PDSCH), uplink signaling in the physical uplink shared channel (PUSCH), and SL signaling in the physical sidelink shared channel (PSSCH). Higher-layer signaling can also be referred to as static signaling or semi-static signaling. Higher-layer signaling can be radio resource control (RRC) protocol signaling or media access control-control element (MAC-CE) signaling. Signaling can be included in a combination of physical layer signaling and higher layer signaling.

[0131] It should be noted that in this invention, when "information" and "message" are different, they can be carried in a single message or in more than one single message.

[0132] according to Figure 4 One or more steps of the method provided herein may be performed by corresponding units or modules. Figure 4 The diagram illustrates units or modules within a device. The device may be ED 110, T-TRP 170, or NT-TRP 172; a communication module within ED 110, T-TRP 170, or NT-TRP 172; or a circuit or chip responsible for one or more communication functions within ED 110, T-TRP 170, or NT-TRP 172. For example, signals may be transmitted by a transmitting unit or transmitting module. Signals may be received by a receiving unit or receiving module. Signals may be processed by a processing unit or processing module. Other steps may be performed by an AI module or a machine learning (ML) module. The corresponding units or modules may be implemented using hardware, one or more components or devices executing software, or a combination thereof. For example, one or more of these units or modules may be circuits such as integrated circuits. Examples of integrated circuits include programmed FPGAs, GPUs, or ASICs. For example, one or more of these units or modules may be logical, such as logical functions performed by circuits, a portion of an integrated circuit, or software instructions executed by a processor. It should be understood that if these modules are implemented using software executed by a processor, etc., then these modules can be retrieved by the processor, in whole or in part, individually or collectively, for processing, or in single or multiple instances, and these modules themselves may include instructions for further deployment and instantiation. Similar units or modules also apply to other nodes / entities in this invention.

[0133] Additional details regarding ED 110, T-TRP 170, and NT-TRP 172 are known to those skilled in the art. Therefore, these details are omitted herein.

[0134] To facilitate understanding of the embodiments of this application, the technologies involved in the embodiments will be briefly introduced first.

[0135] 1. AI or ML.

[0136] The number of new devices in future wireless networks is expected to grow exponentially, with increasingly diverse functionalities. Furthermore, many new applications and use cases are anticipated, with service quality requirements that are more varied than those of 5G applications / use cases. These will demand new key performance indicators (KPIs) for future wireless networks (e.g., 6G networks), which could be extremely challenging. AI technologies, such as ML technologies (e.g., deep learning), have been introduced into telecommunications applications with the goal of improving system performance and efficiency.

[0137] Knowledge sharing (FL) is a form of knowledge sharing in machine learning that enables a group of participants to collaboratively train a model without sharing their private data. It addresses the fundamental challenges of data privacy and ownership. There are two forms of FL: centralized FL and decentralized FL, as described below.

[0138] 2. Centralized FL.

[0139] exist Figure 5 The diagram shows a simplified illustration of a centralized FL scene. As shown in the figure, M Each client network entity (CNE) collaborates with the central server network entity (SNE) to train the model. Figure 5 The arrows in the diagram represent communication links. A CNE (Content Entity) is a network entity that requires physical resources and guidance; it can be, but is not limited to, a UE (User Equipment) or an organization that owns data (e.g., a bank, a hospital). An SNE (Service Entity) is a network entity that manages and orchestrates CNEs; it can be, but is not limited to, a BS (Business Provider) or a central server. A model is a set of neurons organized into layers. The model needs to be trained to recognize certain types of patterns.

[0140] Training is conducted in rounds, called epochs. At the start of the first epoch, the SNE shares an initial model with all participating CNEs. Each CNE then begins training its model using its local data until the end of the epoch. Each CNE then sends its locally trained model back to the SNE. The SNE performs a model composition process to generate a single global model that incorporates knowledge from all CNEs. This process is repeated in each epoch until the global model converges.

[0141] When it comes to systems consisting of a large number of mobile CNEs distributed over a wide area, three significant drawbacks of centralized FL become apparent: scalability, latency, and communication efficiency.

[0142] First, since all participating nodes need to send their locally trained models to the centralized SNE, this can lead to congestion and potential data loss. Furthermore, it makes the system susceptible to single points of failure. These two factors limit the scalability of centralized FL applications. One possible way to achieve scalability is to network participating CNEs via the internet; however, such a paradigm can be very costly and may incur considerable overhead without addressing the single point of failure problem.

[0143] Secondly, centralized model aggregation (FL) can operate in two modes: synchronous and asynchronous. In synchronous mode, model aggregation occurs when all selected participants have completed local training and simultaneously share their locally trained models. This mode is known to have a slower convergence rate because it is limited by the slowest participant. In asynchronous mode, model aggregation occurs when some of the selected participants have completed local training and share their locally trained models. While it's possible to select the best node to participate in model aggregation, this increases complexity, may violate fairness, and leads to distortion of representativeness across all participating participants in the model aggregation process, and may also hinder the model's generality.

[0144] Finally, in centralized federated learning, the need to periodically share large amounts of models between the SNE and CNE over long periods of time can lead to inefficient communication and significant overhead.

[0145] 3. Decentralized FL.

[0146] As is well known, the alternative to centralized FL is decentralized FL, which is described as follows: Figure 6 As shown. Figure 6 The arrows in the diagram represent communication links, while Figure 6 The circles in the diagram represent Centralized Neighborhoods (CNEs). In this paradigm, the centralized entity SNE is eliminated, and model sharing occurs directly between CNEs in a peer-to-peer manner. This helps to eliminate some of the limitations of centralized functional models (FLs). For example, it eliminates the congestion that can occur at the SNE. Nevertheless, decentralization also comes with a number of drawbacks and increased complexity. However, the literature has investigated and proposed many algorithms that address many challenges in efficient model sharing and guaranteed knowledge aggregation, thereby enabling the convergence of the global model.

[0147] Despite extensive research in this area, a fundamental challenge that remains to be addressed is scalability, especially in systems with a large number of participating clients that are mobile and cover a wide geographical area. In such architectures, sharing the model in a peer-to-peer manner and guaranteeing convergence is extremely difficult, let alone finding a way to enable efficient communication.

[0148] In summary, existing technologies do not take into account the unique characteristics of the real world when designing appropriate knowledge-sharing algorithms, such as the existence of a large number of mobile participating clients covering a large geographical area.

[0149] The technical solutions provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0150] Figure 7 This is a schematic diagram of a knowledge-sharing method provided in an embodiment of this application. Method 700 includes: S710, the second device determines at least one area.

[0151] In method 700, the second device can be any device or chip that supports knowledge sharing, such as... Figure 1 The diagram shows the BS and the chip used in the BS. The first device can be any device or chip that supports knowledge sharing, such as... Figure 1 The terminal and the chip applied to the terminal are shown. In any embodiment of this application, the form of the first and second devices is not limited.

[0152] The first and second devices can be connected via a wireless network; for example, they can be connected via a terrestrial network or a non-terrestrial network. It should be understood that the first and second devices can also be connected via other wireless networks. This document does not impose any limitations.

[0153] As an optional implementation, before executing S710, the second device may also perform the following operation: acquire second information, wherein the second information indicates the state and / or environmental state of at least one first device.

[0154] The second device can obtain the second information through information reported by at least one first device or information from a third-party device.

[0155] For example, the terminal sends its own status report to the BS, which indicates storage resources (e.g., storage space), computing resources (e.g., processor processing power), data resources (e.g., training data), communication resources (e.g., channel quality), and power (e.g., remaining battery capacity). Therefore, the BS can obtain the terminal's status through the status report.

[0156] For example, the BS can receive second information from the server, wherein the second information indicates time, geographical location, location of the second device, communication quality, traffic location, type of knowledge data, and current amount of knowledge.

[0157] The second device can also acquire the second information on its own.

[0158] For example, a BS can obtain the location of a terminal using positioning signals, and then determine the terminal's position relative to the charging area. The BS can also determine the terminal's predicted trajectory and movement status based on its location at different times.

[0159] There are no restrictions on the form in which the second information is obtained.

[0160] After acquiring the second information, the second device can determine at least one region based on the second information.

[0161] Here are some examples of identifying at least one region.

[0162] Optionally, the state of at least one of the first devices includes at least one of the following: Storage resources, computing resources, data resources, communication resources, power consumption, trajectory, position relative to the charging area, and movement status.

[0163] Considering storage resources, the second device may select one or more regions of terminals containing sufficient memory space as at least one region, so that most terminals have sufficient resources to store training data and / or models.

[0164] Considering computing resources, the second device may select one or more regions containing more computing-powered terminals as at least one region, so that most terminals have sufficient resources for model aggregation and / or training.

[0165] Considering data resources, the second device can select one or more regions containing more terminals with abundant training data as at least one region, so that most terminals have sufficient resources to train the model.

[0166] Considering communication resources, the second device can select one or more areas containing more broadband-capable terminals as at least one area, so that local models can be sent in a timely manner.

[0167] Considering battery power, the second device may select one or more regions containing more terminals with sufficient remaining battery power as at least one region, so that most terminals have enough power for model aggregation and / or training.

[0168] Considering the trajectory (predicted trajectory or previous trajectory), the second device can select one or more regions covering the trajectory of the terminal as at least one region, so that there are sufficient resources for model aggregation and / or training.

[0169] Considering the location relative to the charging area, the second device can select one or more areas containing the charging device as at least one area, such that there is sufficient power to support model aggregation and / or training.

[0170] Taking into account mobility status, the second device may select one or more areas containing more terminals with predictable mobility and behavioral patterns as at least one area, so that most terminals have an equal opportunity to participate in knowledge sharing and will be able to access the same data.

[0171] Optionally, the environmental state includes at least one of the following: Time, geographical location, location of the second device, communication quality, traffic location, type of knowledge data, and current amount of knowledge.

[0172] Taking time into account, the second device can select one or more areas with longer sunshine hours as at least one area, so that there is enough power to support solar-powered terminals (e.g., satellites) for model aggregation and / or training.

[0173] Considering the geographical location, since the terminal needs to process relatively few data services, the second device can select one or more areas of the ocean or above the ocean as at least one area.

[0174] Considering the location of the second device, the second device can select one or more areas close to the second device as at least one area, so that the second device can immediately access the model when needed.

[0175] Considering communication quality, the second device can select one or more regions with better channel quality as at least one region, so that local model and / or training data can be sent in a timely manner.

[0176] Considering the location of traffic, the second device can select one or more regions with high traffic as at least one region, so that there are sufficient resources for model aggregation and / or training.

[0177] Considering the type of knowledge data, the second device may select one or more regions of the terminal containing more knowledge data of the target type (e.g., images) as at least one region, so that there are suitable resources to train the target model (e.g., a convolutional neural network).

[0178] Considering the current amount of knowledge, the second device can select one or more regions containing more terminals with sufficient knowledge data as at least one region, so that there is enough data to train the model.

[0179] The examples above all use one state to select at least one region. It should be understood that the second device may also use multiple states to select at least one region. This will not be elaborated further.

[0180] Based on the second information, it is determined that at least one area will make full use of the resources of the first device.

[0181] Furthermore, at least one area can be any kind of area.

[0182] For example, at least one area can be one or more planar areas, such as a driveway, a commercial area, a rail plan, an administrative division, a geographical area, etc.

[0183] For example, at least one region can be one or more cubic spaces, such as three-dimensional space in the sky or ocean.

[0184] After identifying at least one region, the second device can send first information, which indicates at least one region for knowledge sharing. The second device can send the first information periodically or non-periodically. Similarly, the second device can send the first information autonomously or upon request from the first device. In any embodiment of this application, there are no restrictions on how or when the first information is sent.

[0185] Accordingly, for the first device, S720 is executed.

[0186] S720, the first device receives first information, wherein the first information indicates at least one area for knowledge sharing.

[0187] The first piece of information can be any kind of information indicating at least one area.

[0188] For example, the first and second devices store multiple predefined regions, each region having an identifier (ID), and the first information may be one or more IDs of at least one of the multiple regions.

[0189] For example, if neither the first nor the second device stores a predefined region, the second device determines the latitude and longitude information of at least one region, and the latitude and longitude information is the first information.

[0190] Knowledge sharing describes a scenario where a device transmits a model and / or data to another device, which, upon receiving the model and / or data, performs training or aggregation locally based on the model and / or data. Knowledge sharing also describes a scenario where a device receives a model or data from another device, which, upon receiving the model and / or data, performs training or aggregation locally based on the model and / or data. There are no restrictions on the form of knowledge sharing; as an optional example, knowledge sharing is FL (Flexible Interchange).

[0191] After receiving the first information, the first device may execute the following S730.

[0192] S730, the first device determines the target area from at least one area.

[0193] The target area may include one or more areas. Determining multiple areas at once can save communication and / or computing resources.

[0194] In one alternative implementation, the first device determines the target region from at least one region based on the state of the first device and / or the state of the target region.

[0195] Here are some examples of identifying a target area from at least one region.

[0196] Optionally, the state of the first device includes at least one of the following: Storage resources, computing resources, data resources, communication resources, power, position relative to the target area, position relative to the charging area, and movement status.

[0197] Considering storage resources, when the first device has sufficient memory space in these regions, the first device can select one or more regions as target regions, so that the first device has sufficient resources to store training data and / or models.

[0198] Considering computational resources, when the first device has sufficient computational resources in these regions, the first device can select one or more regions as target regions, so that the first device has sufficient resources to aggregate and / or train the model.

[0199] Considering data resources, when the first device has sufficient data in these areas, the first device can select one or more areas as target areas, so that the first device has sufficient resources to train the model.

[0200] Considering data resources, when the first device has sufficient data in these areas, the first device can select one or more areas as target areas, so that the first device has sufficient resources to train the model.

[0201] Considering communication resources, when the first device has good channel quality in these areas, the first device can select one or more areas as target areas, so that local models and / or training data can be sent in a timely manner.

[0202] Considering battery power, when the first device has sufficient remaining power in these areas, the first device can select one or more areas as target areas, so that the first device has sufficient power to aggregate and / or train the model.

[0203] Considering its position relative to the target area, the first device can select one or more areas that are relatively close to itself as the target area, so that the first device can make timely use of its resources.

[0204] Considering the location relative to the charging area, the first device can select one or more areas with the charging device as the target area, such that the first device has sufficient power to aggregate and / or train the model.

[0205] Taking mobility status into account, the first device may select one or more areas containing terminals with similar predictable mobility or behavioral patterns as target areas, so that most terminals have an equal opportunity to participate in knowledge sharing and will be able to access the same data.

[0206] Optionally, the state of the target area includes at least one of the following: The knowledge sharing format, the amount of data related to knowledge sharing, the data types related to knowledge sharing, security requirements, and the physical structure of the target area.

[0207] Considering the form of knowledge sharing, the first device can select one or more regions containing terminals that perform similar knowledge sharing as target regions, so that there are suitable resources for model training, or to facilitate the sale of the knowledge of the first device.

[0208] Considering the amount of data related to knowledge sharing, the first device can select one or more regions containing more terminals with data related to knowledge sharing as target regions, so that there is enough data to train the model.

[0209] Considering the data types related to knowledge sharing, the first device may select one or more regions containing more terminals with suitable data types as target regions, so that suitable knowledge-sharing related data (e.g., images) are available to train the model (e.g., a convolutional neural network).

[0210] Considering security requirements, the first device can select one or more areas with a security level higher than its own security requirements as target areas, thereby ensuring the security of knowledge sharing by the first device.

[0211] Considering the physical structure of the target area, the first device can select one or more areas whose shape matches the trajectory of the first device as the target area, so that the first device can make full use of its resources.

[0212] The examples above all use a single state to select the target area. It should be understood that the first device can also use multiple states to select the target area. This will not be elaborated further in this article.

[0213] There is no limitation on the form in which the target region is determined from at least one region. Determining the target region based on the state of the first device and / or the state of the target region will make the target region more consistent with the current conditions of the terminal.

[0214] After determining the target area, the first device can execute the following S740.

[0215] S740, when the first device is within the target area, the first device initiates the first knowledge sharing.

[0216] In one alternative implementation, initiating the first knowledge sharing includes: sending the first knowledge.

[0217] Sending the first knowledge refers to sending information about the first knowledge sharing, such as training data and / or a trained model of the first knowledge sharing. The terminal can send the first knowledge to other devices and receive knowledge from other devices; alternatively, the terminal can also send the first knowledge only to other devices. By sending the first knowledge, terminals with a large amount of knowledge to be shared can choose to pass through areas with less knowledge and can sell their own knowledge to devices within those areas. Therefore, the terminal can fully leverage its advantages. Furthermore, this also has advantages for navigation systems. By recommending terminals with a large amount of knowledge to pass through areas with less knowledge, a more balanced knowledge map will be created, which will help balance traffic on different routes.

[0218] In one alternative implementation, the first device can determine the first knowledge by learning the second knowledge, wherein the second knowledge is received from other devices when the first device is within the target area.

[0219] By receiving the second knowledge, the terminal can determine the first knowledge based on the second knowledge, and then the terminal can send the first knowledge to improve the global model.

[0220] In one alternative implementation, initiating the first knowledge sharing includes: receiving third knowledge.

[0221] By receiving third knowledge, the terminal can learn the third knowledge to improve its own model and / or global model.

[0222] In one alternative implementation, knowledge sharing can be initiated once the first device is within the target area.

[0223] In one alternative implementation, the first device can initiate knowledge sharing when the order of the first device being within the target area and the knowledge sharing being initiated is satisfied.

[0224] The order in which knowledge sharing is initiated can be based on the starting criteria included in the received third information, or it can be based on the starting criteria determined by the first device. Thus, the first device can execute the first knowledge sharing according to the actual situation. For example, when communication in the target area is in a light-load state, the BS can send third information indicating the initiation of the first knowledge sharing, and the terminal can initiate the first knowledge sharing when it is within the target area and receives the third information. Alternatively, when communication in the target area is in a light-load state, the terminal can initiate the first knowledge sharing based on its presence within the target area and in a light-load state.

[0225] In an alternative implementation, before performing S730, method 700 further includes receiving third information, wherein the third information indicates the type of the first knowledge sharing.

[0226] In this implementation, the first device executes the first knowledge sharing instructed by the second device. For example, the BS sends third information indicating that the type of the first knowledge sharing is centralized FL (Flexible Learning Function). The terminal receiving the third information can select a region including the terminal executing the centralized FL as the target region, so that the BS can centrally schedule the knowledge sharing to ensure fairness for all participants.

[0227] In an alternative implementation, before performing S720, method 700 further includes: sending fourth information, wherein the fourth information is used to acquire one or more knowledge-sharing regions on the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing regions on the trajectory of the first device.

[0228] The trajectory can be a previous trajectory (i.e., a historical trajectory) or a predicted trajectory. For example, the terminal sends the fourth information indicating its own predicted trajectory, enabling the terminal to acquire one or more knowledge-sharing regions related to itself. Alternatively, the terminal can determine one or more knowledge-sharing regions on its own predicted trajectory, and then send the fourth information to suggest that the second device adopt it, thus also enabling the terminal to acquire one or more knowledge-sharing regions related to itself.

[0229] In an optional implementation, the method further includes: stopping the first knowledge sharing when the first device is located outside the target area, or when the first knowledge sharing is completed, or when a stopping criterion determined by the first device is met, or when a stopping criterion included in the received third information is met.

[0230] When one or more of the above conditions are met, continuing to perform the first knowledge sharing becomes meaningless, and stopping the first knowledge sharing can save resources for the terminal.

[0231] For example, if the communication channel quality in the target area deteriorates, the terminal can stop the first knowledge sharing; alternatively, it can resume the first knowledge sharing upon receiving a third message instructing the initiation of the first knowledge sharing. In another scenario, when communication in the target area is busy, the terminal can stop the first knowledge sharing upon receiving a third message instructing the initiation of the first knowledge sharing.

[0232] In summary, method 700 divides the real world into at least one region, and the BS sends first information indicating the at least one region, enabling the terminal receiving the first information to select a target region from the at least one region. Since the terminal always knows its own conditions, the target region is always a suitable region for the terminal, and sharing knowledge within the suitable region improves the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0233] Figure 8 This is another schematic diagram of the knowledge sharing method provided in the embodiments of this application. Method 800 includes: S810, the second device determines at least one condition.

[0234] In method 800, the second device can be any device or chip that supports knowledge sharing, such as... Figure 1 The diagram shows the BS and the chip used in the BS. The first device can be any device or chip that supports knowledge sharing, such as... Figure 1 The terminal and the chip applied to the terminal are shown. In any embodiment of this application, the form of the first and second devices is not limited.

[0235] The first and second devices can be connected via a wireless network; for example, they can be connected via a terrestrial network or a non-terrestrial network. It should be understood that the first and second devices can also be connected via other wireless networks. This document does not impose any limitations.

[0236] The condition can be a region. In this case, the second device can perform S810 in the same way as S710, which will not be elaborated further in this article.

[0237] The form of the condition is not limited to a region. For example, the condition can be time, period, or duration. The second device can determine at least one condition as one hour, two hours, three hours, etc. The at least one condition can be of the same type, such as a regional condition or a time condition; the at least one condition can also be of different types, such as a regional condition and a time condition.

[0238] After determining at least one condition, the second device can send first information, which indicates at least one condition for knowledge sharing. The second device can send the first information periodically or non-periodically. Similarly, the second device can send the first information autonomously or upon request from the first device. In any embodiment of this application, there are no restrictions on how or when the first information is sent.

[0239] Accordingly, for the first device, the following S820 is executed.

[0240] S820, the first device receives first information, wherein the first information indicates at least one condition for knowledge sharing.

[0241] The first piece of information can be any kind of information that indicates at least one condition.

[0242] For example, the first device and the second device store multiple predefined conditions, each condition having an ID, and the first information can be one or more IDs of at least one of the multiple conditions.

[0243] For example, if neither the first nor the second device stores predefined conditions, the second device determines time information and / or location information, and the time information and / or location information is the first information.

[0244] Knowledge sharing describes a scenario where a device transmits a model and / or data to another device, which, upon receiving the model and / or data, performs training or aggregation locally based on the model and / or data. Knowledge sharing also describes a scenario where a device receives a model or data from another device, which, upon receiving the model and / or data, performs training or aggregation locally based on the model and / or data. There are no restrictions on the form of knowledge sharing; as an optional example, knowledge sharing is FL (Flexible Interchange).

[0245] After receiving the first information, the first device may execute the following S830.

[0246] S830, the first device determines the target condition from at least one condition.

[0247] The target conditions may include one or more conditions. Determining multiple conditions at once can save communication and / or computing resources.

[0248] In one alternative implementation, the first device determines the target condition from at least one condition based on the state of the first device and / or the state of the environment.

[0249] When at least one condition is at least one region, the first device can perform S830 in the same way as S730, which will not be described in detail here.

[0250] When at least one condition is a time condition, here are some examples of determining the target region from at least one region.

[0251] Optionally, the state of the first device includes at least one of the following: Storage resources, computing resources, data resources, communication resources, power, position relative to the charging area, and movement status.

[0252] If the first device has sufficient resources (e.g., storage resources, computing resources, data resources, communication resources, and power) to perform knowledge sharing at one or more times, the first device may select one or more times as target conditions. The first device may also select said one or more times as target conditions when it is near a charging area at one or more times. Furthermore, the first device may select said one or more times as target conditions if nearby terminals exhibit similar predictable mobility or behavioral patterns at said one or more times.

[0253] Optionally, the environmental status includes at least one of the following: the form of knowledge sharing, the amount of data associated with knowledge sharing, the data types associated with knowledge sharing, security requirements, and the physical structure of the area.

[0254] When the environmental conditions match the requirements of the first device at one or more times, the first device may select one or more times as the target conditions.

[0255] It should be understood that the first device can use multiple states to select the target conditions. This will not be elaborated further in this article.

[0256] There is no limitation on the form in which the target condition is determined from at least one condition. Determining the target condition based on the state of the first device and / or the environmental state will make the target condition more consistent with the current conditions of the terminal.

[0257] After determining the target conditions, the first device can execute the following S840.

[0258] S840, when the target conditions are met, the first device initiates the first knowledge sharing.

[0259] For example, the target condition is a target area; when the first device is within the target area, the target condition is considered met. As another example, the target condition is a target time; when the target time arrives, the target condition is considered met.

[0260] When the target conditions are met, the first device can execute S840 in the same way as S740, which will not be elaborated further in this article.

[0261] In summary, in method 800, the real world is described as at least one condition, which can be a region or time, etc., from which the terminal selects a target condition. Since the terminal always knows its own state, the target condition is always suitable for the terminal, and sharing knowledge under suitable conditions improves the efficiency of knowledge sharing. Furthermore, the terminal decides when and where to share knowledge, and other nodes in the knowledge-sharing system do not need to determine how to share knowledge, which also reduces the complexity of knowledge sharing.

[0262] In this application, method 700 or 800 can be applied to various application scenarios. Therefore, several implementation methods for different scenarios are exemplarily listed below, and these implementation methods are described in detail below.

[0263] Figure 9 This is a scenario of the knowledge sharing method provided in the embodiments of this application. As shown in the figure, ABCDEFGH represent eight satellites, such as low Earth orbit (LEO) satellites. Ma 1~ Mh 1 represents the model of eight satellites at time 1, where Ma 1 represents the model of satellite A at time 1. Mb 1 represents the model of satellite B at time 1, and so on. Time 1 is any time of day. Figure 9 It also shows the Earth and regions within it.

[0264] These eight satellites are examples of first-hand devices participating in knowledge sharing, such as FL. The challenges of implementing FL on satellites are as follows: Communication overhead.

[0265] In traditional workflows, participants need to periodically share their locally trained models with other participants or a central server. Neither centralized nor decentralized workflows are highly efficient in terms of communication, especially as network size increases.

[0266] Limited resources.

[0267] Satellites may have limited resources, such as power, computing power, and bandwidth.

[0268] Delay.

[0269] Assume the ground station acts as a central aggregator. However, if there is no line-of-sight (LoS) connection between the satellite and the ground station, the satellite must offload its locally trained model to the ground station via a link composed of other satellites. This is resource-inefficient and introduces latency.

[0270] Because satellites exhibit predictable movement behavior, they are used as one embodiment in addressing the aforementioned challenges. In this embodiment: The participating entity that performs FL (example of the first device) is a LEO satellite orbiting the Earth.

[0271] The equipment used to determine at least one area for FL may be a ground station (an example of a second device). Figure 9 (Not shown in the image), the device may also be referred to as an Aggregation Region Recommendation Unit (ARRU), and the at least one region may be referred to as at least one Recommendation Aggregation Region (RAR), which includes Figure 9 The area shown.

[0272] ARRU collects information about the current state of the LEO network and runs an optimization function to find a suitable RAR. The optimization function can use input parameters from one or more categories, such as local parameters specific to the LEO satellites themselves, and external parameters describing the surrounding environment, as shown in Table 1. An example of the optimization function is as follows: F ( p , c , b , f p , f c , f b , t , g , q , s ).

[0273] Table 1

[0274] Some guidelines for designing RARs include, but are not limited to: Rule 1: RAR is located over the sea, ensuring that known satellites reaching the area have sufficient computational resources to aggregate and train the model.

[0275] When the satellite is on the sea surface, there are fewer tasks to be processed, so the available resources on the satellite can be used for model training.

[0276] Guideline 2: RARs should be located close to ground stations so that ground stations can access the model immediately when it is needed.

[0277] Satellites can be used to train models for certain ground applications. Therefore, if a ground application doesn't need the model for a period of time (e.g., the next 24 hours), the model can be sent to the satellite for training during that period. However, if a ground application is awakened at some point and requests the model, it becomes crucial to deliver the model to it as quickly as possible. Therefore, by placing the RAR (Radar Arcade) close to a ground station, the model is practically always accessible, as it can be easily sent down to the ground upon request. This contrasts with the scenario where the RAR is located in the middle of an ocean with no ground station. The ground application requests access to the model. The request is submitted to the nearest ground station. The ground station communicates with the nearest satellite. The nearest satellite communicates with its neighboring satellite closest to the RAR. The request continues to propagate through the satellite network until it reaches the RAR, which collects the model and sends it back to the ground station for use by the ground application.

[0278] Ground stations can be used to generate global models or as gateways to deliver models being trained to owners, which can be terrestrial applications.

[0279] Guideline 3: All satellites will eventually undergo RAR.

[0280] Rule 4: The function considers fairness among participating nodes.

[0281] For example, the location of RAR should be chosen to give all satellites an equal opportunity to pass through. Therefore, all satellites will have an equal chance to participate in knowledge sharing and gain access to the same data.

[0282] Guideline 5 states that the function has power and resource awareness capabilities.

[0283] When designing and generating RARs, the function should take into account information related to power, computation, and data availability, thus giving the proposed function power and resource awareness. Power and resource awareness in a satellite context is based on the fact that LEO satellites have limited access to power and computational resources. The amount of data available for training also varies among them.

[0284] First, power resources.

[0285] LEO satellites rely on a combination of batteries and solar power to operate their components. Therefore, the amount of power available to an LEO satellite varies depending on load conditions, satellite location, and time of day. For example, if a satellite is over a continent like North America during the day, the expected traffic volume it needs to support may be high. During this period, all LEO power resources will be dedicated to carrying network data. When the satellite leaves the North American region and enters ocean airspace, the available power resources are likely to have been largely consumed. Such satellites cannot immediately participate in model training. They first need to receive sunlight to recharge their batteries.

[0286] Second, computing resources.

[0287] Given the limited computing resources of LEO satellites, these resources will likely be dedicated to a single function, either hosting network data or participating in model training and knowledge-sharing activities. Therefore, a good RAR generation function should take into account the availability of computing resources.

[0288] Finally, data access.

[0289] For any AI application, access to abundant data is crucial. Therefore, LEO satellites, which possess data, are ideal over other types of satellites. Satellites can acquire training data in various ways, such as through onboard sensors, transmission from ground stations, or sharing with neighboring satellites. When over the ocean, the amount of available data is limited. Therefore, a good RAR (Rapid Application Analyzer) will be positioned in areas where satellites possess a large amount of data that can be used to enhance knowledge.

[0290] Guideline 6: Other factors may also be considered when determining RAR.

[0291] First, communication.

[0292] Knowledge sharing requires data communication between clients. Therefore, RARs should not be located in areas where communication bandwidth has been used for other purposes and there are no remaining resources available for clients to participate in knowledge sharing. However, since bandwidth utilization changes over time, RARs can be designed accordingly by predicting future bandwidth resources.

[0293] Second, time.

[0294] Similarly, time is also an important factor. Satellites need sunlight to charge their batteries. However, the time of day for sunlight exposure is determined by the time of day. Therefore, if it is known that the satellite will receive sunlight an hour later, it might be best to design a RAR that is "more than an hour" away from the satellite's current location to ensure that it will have the power needed to participate in knowledge sharing.

[0295] Finally, channel quality.

[0296] Channel quality affects the accuracy of transmitted data. If channel quality is poor, knowledge shared between satellites may be lost during transmission due to noise and low channel quality. Therefore, RAR should take this into account. This may also affect the type of knowledge-sharing paradigm used.

[0297] It should be understood that the dissemination of information and details describing RAR can be accomplished in various ways: directly from ARRU to satellite, via network routing in a manner similar to the Internet, through peer-to-peer communication, etc.

[0298] Satellites can obtain any RAR information through active querying or passive reception, and can use this information to decide which RAR to join. For example, if a satellite is looking for a more energy-efficient knowledge-sharing paradigm, it can decide to use a centralized FL's RAR.

[0299] Satellites can assess their own status and decide whether to join or skip a particular RAR. Skipping may be due to their own reasons, such as the satellite's current power level, computing resources, storage resources, future state in terms of load conditions, and position relative to the RAR; it may also be due to reasons related to the RAR, such as the amount of knowledge in the RAR, the type of knowledge, and the knowledge-sharing paradigm used.

[0300] Back Figure 9 The region in question is a RAR defined using an optimization function executed by ARRU, and was selected by these eight satellites as the target region for knowledge sharing. For simplicity, in Figure 9 In this configuration, a RAR can only have one satellite at a time (i.e., satellite B). Over time, satellite B will leave the RAR, while satellite A will enter the RAR, and so on. Figure 10 As shown.

[0301] Knowledge sharing occurs between satellites, and for the same reasons mentioned above, it is assumed that knowledge sharing is achieved by allowing only one satellite to send its model to the previous satellite. For example... Figure 10 As shown, knowledge sharing occurs between satellite B and satellite A.

[0302] For example, when satellite A is in RAR, it requests a model from satellite B (shown as...) ), and combine the model with its own model (shown as Aggregate the data to generate a more knowledge-rich model (shown as...). Then, satellite A will train the aggregated model while it is within the RAR. Finally, satellite A will leave the RAR, and satellite H will enter the RAR, as... Figure 11As shown. Once satellite H is in RAR, it requests the aggregated and trained model (shown as) from satellite A. ), and its pattern (shown as Aggregation to generate a more knowledge-rich model (shown as) The process continues. In this scheme, a more knowledge-rich version of the model will always remain in the RAR.

[0303] For example, a satellite might be included in RAR but decide not to participate in knowledge sharing. If such a scenario occurs... Figure 10 or Figure 11 In the simplified scenario presented, the satellite receives the model from the satellite in the preceding RAR, but does not aggregate the model with its own model. Essentially, it merely acts as a storage device for the most knowledge-rich model after aggregation. Once it leaves the RAR, it sends the model to the next satellite entering the RAR. If the next satellite also decides not to participate, it does not aggregate its model into the most knowledge-rich model, but merely retains it. And so on. Furthermore, if a satellite arriving at the RAR has decided not to participate in knowledge sharing, it can choose not to store the model for subsequent satellites. If such a scenario occurs, the satellite possessing the most knowledge-rich model can choose to send the model down to the ground station for storage until a satellite arrives at the RAR and requests the model. In this case, the ground station is the second device as described in Aspects 2 and 4 (in... Figures 9 to 11 (not shown in the image), but it is used as knowledge storage until the next device requests the knowledge.

[0304] It needs to be emphasized that, Figures 9 to 11 The scenarios presented are merely simplified examples to illustrate this idea. Other embodiments are also possible in the satellite field.

[0305] Figure 12 This is another scenario of the knowledge-sharing method provided in this application's embodiments. As shown in the figure, a car is traveling on a highway or street with exits / entrances. Since cars in cities have predictable movement and behavior on streets / highways, a car is introduced as one example in this embodiment to address the challenges of performing FL (Follow-up Function), such as the communication overhead and limited resources mentioned above. In this embodiment: The participant entity that performs FL (example of the first device, such as...) Figure 12 (As shown) are cars on the street.

[0306] ARRU may be an example of BS (second device), such as Figure 12 (As shown).

[0307] ARRU collects information about the current state of the V2X network (e.g., traffic behavior, user behavior, time of day, available resources, etc.) and runs an optimization function to find a suitable RAR. The optimization function can use input parameters from one or more categories, such as local parameters specific to the LEO satellite itself, as well as external parameters describing the surrounding environment, as shown in Table 1.

[0308] ARRU determines the RAR on the path based on the above inputs and the collected information. For example... Figure 12 As shown, these RARs can be of any shape. As previously mentioned, a RAR can be a geographic location or any content that indicates favorable conditions for knowledge sharing.

[0309] ARRU then publishes information about RARs. Vehicles entering these RARs can decide to participate in knowledge-sharing processes (e.g., federated learning).

[0310] Because a car possesses information about all the RARs (Rays) in front of it, it can plan ahead. For example, in Figure 12 In this scenario, a vehicle may choose to participate in federated learning in RAR2 rather than in RAR1 based on its current conditions and available resources. This could be because the knowledge provided by RAR2 is more valuable to the vehicle than the knowledge provided by RAR1, or the vehicle may not have sufficient memory / computing / power resources to participate in knowledge sharing in RAR1, but will have sufficient memory / computing / power resources to participate in knowledge sharing in RAR2.

[0311] It should be emphasized that the difference between RAR1 and RAR2 mentioned above is just an example. The differences between RARs can be in size, location, amount of knowledge, type of knowledge, trust level, etc.

[0312] All cars exhibit predictable motion behavior. They cannot change direction or disappear from the road. Therefore, they will all eventually undergo RAR and participate in federated learning, enabling them to learn a fair global model.

[0313] Vehicles can also submit queries to ARRU to gather information of interest about a specific RAR, any RARs previously notified on its route, or RARs at a specific location of interest.

[0314] For example, an electric vehicle might be interested in knowledge sharing near the end of its journey, ideally near the last charging station at its final destination. The vehicle could submit a discovery query to the ARRU to identify potential RAR candidates of interest.

[0315] Figure 12The concept proposed can be integrated into navigation systems and used as a route selection preference parameter. Within a navigation system, preferences can be set to select routes to a destination. For example, some people might be interested in the most fuel-efficient route, while others prefer the fastest route. Similarly, RAR can be used to set route preferences.

[0316] On the one hand, one might want to take a route with the highest knowledge content and the least amount of RAR, because they want to train their model in the most energy-efficient way.

[0317] On the other hand, since knowledge sharing is a two-way process—one can both learn from and teach others—a car possessing a wealth of shareable knowledge can choose to take a route with less knowledge. This car can leverage its advantage by traversing a less knowledge-intensive route, selling its knowledge to other cars traveling along that route. Furthermore, this also benefits navigation systems. By recommending those with abundant knowledge to travel through less knowledge-intensive areas, a more balanced knowledge map is created, which helps to balance business across different routes.

[0318] The above text has already shown two possible scenarios for knowledge sharing; now we will combine them with the following... Figure 13 The flowchart illustrates the set of possible steps between ARRU and a participant in the proposed method.

[0319] exist Figure 13 In the illustrated embodiment, it is assumed that the ARRU participates in the model training process. In other embodiments, the ARRU may only be responsible for collecting a specific set of relevant information (which may be sufficient and necessary for determining the optimal RAR) and for sharing RAR information with participating clients periodically or upon request. The collected information may be directly related to model performance, or only related to the periodic behavior of participants, or a combination of both. The method of collecting information is considered implementation-dependent and is beyond the scope of this invention.

[0320] When the method starts, ARRU initializes the model, which can be either a centralized or decentralized FL model. ARRU then sends this model to all participants. Participants train the model locally.

[0321] ARRU collects information and runs functions to find a suitable RAR, which is then shared with all participants.

[0322] After receiving information about the RAR, each participant begins planning to find a target RAR. Then, participants access the target RAR and share their local models.

[0323] The local model can be aggregated in ARRU to update and obtain a new global model. ARRU determines whether the global model has converged or whether its training has reached the maximum number of training epochs. If the global model has converged or its training has reached the maximum number of training epochs, ARRU terminates the method. If the global model has not converged and its training has not reached the maximum number of training epochs, ARRU performs the step of sending the current model to all participants.

[0324] It should be understood that Figure 13 This is a possible schematic diagram of the steps. Depending on the embodiment, all or some of these steps may be required.

[0325] The examples of methods provided in the embodiments of this application have been described in detail above. It should be understood that, in order to achieve the above functions, the corresponding device includes corresponding hardware structures and / or software modules for implementing each function. It will be apparent to those skilled in the art that, in conjunction with the units and algorithm steps of the examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether the function is executed in hardware or by computer software driving hardware execution depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0326] Figure 14 and Figure 15 These are two schematic diagrams of the knowledge-sharing device provided in the embodiments of this application. They can be used to implement the functions of the terminal or BS in the above method embodiments, and therefore also have the beneficial effects of the above method embodiments. In the embodiments of this application, these devices can be as follows: Figure 1 The terminal or BS shown can also be a module (e.g., a chip) applied to the terminal or BS.

[0327] like Figure 14 As shown, the device 1400 includes a processing unit 1410 and a transceiver unit 1420. The transceiver unit 1420 performs receiving and / or sending steps under the control of the processing unit 1410, wherein the transceiver unit 1420 is a sending unit when performing the sending step and a receiving unit when performing the receiving step. The device 1400 is used to implement the functions of a terminal or BS in the above method embodiments.

[0328] When device 1400 is used to achieve Figure 7When the first device in the described method embodiment functions, the transceiver unit 1420 is configured to: receive first information, wherein the first information indicates at least one region for knowledge sharing; the processing unit 1410 is configured to: determine a target region from the at least one region; and initiate first knowledge sharing when the device 1400 is within the target region.

[0329] Optionally, the processing unit 1410 is also configured to perform: determining a target region from at least one region based on the state of the device 1400 and / or the state of the target region.

[0330] Optionally, the transceiver unit 1420 is also used to perform: sending first knowledge.

[0331] Optionally, the transceiver unit 1420 is further configured to perform: receiving second knowledge when the device 1400 is within the target area; the processing unit 1410 is further configured to perform: determining first knowledge by learning the second knowledge.

[0332] Optionally, the transceiver unit 1420 is also used to perform: receiving third-party knowledge.

[0333] Optionally, the transceiver unit 1420 is further configured to perform the following operations: receive third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0334] Optionally, the transceiver unit 1420 is further configured to perform the following operations: send fourth information, wherein the fourth information is used to acquire one or more knowledge-sharing regions on the trajectory of the device 1400, or the fourth information is used to suggest one or more knowledge-sharing regions on the trajectory of the device 1400.

[0335] Optionally, the processing unit 1410 is further configured to: stop the first knowledge sharing when the device 1400 is outside the target area, or when the first knowledge sharing is completed, or when the stopping criteria determined by the device 1400 are met, or when the stopping criteria included in the received third information are met.

[0336] When device 1400 is used to achieve Figure 7 When the second device in the described method embodiment functions, the processing unit 1410 is configured to perform: determining at least one region, wherein the at least one region is used for knowledge sharing; and the transceiver unit 1420 is configured to perform: sending first information, wherein the first information indicates the at least one region.

[0337] Optionally, the processing unit 1410 is further configured to perform the following operations: acquire second information, wherein the second information indicates the state and / or environmental state of at least one first area; and determine the at least one condition based on the second information.

[0338] Optionally, the transceiver unit 1420 is further configured to perform the following operation: send third information, wherein the third information indicates the type of the first knowledge share and / or the order of the first knowledge share.

[0339] Optionally, the transceiver unit 1420 is further configured to perform the following operations: receive fourth information from the first device, wherein the fourth information is used to obtain one or more knowledge-sharing regions on the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing conditions on the trajectory of the first device; and send the first information according to the fourth information, wherein at least one region is a region on the trajectory of the first device.

[0340] Optionally, the at least one region includes a target region, and the transceiver unit 1420 is further configured to perform the following operations: when the first device is within the target region, receive first knowledge from the first device; and / or when the first device is within the target region, send the first knowledge to a third device.

[0341] When device 1400 is used to achieve Figure 8 When the first device in the described method embodiment functions, the transceiver unit 1420 is configured to: receive first information, wherein the first information indicates at least one condition for knowledge sharing; and the processing unit 1410 is configured to: determine a target condition from the at least one condition; and when the target condition is met, initiate first knowledge sharing.

[0342] Optionally, the processing unit 1410 is further configured to perform: determining a target condition from at least one condition based on the state of the device 1400 and / or the state of the target area.

[0343] Optionally, the transceiver unit 1420 is also used to perform: sending first knowledge.

[0344] Optionally, the transceiver unit 1420 is also configured to: receive second knowledge when the target condition is met; the processing unit 1410 is also configured to: determine first knowledge by learning the second knowledge.

[0345] Optionally, the transceiver unit 1420 is also used to perform: receiving third-party knowledge.

[0346] Optionally, the transceiver unit 1420 is further configured to perform the following operations: receive third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

[0347] Optionally, the transceiver unit 1420 is further configured to perform the following operations: send fourth information, wherein the fourth information is used to obtain one or more knowledge-sharing conditions related to the device 1400, or the fourth information is used to suggest one or more knowledge-sharing conditions related to the device 1400.

[0348] Optionally, the processing unit 1410 is further configured to: stop the first knowledge sharing when the target condition is not met, or when the first knowledge sharing is completed, or when the stopping criterion determined by the first device is met, or when the stopping criterion included in the received third information is met.

[0349] When device 1400 is used to achieve Figure 8 When the second device in the described method embodiment functions, the processing unit 1410 is configured to perform: determining at least one condition, wherein the at least one condition is for knowledge sharing; and the transceiver unit 1420 is configured to perform: sending first information, wherein the first information indicates the at least one condition.

[0350] Optionally, the processing unit 1410 is further configured to perform the following operations: acquire second information, wherein the second information indicates the state and / or environmental state of at least one first device; and determine the at least one condition based on the second information.

[0351] Optionally, the transceiver unit 1420 is further configured to perform the following operation: send third information, wherein the third information indicates the type of the first knowledge share and / or the order of the first knowledge share.

[0352] Optionally, the transceiver unit 1420 is further configured to perform the following operations: receive fourth information from the first device, wherein the fourth information is used to obtain one or more knowledge-sharing conditions related to the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing conditions related to the trajectory of the first device; and send the first information according to the fourth information, wherein at least one condition is a condition related to the trajectory of the first device.

[0353] Optionally, the at least one condition includes a target condition, and the transceiver unit 1420 is further configured to perform the following operations: when the first device satisfies the target condition, receive first knowledge from the first device; and / or when the first device satisfies the target condition, send the first knowledge to the third device.

[0354] Device 1400 can be a terminal or a BS. Processing unit 1410 can be implemented in hardware or software. When processing unit 1410 is implemented in hardware, it can be a logic circuit, integrated circuit, etc. When processing unit 1410 is implemented in software, it can be a general-purpose processor that reads software code stored in a memory unit. The memory unit can be integrated into processing unit 1410 or located outside processing unit 1410 and exist independently.

[0355] like Figure 15 As shown, device 1500 includes a processor 1510 and interface circuitry 1520. The processor 1510 and interface circuitry 1520 are coupled to each other. It should be understood that interface circuitry 1520 may be a transceiver or an input-output interface. Optionally, device 1500 may further include a memory 1530 for storing instructions executed by the processor 1510, or storing input data required for the processor 1510 to execute instructions, or storing data generated after the processor 1510 executes instructions.

[0356] When device 1500 is used to achieve Figure 7 or Figure 8 In the method shown, the processor 1510 is used to implement the functions of the processing unit 1410, and the interface circuit 1520 is used to implement the functions of the transceiver unit 1420.

[0357] When device 1500 is a terminal chip (i.e., a chip applied to a terminal), the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receiving information from the BS can be understood as the information first being received by other modules in the terminal (e.g., an RF module or antenna), and then sent to the terminal chip by these modules. The terminal chip sending information to the BS can be understood as the information first being sent by other modules in the terminal (e.g., an RF module or antenna), and then sent to the BS by these modules.

[0358] When device 1500 is a BS chip (i.e., a chip applied to a BS), the BS chip implements the functions of the BS in the above method embodiments. The BS chip receiving information from the terminal can be understood as the information first being received by other modules in the BS (e.g., an RF module or antenna), and then sent to the BS chip by these modules. The BS chip sending information to the terminal can be understood as the information first being sent by other modules in the BS (e.g., an RF module or antenna), and then sent to the terminal by these modules.

[0359] In this application, entity A sends information to entity B, either directly from A to B or via other entities. Similarly, entity B receives information from entity A, either directly from B to A or via other entities. Here, entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be information interaction between a RAN node and a terminal, such as information interaction between a BS and a terminal. Information transmission and reception can also be information interaction between two RAN nodes, such as information interaction between a CU and a DU. Information transmission and reception can also be information interaction between different modules within a device, such as information interaction between a terminal chip and other modules within the terminal, or information interaction between a BS chip and other modules within the BS.

[0360] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSPs), ASICs, FPGAs, or any other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0361] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor.

[0362] The above embodiments can be implemented, in whole or in part, by instructions, software, hardware, firmware, or any combination thereof.

[0363] When implemented via instructions, the instructions may consist of corresponding software modules, which may be stored in a computer-readable storage medium. The computer-readable storage medium may be a volatile storage medium or a non-volatile storage medium, or may include both types. Non-volatile storage media may be flash memory, a hard disk, a portable hard disk, a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or any other form of non-volatile storage medium known in the art. The volatile storage medium can be random access memory (RAM). By way of illustration and not limitation, many forms of RAM can be used, such as registers, static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), or any other form of volatile storage medium known in the art.

[0364] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a BS or terminal. The processor and storage medium can also exist as discrete components in the BS or terminal.

[0365] When implemented in software, it can be implemented wholly or partially as a computer program product. A computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are executed. The computer may be a general-purpose computer, a specific computer, a computer network, a network device, a UE, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another via wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; or an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive.

[0366] Finally, regarding the embodiments of this application, a few points should be made: First, in the embodiments of this application, the terms "first," "second," and various numerical designations are merely for descriptive purposes and are not intended to limit the scope of the embodiments of this application. For example, "first information" and "third information" represent two pieces of information, which can be two different pieces of information or the same pieces of information.

[0367] Secondly, in the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be indicated. In specific implementations, there are many ways to indicate the information to be indicated. For example, the information to be indicated can be directly indicated, such as the information to be indicated itself or an index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed upon in advance. For example, the indication of the information to be indicated can be achieved by pre-agreeing (e.g., by an agreement specifying) whether information elements exist, thereby reducing the indication overhead to a certain extent.

[0368] Third, the “protocol” mentioned in the embodiments of this application may be a standard protocol in the field of communication, such as the Long Term Evolution (LTE) protocol, the New Radio (NR) protocol and related protocols in future communication systems, but this application is not limited to these.

[0369] Fourth, "predefined" or "preconfigured" can be achieved by pre-storing corresponding instruction-related information codes, tables, or other means in the device (e.g., terminal or BS). This application does not limit the specific implementation method. "Storage" can mean being stored in one or more memories, which can be set up separately or integrated into the processor or communication device. The one or more memories can also be partially set up separately and partially integrated into the processor or communication device. The type of memory can be any form of storage medium, and this application is not limited to this.

[0370] Fifth, "at least one" means one or more, and "multiple" means two or more. "And / or" refers to the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, B alone, and A and B simultaneously, where A and B can be single objects or multiple objects respectively. The character " / " usually indicates that the related objects are in an "OR" relationship. "At least one of the following" or similar expressions indicate any combination of these items, including any combination of single or compound items. For example, at least one of a, b, and c can be represented as: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c. Here, a, b, and c can be single objects or multiple objects respectively.

[0371] Sixth, in the embodiments of this application, "when," "when," "under what circumstances," and "if" all refer to the objective circumstances under which the device (e.g., a terminal or BS) will perform corresponding processing. They do not limit the time, nor do they require the device to have a judgment action during execution, nor do they imply any other limitations.

[0372] Seventh, in the various embodiments of this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The applicant hereby separately discloses each individual feature described herein and any combination of two or more such features. With ordinary knowledge of those skilled in the art, such features or combinations can be implemented as a whole according to this specification, regardless of whether such features or combinations of features solve any problem disclosed herein; and without limiting the scope of the claims. In view of the foregoing description, those skilled in the art will clearly find that various modifications can be made within the scope of this invention.

[0373] Eighth, although the present invention has reference to illustrative embodiments, it is not intended to be interpreted in a limiting sense. Therefore, the specification and drawings are to be regarded only as illustrative of some embodiments of the invention as defined by the appended claims, and are intended to cover any and all modifications, variations, combinations, or equivalents falling within the scope of the invention. Thus, while various embodiments and potential advantages have been described in detail, various changes, substitutions, and alterations can be made without departing from the invention as defined by the appended claims. Furthermore, the scope of this application is not limited to the specific embodiments of the processes, machines, articles of manufacture, compositions of matter, components, methods, and steps described in the specification. Based on the disclosure of the present invention, those skilled in the art will readily understand that processes, machines, articles of manufacture, compositions of matter, components, methods, or steps (including those currently existing or later developed) that perform substantially the same functions or achieve substantially the same results as the corresponding embodiments described herein can be used according to the present invention. Accordingly, the scope of the appended claims is intended to include such processes, machines, articles of manufacture, compositions of matter, components, methods, or steps.

Claims

1. A knowledge-sharing method applied to a first device, characterized in that, The method includes: Receive first information, wherein the first information indicates at least one area for knowledge sharing; Determine the target region from the at least one region; When the first device is within the target area, the first knowledge sharing is initiated.

2. The method according to claim 1, characterized in that, Determining the target region from the at least one region includes: The target region is determined from the at least one region based on the state of the first device and / or the state of the target region.

3. The method according to claim 2, characterized in that, The state of the first device includes at least one of the following: Storage resources, computing resources, data resources, communication resources, power consumption, position relative to the target area, position relative to the charging area, and movement status; The state of the target area includes at least one of the following: The knowledge sharing format, the amount of data related to knowledge sharing, the data types related to knowledge sharing, security requirements, and the physical structure of the target area.

4. The method according to any one of claims 1 to 3, characterized in that, Launching First Knowledge Sharing includes: Sending the first piece of knowledge.

5. The method according to claim 4, characterized in that, The method further includes: When the first device is within the target area, it receives the second knowledge. By learning the second knowledge, the first knowledge is determined.

6. The method according to any one of claims 1 to 5, characterized in that, Launching First Knowledge Sharing includes: Receive third-party knowledge.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Receive third information, wherein the third information indicates the type of the first knowledge sharing and / or the order of the first knowledge sharing.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Send a fourth message, wherein the fourth message is used to obtain one or more knowledge-sharing regions on the trajectory of the first device, or the fourth message is used to suggest one or more knowledge-sharing regions on the trajectory of the first device.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: The first knowledge sharing is stopped when the first device is located outside the target area, or when the first knowledge sharing is completed, or when the stopping criteria determined by the first device are met, or when the stopping criteria included in the received third information are met.

10. The method according to any one of claims 1 to 9, characterized in that, The target area includes one or more areas.

11. A knowledge-sharing method applied to a second device, characterized in that, The method includes: Identify at least one region, wherein the at least one region is used for knowledge sharing; Send a first message, wherein the first message indicates the at least one region.

12. The method according to claim 11, characterized in that, The method further includes: Acquire second information, wherein the second information indicates the state of at least one first device and / or the environmental state; Determining at least one region includes: The at least one region is determined based on the second information.

13. The method according to claim 12, characterized in that, The state of the at least one first device includes at least one of the following: Storage resources, computing resources, data resources, communication resources, power consumption, trajectory, position relative to the charging area, and movement status; The environmental state includes at least one of the following: Time, geographical location, location of the second device, communication quality, traffic location, type of knowledge data, and current amount of knowledge.

14. The method according to any one of claims 11 to 13, characterized in that, The method further includes: Send a third message, wherein the third message indicates the type of the first knowledge share and / or the order of the first knowledge share.

15. The method according to any one of claims 11 to 14, characterized in that, The method further includes: Receive fourth information from the first device, wherein the fourth information is used to obtain one or more knowledge-sharing regions on the trajectory of the first device, or the fourth information is used to suggest one or more knowledge-sharing regions on the trajectory of the first device; The first message sent includes: The first information is sent according to the fourth information, wherein the at least one region is the region on the trajectory of the first device.

16. The method according to any one of claims 11 to 15, characterized in that, The at least one region includes a target region, and the method further includes: When the first device is within the target area, the first knowledge is received from the first device; and / or When the first device is within the target area, it sends the first knowledge to the third device.

17. A knowledge-sharing device, characterized in that, The device includes: At least one processor coupled to at least one memory storing instructions, which, when executed by the at least one processor, cause the device to: Perform the method according to any one of claims 1 to 16.

Images