Resource configuration method, terminal device, and network device

Abstract

Provided are a resource configuration method, a terminal device, and a network device. The method comprises: a terminal device receives resource configuration information sent by a network device, the resource configuration information comprising first information and second information, wherein the first information is used for indicating time-domain position information and time-domain length information of a first time-domain resource, the first time-domain resource is used for bearing a first physical channel, and the second information is used for indicating AI / ML configuration information associated with the first physical channel.

Description

Resource configuration method, terminal device and network device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a resource configuration method, terminal equipment, and network equipment. Background Art

[0002] With the development of communication technology, wireless communication systems have gradually introduced artificial intelligence / machine learning (AI / ML) processing solutions to replace traditional non-AI / ML processing solutions. In air interface technology, terminal devices can process (receive or transmit) physical channels based on AI / ML models. The time domain resources corresponding to the physical channels are different, and the AI / ML processing solutions suitable for the time domain resources (or the physical channels transmitted within the time domain resources) may also be different. Therefore, how to avoid mismatches between the time domain resources of the physical channels and the AI / ML processing solutions is a problem that needs to be solved.

[0003] Summary of the Invention

[0004] This application provides a resource configuration method, terminal device, and network device. The following introduces various aspects involved in this application.

[0005] In a first aspect, a resource configuration method is provided, including: a terminal device receives resource configuration information sent by a network device, the resource configuration information including first information and second information; wherein, the first information is used to indicate time domain position information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein, the second information is used to indicate AI / ML configuration information associated with the first time domain resource.

[0006] According to a second aspect, a resource configuration method is provided, including: a network device sends resource configuration information to a terminal device, the resource configuration information including first information and second information; wherein, the first information is used to indicate time domain position information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein, the second information is used to indicate AI / ML configuration information associated with the first time domain resource.

[0007] According to a third aspect, a terminal device is provided, including: a first communication unit for receiving resource configuration information sent by a network device, the resource configuration information including first information and second information; wherein, the first information is used to indicate time domain position information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein, the second information is used to indicate AI / ML configuration information associated with the first time domain resource.

[0008] In a fourth aspect, a network device is provided, including: a first communication unit, used to send resource configuration information to a terminal device, the resource configuration information including first information and second information; wherein, the first information is used to indicate the time domain position information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein, the second information is used to indicate the AI / ML configuration information associated with the first time domain resource.

[0009] In a fifth aspect, a terminal device is provided, comprising a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the method of the first aspect.

[0010] In a sixth aspect, a network device is provided, comprising a processor, a memory, and a transceiver, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the network device executes part or all of the steps in the method of the second aspect.

[0011] In a seventh aspect, a device is provided, comprising a processor for calling a program from a memory so that the device executes the method as described in the first aspect or the second aspect.

[0012] In an eighth aspect, a chip is provided, comprising a processor for calling a program from a memory so that a device equipped with the chip executes the method described in the first aspect or the second aspect.

[0013] In a ninth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0014] In a tenth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method as described in the first aspect or the second aspect.

[0015] In an eleventh aspect, a computer program is provided, wherein the computer program enables a computer to execute the method as described in the first aspect or the second aspect.

[0016] The embodiment of the present application establishes a correspondence between the first information (time domain resource configuration information) and the second information (AI / ML configuration information) in the resource configuration information, thereby binding the AI / ML configuration information to a specific time domain resource to avoid a mismatch between the time domain resource and the AI / ML processing solution, thereby improving the reliability of the wireless communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 is a system architecture diagram of a wireless communication system to which an embodiment of the present application may be applied.

[0018] FIG2 is a schematic diagram of a model selection scheme provided by related art.

[0019] FIG3 is a flow chart of a resource configuration method provided in an embodiment of the present application.

[0020] FIG4 is an example diagram of a downlink scheduling scenario provided by an embodiment of the present application.

[0021] FIG5 is an example diagram of a downlink scheduling scenario provided by another embodiment of the present application.

[0022] FIG6 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0023] FIG7 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0024] FIG8 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0025] FIG9 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0026] FIG10 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0027] FIG11 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0028] FIG12 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0029] FIG13 is an example diagram of a downlink scheduling scenario provided in another embodiment of the present application.

[0030] FIG14 is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application.

[0031] FIG15 is a schematic diagram of the structure of the network device provided in an embodiment of the present application.

[0032] FIG16 is a schematic structural diagram of a device to which an embodiment of the present application can be applied. DETAILED DESCRIPTION

[0033] Figure 1 is a diagram illustrating an example of the system architecture of a wireless communication system 100 to which an embodiment of the present application may be applied. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide network coverage for a specific geographical area and may communicate with the terminal device 120 located within the coverage area. The terminal device 120 may access a network (e.g., a wireless network) through the network device 110. Optionally, the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.

[0034] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: 5G system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0035] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects, and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the terminal device can be used to act as a base station. For example, the terminal device can act as a scheduling entity that provides sidelink signals between terminal devices in vehicle to everything (V2X) or device to device (D2D). For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through a base station.

[0036] The network device in the embodiment of the present application may be a device for communicating with a terminal device. The network device may be, for example, an access network device or a wireless access network device. For example, the network device may be a base station. The base station may broadly cover the following various names, or be replaced with the following names: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmitting point (TP), home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, base band unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. The base station may be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof.

[0037] The foregoing describes in detail the wireless communication system to which the embodiments of the present application can be applied. The air interface (Uu interface) system is an important component of the wireless communication system. With the development of technology, the industry has begun to study the application of AI / ML models in air interface systems (such as 5G / 6G air interface systems). The study believes that for certain functions (functionality) or features (feature) of the air interface, the processing solution based on the AI / ML model (referred to as the AI / ML processing solution) may obtain certain performance gains compared with the traditional processing solution (i.e., non-AI / ML processing solution). Therefore, in future air interface systems, in suitable scenarios, for a certain function or feature, the AI / ML model can be activated or selected, thereby using the AI / ML processing solution instead of the traditional processing solution, thereby obtaining performance gains.

[0038] For example, if an AI / ML model exists for a function or feature, the network device can configure a set of AI / ML models available for activation based on the capabilities of the terminal device (such as AI / ML model 1 and AI / ML model 2 as shown in Figure 2). The network device can then select or activate an AI / ML model from the set of AI / ML models for use by the terminal device.

[0039] If the AI / ML model is an AI / ML model specifically optimized for a deployment scenario, there may be multiple AI / ML models for a function or feature, and different AI / ML models may be suitable for different deployment scenarios. When the network device detects that a certain AI / ML model is not working well, the network device can instruct the terminal device to switch to another AI / ML model. This process can be called model switching. For example, as the terminal device moves, the terminal device can switch from one cell to another. The situations in different cells may be different, so the AI / ML model originally used by the terminal device may have performance deterioration problems in the new cell. In this case, once the network device detects that the performance of the AI / ML model has deteriorated, the AI / ML model used by the terminal device can be switched to another AI / ML model to adapt to the new cell environment.

[0040] In air interface systems, AI / ML processing solutions can be applied to the processing of physical channels (such as data channels at the physical layer) to improve the performance of physical channel reception or transmission. For example, channel encoding / decoding can be performed based on AI / ML models, thereby improving channel encoding and decoding performance. Another example is that signal modulation / demodulation can be performed based on AI / ML models to increase the flexibility of signal modulation / demodulation.

[0041] Different physical channels correspond to different time domain resources, and the AI / ML processing schemes suitable for these time domain resources (or the physical channels transmitted within these time domain resources) may also vary. In related technologies, AI / ML configuration information and the time domain resource configuration information for the physical channels are configured separately. This configuration method can easily lead to a mismatch between the AI / ML configuration information and the time domain resources of the physical channels, thereby reducing the reliability of the wireless communication system.

[0042] For example, the network device will pre-configure a variety of time domain resource configuration information (corresponding to a variety of time domain resources of the physical channel) for the terminal device based on radio resource control (RRC) signaling, and indicate the time domain resource configuration information currently used by the terminal device through downlink control information (DCI). If the time domain resource indicated by the DCI is in the same time slot as the DCI, the terminal device may not have time to load the AI / ML model or can only load an AI / ML model with a simple algorithm; for example, if the time domain resource indicated by the DCI is in a different time slot from the DCI, the terminal device can load more or more AI / ML models with more complex algorithms, thereby improving the processing performance of the physical channel. It can be seen that different time domain resources may be suitable for different AI / ML processing schemes. In the above scenario, if the network device instructs the terminal device to use an inappropriate AI / ML processing scheme, the terminal device may not have time to process the physical channel within a limited time, thereby reducing the reliability of the wireless communication system.

[0043] It can be seen from this that how to ensure the adaptability of AI / ML configuration information and the time domain resources of the physical channel, thereby improving the reliability of the wireless communication system, is a problem that needs to be solved. To address this problem, the embodiment of the present application introduces a correspondence between time domain resource configuration information and AI / ML configuration information in the resource configuration information of the physical channel, thereby binding the AI / ML configuration information to specific time domain resources. Based on this binding relationship, the mismatch between the time domain resources of the physical channel and the AI / ML processing solution can be avoided, thereby improving the reliability of the wireless communication system.

[0044] The following is a detailed description of the embodiments of the present application.

[0045] FIG3 is a flow chart of a resource configuration method according to an embodiment of the present application. The method of FIG3 can be executed by a terminal device and a network device. The terminal device can be, for example, the terminal device 120 mentioned above, and the network device can be, for example, the network device 110 mentioned above.

[0046] Referring to Figure 3, in step S310, the terminal device receives resource configuration information sent by the network device. The resource configuration information may be resource configuration information of a first physical channel. The first physical channel mentioned here may be any type of physical channel suitable for processing using an AI / ML processing solution. Exemplarily, the first physical channel is a data channel, such as a physical downlink shared channel (PDSCH), a physical uplink shared channel (PUSCH), or a physical sidelink shared channel (PSSCH).

[0047] The resource configuration information may be used to configure the time domain resources of the first physical channel. Therefore, the resource configuration information may also be referred to as the time domain resource configuration information or time domain resource allocation information of the first physical channel. The resource configuration information may be, for example, RRC configuration information or a system information block (SIB).

[0048] The resource configuration information may include first information. The first information may be one of multiple types of time domain resource configuration information included in the resource configuration information. The first information may be used to indicate a first time domain resource (used to carry a first physical channel). For ease of description, the first information will be referred to as the first time domain resource configuration information below. It should be understood that in the embodiments of the present application, the first information and the first time domain resource configuration information may be interchangeable if there is no conflict.

[0049] The embodiment of the present application does not specifically limit the content of the first time domain resource configuration information, as long as it can indicate the time domain resources of the first physical channel. In some implementations, the first time domain resource configuration information may include time domain location information and / or time domain length information of the first time domain resources.

[0050] The time domain location information of the first time domain resource may include one or more of the following: a starting time slot of the first time domain resource, and a starting symbol of the first time domain resource.

[0051] The time domain length information of the first time domain resource may include one or more of the following: the number of time slots occupied by the first time domain resource, and the number of symbols occupied by the first time domain resource.

[0052] Taking PDSCH or PUSCH as an example, the first time domain resource configuration information may include one or more of the following three parameters: parameter K, parameter S, and parameter L. Parameter K represents the time slot displacement from the physical downlink control channel (PDCCH) to the PDSCH / PUSCH scheduled by the PDCCH. Parameter S represents the starting symbol of the PDSCH / PUSCH in the scheduled time slot. Parameter L represents the length (or number of symbols) of the PDSCH / PUSCH. Parameters K and S correspond to the time domain position information mentioned above. Parameter L corresponds to the time domain length information mentioned above.

[0053] In addition to the first time domain resource configuration information, the resource configuration information may also include second information corresponding to the first time domain resource configuration information. The second information is (or is used to indicate) the AI / ML configuration information associated with the first time domain resource. For ease of understanding, the second information will be referred to as the AI / ML configuration information below. It should be understood that in the embodiments of the present application, the second information and the AI / ML configuration information can be replaced with each other if there is no conflict.

[0054] In some implementations, the second information and the first information may be carried in the same resource configuration information.

[0055] The resource configuration information including the AI / ML configuration information corresponding to the first time-domain resource configuration information means that the resource configuration information not only configures the first time-domain resource configuration information, but also configures the correspondence between the first time-domain resource configuration information and the AI / ML configuration information. For example, the AI / ML configuration information may be included in the first time-domain resource configuration information, i.e., it may be part of the first time-domain resource configuration information.

[0056] In some implementations, the correspondence between the first time domain resource configuration information and the AI / ML configuration information can be understood as the correspondence between the AI / ML configuration information and the first time domain resource configured by the first time domain resource configuration information, or the correspondence between the AI / ML configuration information and the first physical channel transmitted in the first time domain resource. In other words, based on the above correspondence, it can be determined that the first physical channel transmitted in the first time domain resource supports the AI / ML function or AI model indicated by the AI / ML configuration information. Establishing a correspondence between the first time domain resource configuration information and the AI / ML configuration information is equivalent to binding the AI / ML configuration information to a specific time domain resource, which can avoid mismatching between the AI / ML configuration information and the time domain resource, thereby improving the reliability of the wireless communication system based on AI / ML.

[0057] The embodiments of the present application do not specifically limit the content of the AI / ML configuration information. For example, the AI / ML configuration information may configure or indicate the AI / ML functions supported by the first time domain resource. In another example, the AI / ML configuration information may configure or indicate the AI / ML models supported by the first time domain resource. In another example, the AI / ML configuration information may simultaneously configure or indicate both the AI / ML functions and the AI / ML models supported by the first time domain resource. The content of the AI / ML configuration information is described in more detail below with reference to specific examples.

[0058] Example 1: AI / ML configuration information indicates the AI / ML function supported by the first time domain resource

[0059] The AI / ML configuration information may directly indicate the AI / ML function supported or not supported by the first time domain resource. Alternatively, the AI / ML configuration information may also indicate the AI / ML function supported or not supported by the first time domain resource through an identifier (ID) of the AI / ML function. For example, the AI / ML configuration information may include one or more of the following: an identifier of the AI / ML function supported by the first time domain resource, and an identifier of the AI / ML function not supported by the first time domain resource. Indicating the AI / ML function based on the identifier can reduce the configuration complexity of the time domain resource configuration information.

[0060] The following is combined with Table 1, taking the first physical channel as PDSCH or PUSCH as an example for explanation. In the following example, the time domain resource configuration information may include the following three parameters: the time slot displacement from the PDCCH to the PDSCH / PUSCH scheduled by the PDCCH (parameter K), the starting symbol of the PDSCH / PUSCH in the scheduled time slot (parameter S), and the length or number of symbols of the PDSCH / PUSCH (parameter L). Further, in the following example, each time domain resource configuration information includes corresponding AI / ML configuration information. The AI / ML configuration information can be used to indicate which AI / ML functions can be supported when transmitting PDSCH / PUSCH using the time domain resources configured by the time domain resource configuration information.

[0061] As shown in Table 1, the network device configures 8 candidate time domain resources for the terminal device and configures the supported AI / ML functions for each time domain resource. The example in Table 1 mainly determines whether a certain AI / ML function is supported based on the distance between the PDSCH / PUSCH and the PDCCH. For example, since it takes a long time to load some more complex AI / ML algorithms, for PDSCH / PUSCH farther from the PDCCH, more functions can be processed by the AI / ML algorithm, while for PDSCH / PUSCH closer to the PDCCH, only fewer functions can be processed by the AI / ML algorithm.

[0062] For example, for time domain resource configurations 1 and 3, since PDSCH / PUSCH and PDCCH are located in the same time slot (i.e., K=0), and PDSCH / PUSCH is transmitted from the head of the time slot (i.e., S=0), the algorithms of functions 1, 2, and 3 are not loaded in time, so functions 1, 2, and 3 are all configured as not supported.

[0063] For example, for time domain resource configurations 5 and 7, PDSCH / PUSCH and PDCCH are located in the same time slot (i.e., K = 0), but PDSCH / PUSCH transmission starts from the middle of the time slot (i.e., S = 7). In this case, the algorithm for function 1 can complete the loading. Therefore, in time domain resource configurations 5 and 7, function 1 is configured as supported, while functions 2 and 3 are configured as not supported.

[0064] For example, for time domain resource configurations 2 and 4, since PDSCH / PUSCH is located in the next time slot of the time slot where PDCCH is located (i.e., K=1) and PDSCH / PUSCH is transmitted from the head of the time slot (i.e., S=0), the algorithms of functions 1 and 2 can complete the loading. Therefore, in these two time domain resource configurations, functions 1 and 2 are configured as supported, and function 3 is configured as not supported.

[0065] For example, for time domain resource configurations 6 and 8, since the PDSCH / PUSCH is located in the time slot following the PDCCH (i.e., K=1) and PDSCH / PUSCH transmission starts in the middle of the time slot (e.g., S=7), the algorithms for functions 1, 2, and 3 can all be loaded. Therefore, in time domain resource configurations 6 and 8, functions 1, 2, and 3 are all configured to be supported.

[0066] Table 1: Time Domain Resource Configuration Information (including AI / ML Function Configuration Information)

[0067] The above solution binds specific time domain resources to the AI / ML functions supported by these time domain resources, ensuring the compatibility of the AI / ML configuration information with the time domain resources of the first physical channel. Based on this solution, terminal devices can use AI / ML functions only in appropriate scenarios, thereby ensuring the reliability of the wireless communication system.

[0068] Example 2: AI / ML configuration information indicates the AI / ML model supported by the first time domain resource

[0069] It should be understood that for the same AI / ML function, the AI / ML configuration information may indicate only one AI / ML model corresponding to the AI / ML function, or may indicate multiple AI / ML models corresponding to the AI / ML function (that is, any one of the multiple AI / ML models may be used to implement the corresponding AI / ML function). In some implementations, if one AI / ML function corresponds to multiple AI / ML models, the multiple AI / ML models may include a default AI / ML model. The so-called default AI / ML model refers to the AI / ML model used by default. For example, if the network device activates the AI / ML function but does not indicate the AI / ML model corresponding to the AI / ML function, the terminal device may use the default AI / ML model to process the first physical channel.

[0070] The AI / ML configuration information may directly indicate the AI / ML models supported or not supported by the first time domain resource. Alternatively, the AI / ML configuration information may also indicate the AI / ML models supported or not supported by the first time domain resource through the identifier of the AI / ML model. For example, the AI / ML configuration information may include one or more of the following information: the identifier of the AI / ML model supported by the first time domain resource, and the identifier of the AI / ML model not supported by the first time domain resource. Indicating the AI / ML model based on the identifier can reduce the configuration complexity of the time domain resource configuration information.

[0071] The following is combined with Table 2, taking the first physical channel as PDSCH or PUSCH as an example for explanation. In the following example, the time domain resource configuration information may include the following three parameters: the time slot displacement from the PDCCH to the PDSCH / PUSCH scheduled by the PDCCH (parameter K), the starting symbol of the PDSCH / PUSCH in the scheduled time slot (parameter S), and the length or number of symbols of the PDSCH / PUSCH (parameter L). Further, in the following example, the time domain resource configuration information includes corresponding AI / ML configuration information. The AI / ML configuration information may indicate which AI / ML functions can be supported when using the time domain resources to transmit PDSCH / PUSCH. In addition, the AI / ML configuration information may also indicate the AI ​​model corresponding to the AI / ML function.

[0072] As shown in Table 2, the network device configures eight candidate time domain resources for the terminal device and configures the supported AI / ML functions and AI / ML models for each time domain resource. The example in Table 2 mainly determines whether a certain AI / ML function is supported based on the distance between the PDSCH / PUSCH and the PDCCH. For example, because loading some more complex AI / ML algorithms takes a long time, for PDSCH / PUSCHs farther from the PDCCH, more functions can be processed by the AI / ML algorithm, while for PDSCH / PUSCHs closer to the PDCCH, only fewer functions can be processed by the AI / ML algorithm.

[0073] For example, for time domain resource configurations 1 and 3, since PDSCH / PUSCH and PDCCH are located in the same time slot (i.e., K=0) and PDSCH / PUSCH is transmitted from the head of the time slot (i.e., S=0), the algorithms of functions 1, 2, and 3 are not loaded in time, so functions 1, 2, and 3 are all configured as not supported.

[0074] For example, for time domain resource configurations 5 and 7, PDSCH / PUSCH and PDCCH are located in the same time slot (i.e., K = 0) but PDSCH / PUSCH transmission starts from the middle of the time slot (e.g., S = 7). In this case, the algorithm for function 1 can complete the loading. Therefore, in these two time domain resource configurations, function 1 is configured as supported and AI / ML model 1-1 is used. Functions 2 and 3 are configured as not supported.

[0075] For example, for time domain resource configurations 2 and 4, since the PDSCH / PUSCH is located in the time slot following the PDCCH time slot (i.e., K=1) and PDSCH / PUSCH transmission starts at the beginning of the time slot (i.e., S=0), the algorithms for functions 1 and 2 can be loaded. Therefore, in these two time domain resource configurations, functions 1 and 2 are configured as supported, and AI / ML model 1-1 and AI / ML model 2-1 are used, respectively. Function 3 is configured as not supported.

[0076] For example, for time domain resource configurations 6 and 8, since PDSCH / PUSCH is located in the next time slot of the time slot where PDCCH is located (i.e., K=1) and PDSCH / PUSCH is transmitted from the middle of the time slot (such as S=7), the algorithms of functions 1, 2, and 3 can all be loaded. Therefore, in these two time domain resource configurations, functions 1, 2, and 3 are all configured to be supported, and AI / ML model 1-1, AI / ML model 2-1, and AI / ML model 3-2 are used respectively.

[0077] Table 2: Time Domain Resource Configuration Information (including AI / ML Function and AI / ML Model Configuration Information)

[0078] The above solution binds specific time domain resources with the AI / ML functions and AI / ML models supported by the specific time domain resources, ensuring the compatibility of the AI / ML configuration information with the time domain resources of the first physical channel. Based on this solution, terminal devices can use AI / ML functions and AI / ML models only in appropriate scenarios, thereby ensuring the reliability of the wireless communication system.

[0079] The above describes the content of the resource configuration information in detail. The following describes in detail how to schedule the time domain resources configured by the resource configuration information (and the AI / ML configuration information corresponding to the time domain resources).

[0080] In some implementations, the method of FIG. 3 may further include: the terminal device receiving first control information. The first control information may be, for example, DCI, a medium access control element (MAC CE), or sidelink control information (SCI). If the first control information is DCI or MAC CE, the first control information may be sent by the network device. If the first control information is SCI, the first control information may be sent by another terminal device.

[0081] The first control information may include first indication information (for example, a time domain resource indicator). The first indication information may be used to indicate the first time domain resource configuration information mentioned above. The first indication information may indicate the first time domain resource configuration information currently in use from the multiple time domain resource configuration information configured by the resource configuration information. As mentioned above, the first time domain resource configuration information has a corresponding relationship with the AI / ML configuration information. Therefore, if the first indication information indicates the first time domain resource configuration information, it can be considered that the network device has selected the AI / ML configuration information corresponding to the first time domain resource configuration information. It can be seen from this that the embodiment of the present application does not need to set a separate field for indicating the AI / ML configuration information in the first control information, thereby greatly reducing the signaling overhead required to transmit the first control information.

[0082] After receiving the first control information, the terminal device can determine the first time domain resource based on the first time domain resource configuration information indicated by the first control information, and receive or send the first physical channel in the first time domain resource according to the AI / ML configuration information. In other words, the terminal device can determine the first time domain resource based on the time domain position information and time domain length information of the first time domain resource, and receive or send the first physical channel in the first time domain resource according to the AI / ML configuration information associated with the first time domain resource. For example, the terminal device can first determine the AI / ML function and / or AI / ML model that the terminal device should use based on the AI / ML configuration information; then, the terminal device can receive or send the first physical channel based on the AI / ML function and / or AI / ML model. If the AI / ML configuration information indicates that the first physical channel in the first time domain resource does not support AI / ML processing, the terminal device can use the traditional solution to receive or send the first physical channel.

[0083] As mentioned above, the AI / ML configuration information can indicate multiple AI / ML models corresponding to the same AI / ML function. If the AI / ML configuration information indicates (or configures) multiple AI / ML models, in order to enable the terminal device to clearly know which AI / ML model among the multiple AI / ML models to use to process the first physical channel, the first control information may further carry second indication information. The second indication information can be used to indicate at least one AI / ML model (such as one AI / ML model) among the multiple AI / ML models. The introduction of the second indication information in the first control information enables the network device to schedule the terminal device to use the appropriate AI / ML model to process the first physical channel, thereby improving the reliability of communication.

[0084] To save signaling overhead, in some implementations, a default AI / ML model may be set among multiple AI / ML models. This default AI / ML model may be used when the first control information does not include the second indication information. For example, if the AI / ML configuration information indicates multiple AI / ML models, but the terminal device does not receive the second indication information from the first control information, the terminal device may use the default AI / ML model to process the first physical channel.

[0085] The following takes the first control information as DCI, the first indication information as the time domain resource indicator in the DCI, and the second indication information as the AI / ML model indicator as an example to describe the embodiments of the present application in more detail. It should be noted that the following examples are only intended to help those skilled in the art understand the embodiments of the present application, and are not intended to limit the embodiments of the present application to the specific numerical values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the examples below, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0086] Example 1: Time domain resources and AI / ML configuration information configured using DCI scheduling resource configuration information

[0087] Resource configuration information (such as RRC configuration information) may include multiple time domain resource configuration information. In this case, a time domain resource indicator in the DCI may be used to indicate one time domain resource configuration information from multiple time domain resource configuration information, thereby activating the AI / ML function bound to the time domain resource while scheduling the corresponding time domain resource. As shown in Table 3, each time domain resource configuration information corresponds to a value of the time domain resource indicator in the DCI.

[0088] In the example in Table 3, when the time domain resource indicator value in the DCI is 000, the DCI schedules time domain resource 1 (K=0, S=0, L=7) for the PDSCH. This time domain resource occupies the first half of the time slot where the PDCCH is located (time slot N) (as shown in Figure 4), meaning that the PDSCH and PDCCH are transmitted almost simultaneously. Since functions 1, 2, and 3 in time domain resource 1 are all configured as unsupported, the AI / ML algorithms for functions 1, 2, and 3 do not need to be used under extremely short latency conditions.

[0089] When the time domain resource indicator value in the DCI is 110, the DCI schedules time domain resource 7 (K=0, S=7, L=7) for the PDSCH. This time domain resource occupies the second half of the time slot (time slot N) where the PDCCH resides (as shown in Figure 5). That is, the PDSCH is transmitted slightly after the PDCCH. Because function 1 in time domain resource 7 is configured as supported and functions 2 and 3 are not configured as supported, only the AI / ML algorithm of function 1 is used with shorter latency.

[0090] When the time domain resource indicator value in the DCI is 001, the DCI schedules time domain resource 2 (K=1, S=0, L=7) for the PDSCH. This time domain resource occupies the first half of the time slot following the time slot where the PDCCH is located (time slot N+1) (as shown in Figure 6). That is, the PDSCH is transmitted one time slot period after the PDCCH. Because functions 1 and 2 in time domain resource 2 are configured as supported and function 3 is configured as unsupported, the AI / ML algorithms of functions 1 and 2 can be used with slightly longer latency.

[0091] When the time domain resource indicator value in the DCI is 111, the DCI schedules time domain resource 8 (K=1, S=7, L=7) for the PDSCH. This time domain resource occupies the second half of the time slot following the PDCCH (time slot N+1) (as shown in Figure 7). That is, the PDSCH is transmitted later than the PDCCH. Because functions 1, 2, and 3 in time domain resource 8 are all configured to support, the AI / ML algorithms of functions 1, 2, and 3 can be used under longer delays.

[0092] Table 3: Correspondence between the time domain resource indicator in the DCI and the time domain resource configuration (including configuration information for AI / ML functions)

[0093] If the time domain resource configuration information includes not only configuration information for the AI / ML function but also configuration information for the AI / ML model (as shown in Table 4), the time domain resource indicator can be used to indicate one time domain resource configuration information from multiple time domain resource configuration information, thereby activating the AI / ML function bound to this time domain resource while scheduling the corresponding time domain resource, and specifying the AI / ML model used for this AI / ML function.

[0094] In the example in Table 4, when the time domain resource indicator value in the DCI is 000, the DCI schedules time domain resource 1 (K=0, S=0, L=7) for the PDSCH. This time domain resource occupies the first half of the time slot where the PDCCH is located (time slot N) (as shown in Figure 8), meaning that the PDSCH and PDCCH are transmitted almost simultaneously. Since functions 1, 2, and 3 in time domain resource 1 are all configured as unsupported, the AI / ML algorithms for functions 1, 2, and 3 do not need to be used under extremely short latency conditions.

[0095] When the time domain resource indicator value in the DCI is 110, the DCI schedules time domain resource 7 (K=0, S=7, L=7) for the PDSCH. This time domain resource occupies the second half of the time slot (time slot N) where the PDCCH resides (as shown in Figure 9). This means that the PDSCH is transmitted slightly after the PDCCH. Because function 1 in time domain resource 7 is configured as supported, Model 1-1 is used for function 1 processing, and functions 2 and 3 are configured as unsupported. Therefore, only the AI / ML algorithm of function 1 is used with shorter latency.

[0096] When the time domain resource indicator value in the DCI is 001, the DCI schedules time domain resource 2 (K=1, S=0, L=7) for the PDSCH. This time domain resource occupies the first half of the time slot following the time slot where the PDCCH is located (time slot N+1) (as shown in Figure 10). That is, the PDSCH is transmitted one time slot period after the PDCCH. Since functions 1 and 2 in time domain resource 2 are configured as supported, Model 1-1 is used for processing function 1, and Model 2-1 is used for processing function 2. Function 3 is configured as not supported. Therefore, the AI / ML algorithms of functions 1 and 2 can be used with slightly longer latency.

[0097] When the value of the time domain resource indicator in the DCI is 111, the DCI schedules time domain resource 8 (K=1, S=7, L=7) for the PDSCH. This time domain resource occupies the second half of the time slot following the time slot where the PDCCH is located (time slot N+1) (as shown in Figure 11). That is, the PDSCH is transmitted later than the PDCCH. Since functions 1, 2, and 3 in time domain resource 8 are all configured to support, Model 1-1 is used for processing function 1, Model 2-1 is used for processing function 2, and Model 3-2 is used for processing function 3. Therefore, the AI / ML algorithms of functions 1, 2, and 3 can be used under longer delays.

[0098] Table 4: Time Domain Resource Configuration (including configuration information for AI / ML functions and configuration information for AI / ML models)

[0099] Example 1 binds supported AI / ML functions and models to specific time domain resources and indicates these specific time domain resources using a time domain resource indicator in the DCI. This allows the time domain resource indicator to activate the configuration information for the AI / ML functions and models bound to the time domain resources, significantly reducing DCI overhead. Furthermore, this example ensures the compatibility of the AI / ML configuration information with channel transmission resources, thereby ensuring the reliability of the wireless communication system.

[0100] Example 2: Using DCI to activate one AI / ML model from multiple AI / ML models bound to time domain resources

[0101] Table 5: Time Domain Resource Configuration (for one AI / ML function, including configuration information for multiple AI / ML models)

[0102] As shown in Table 5, multiple AI / ML models can be configured for an AI / ML function in the time domain resource configuration information. Then, an AI / ML model can be activated from these AI / ML models using the AI / ML model indicator in the DCI. In scenarios where multiple AI / ML models are configured for an AI / ML function, a default AI / ML model can be configured, and when the DCI does not include the AI / ML model indicator, the default AI / ML model can be automatically activated.

[0103] According to the configuration in Table 5, when the value of the time domain resource indicator in the DCI is 110, the DCI schedules time domain resource No. 7 (K = 0, S = 7, L = 7) for PDSCH. Function 1 in this time domain resource is configured to be supported, and Model 1-1 and Model 1-2 can be used for processing function 1, where Model 1-1 is the default model. Functions 2 and 3 are configured not to be supported. The DCI may include a second indicator (AI model indicator), as shown in Figure 12. The value of this indicator is 01, so Model 1-2 is activated for AI / ML function 1. If there is no AI model indicator in the DCI, the default model Model 1-1 is automatically activated.

[0104] According to the configuration in Table 5, when the value of the time domain resource indicator in the DCI is 001, the DCI schedules time domain resource No. 2 for PDSCH (K=1, S=0, L=7). Functions 1 and 2 in this time domain resource are configured to be supported, and Model 1-1 and Model 1-2 can be used for processing function 1, where Model 1-1 is the default model; Model 2-1, Model 2-2, and Model 2-3 can be used for processing function 2, where Model 2-1 is the default model. Function 3 is configured not to be supported. The DCI may include a second indicator (AI model indicator), as shown in Figure 13. The value of the AI / ML function 1 field in this indicator is 01, so Model 1-2 is activated for AI / ML function 1; the value of the AI / ML function 2 field in this indicator is 10, so Model 2-3 is activated for AI / ML function 2. If there is no AI model indicator in the DCI, the default model Model 1-1 is automatically activated for AI / ML function 1, and the default model Model 2-1 is automatically activated for AI / ML function 2.

[0105] In Example 2, multiple AI / ML models are configured for an AI / ML function within a time domain resource, and one is selected through DCI. This provides greater flexibility in AI / ML model selection and enables better wireless transmission performance. Furthermore, configuring a default AI / ML among multiple AI / ML models also eliminates the need for an AI / ML model indicator in the DCI, automatically activating the default model and saving DCI overhead.

[0106] In the above description, the AI / ML configuration information includes information related to the AI / ML function and / or AI / ML model. In addition, in some other implementations, the AI / ML configuration information may also include identification (or index) information of the AI / ML configuration information. The identification information of the AI / ML configuration information can be used to identify or index the independently configured AI / ML configuration information. That is, based on the identification information of the AI / ML configuration information, the corresponding AI / ML function and / or AI / ML model can be obtained by searching for the independently configured AI / ML configuration information. This implementation method increases the flexibility of the AI / ML configuration and avoids repeatedly configuring the same AI / ML configuration information in multiple time domain resource configuration information, thereby saving the signaling overhead caused by adding AI / ML configuration information to the time domain configuration information. The following is a detailed explanation of this implementation method with two more specific examples.

[0107] Example 1

[0108] In Example 1, first, the configuration information of the AI / ML function can be configured separately for the terminal device. Table 6 shows an example of the configuration information of the AI / ML function. As can be seen from Table 6, the configuration information of the AI / ML function includes the identifier corresponding to the configuration information of each AI function.

[0109] Table 6: Configuration information for AI / ML functions

[0110] After separately configuring the configuration information of the above-mentioned AI / ML function, the identifier of the configuration information of the AI / ML function can be included in the time domain resource configuration information, thereby conveniently indicating the correspondence between the time domain resources and the AI ​​function. Table 7 gives an example.

[0111] Table 7: Time Domain Resource Configuration Information (including configuration identifiers for AI / ML functions)

[0112] Example 2:

[0113] Separate AI / ML configuration information may also include configuration information for the AI / ML model, as shown in Table 8.

[0114] Table 8: Individual AI / ML configuration information

[0115] Based on the AI / ML configuration information shown in Table 8, each time domain resource configuration may include an identifier of the AI / ML configuration without including specific configuration information of the AI / ML function and AI / ML model (as shown in Table 9).

[0116] Table 9: Time Domain Resource Configuration Information (including configuration identifiers for AI / ML functions)

[0117] Example 2 increases the flexibility of AI / ML configuration and avoids repetitive configuration of the same AI / ML configuration in multiple time domain resources, saving the signaling overhead required to configure time domain resource configuration information. At the same time, by including the AI / ML configuration ID in the time domain resource, the configuration of AI / ML functions and models can still be bound to the time domain resource, ensuring the adaptability of the AI / ML configuration to the channel transmission resources, thereby ensuring the reliability of the wireless communication system.

[0118] In some implementations, before the terminal device receives the resource configuration information sent by the network device, the terminal device may send first capability information to the network device. The first capability information is used to indicate the AI / ML functions supported by the terminal device. The reporting of the first capability information may be performed for a bandwidth part (BWP). That is, the terminal device may report whether the terminal device supports the AI / ML function within a certain BWP. The AI / ML functions supported by the terminal device in different BWPs may be the same or different.

[0119] The first capability information may directly indicate the AI / ML functions supported by the terminal device, or may carry an identifier of the AI / ML function supported by the terminal device and / or an identifier of the AI / ML function not supported by the terminal device in the first capability information. Indication based on the identifier of the AI / ML function can reduce the communication overhead required for capability information indication.

[0120] In some implementations, before the terminal device receives the resource configuration information sent by the network device, the terminal device may send second capability information to the network device. The second capability information is used to indicate the AI / ML model supported by the terminal device. The reporting of the second capability information can be performed for the BWP. That is, the terminal device can report whether the terminal device supports the AI / ML model within a certain BWP. The AI / ML models supported by the terminal device in different BWPs can be the same or different. The first capability information and the second capability information can be reported to the network device through the same message, or they can be reported to the network device through different messages.

[0121] The second capability information may directly indicate the AI / ML models supported by the terminal device, or may carry the identifier of the AI / ML model supported by the terminal device and / or the identifier of the AI / ML model not supported by the terminal device in the second capability information. Indication based on the identifier of the AI / ML model can reduce the communication overhead required for capability information indication.

[0122] If a particular AI / ML function corresponds to multiple AI / ML models (i.e., all of the multiple AI / ML models can be used to implement the AI / ML function, and different AI / ML models can correspond to different deployment scenarios), in some implementations, the second capability information may indicate a default AI / ML model among the multiple AI / ML models. Reporting the default AI / ML model to the network device helps reduce the signaling overhead of the network device (for a detailed description of the default model, please refer to the previous article and will not be detailed here).

[0123] It should be noted that the AI / ML functionality mentioned in various embodiments of this application can also be referred to as AI / ML features. If there is no conflict, the two can be used interchangeably.

[0124] It should also be noted that the symbols mentioned in various embodiments of the present application may refer to orthogonal frequency division multiplexing (OFDM) symbols.

[0125] The method embodiment of the present application is described in detail above in conjunction with Figures 3 to 13. The device embodiment of the present application is described in detail below in conjunction with Figures 14 to 16. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment. Therefore, for parts not described in detail, reference can be made to the above method embodiment.

[0126] Figure 14 is a schematic diagram of the structure of a terminal device provided in an embodiment of the present application. The terminal device 1400 shown in Figure 14 may include a first communication unit 1410. The first communication unit 1410 may be used to receive resource configuration information sent by a network device, wherein the resource configuration information includes first information and second information; wherein the first information is used to indicate time domain location information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein the second information is used to indicate AI / ML configuration information associated with the first time domain resource.

[0127] In some implementations, the AI / ML configuration information is used to configure AI / ML functions supported by the first time domain resources.

[0128] In some implementations, the AI / ML configuration information includes one or more of the following: an identifier of an AI / ML function supported by the first time domain resource; and an identifier of an AI / ML function not supported by the first time domain resource.

[0129] In some implementations, the AI / ML configuration information is used to configure an AI / ML model supported by the first time domain resource.

[0130] In some implementations, the AI / ML configuration information includes one or more of the following: an identifier of an AI / ML model supported by the first time domain resource; an identifier of an AI / ML model not supported by the first time domain resource.

[0131] In some implementations, the AI / ML configuration information is used to configure multiple AI / ML models supported by the first time domain resources, and the multiple AI / ML models correspond to the same AI / ML function, and the multiple AI / ML models include a default AI / ML model.

[0132] In some implementations, the second information includes an identifier of AI / ML configuration information, where the identifier of the AI / ML configuration information is used to identify the AI / ML configuration information associated with the first time-domain resource.

[0133] In some implementations, the terminal device 1400 further includes: a second communication unit, configured to receive first control information, where the first control information includes first indication information, and the first indication information is configured to indicate the first information.

[0134] In some implementations, the terminal device 1400 further includes: a third communication unit, configured to determine the first time domain resource based on the time domain position information and time domain length information of the first time domain resource; and a fourth communication unit, configured to receive or send the first physical channel in the first time domain resource based on the AI / ML configuration information associated with the first time domain resource.

[0135] In some implementations, the AI / ML configuration information is used to configure multiple AI / ML models supported by the first time domain resource, and the multiple AI / ML models correspond to the same AI / ML function. The first control information also includes second indication information, and the second indication information is used to indicate one AI / ML model among the multiple AI / ML models.

[0136] In some implementations, the multiple AI / ML models further include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

[0137] In some implementations, the first control information is DCI, or MAC CE, or SCI.

[0138] In some implementations, the time domain location information includes one or more of the following: a starting time slot of the first time domain resource; and a starting symbol of the first time domain resource.

[0139] In some implementations, the time domain length information includes one or more of the following: the number of time slots occupied by the first time domain resource; the number of symbols occupied by the first time domain resource.

[0140] In some implementations, the resource configuration information is RRC configuration information or SIB.

[0141] In some implementations, the terminal device 1400 further includes: a fifth communication unit, configured to send first capability information to the network device before the terminal device receives resource configuration information sent by the network device, wherein the first capability information is used to indicate the AI / ML functions supported by the terminal device.

[0142] In some implementations, the first capability information includes one or more of the following: an identifier of an AI / ML function supported by the terminal device; an identifier of an AI / ML function not supported by the terminal device.

[0143] In some implementations, the terminal device 1400 further includes: a sixth communication unit, configured to send second capability information to the network device before the terminal device receives resource configuration information sent by the network device, wherein the second capability information is used to indicate the AI / ML model supported by the terminal device.

[0144] In some implementations, the second capability information includes one or more of the following: an identifier of an AI / ML model supported by the terminal device; an identifier of an AI / ML model not supported by the terminal device.

[0145] In some implementations, the second capability information indicates that the terminal device supports multiple AI / ML models, the multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates a default AI / ML model among the multiple AI / ML models.

[0146] In some implementations, the first physical channel is a data channel.

[0147] In some implementations, the data channel is a PDSCH, a PUSCH, or a PSSCH.

[0148] Figure 15 is a schematic diagram of the structure of a network device provided in an embodiment of the present application. The network device 1500 shown in Figure 15 may include a first communication unit 1510. The first communication unit 1510 is used to send resource configuration information to a terminal device, where the resource configuration information includes first information and second information; wherein the first information is used to indicate time domain location information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein the second information is used to indicate AI / ML configuration information associated with the first time domain resource.

[0149] In some implementations, the AI / ML configuration information is used to configure AI / ML functions supported by the first time domain resources.

[0150] In some implementations, the AI / ML configuration information includes one or more of the following: an identifier of an AI / ML function supported by the first time domain resource; and an identifier of an AI / ML function not supported by the first time domain resource.

[0151] In some implementations, the AI / ML configuration information is used to configure an AI / ML model supported by the first time domain resource.

[0152] In some implementations, the AI / ML configuration information includes one or more of the following: an identifier of an AI / ML model supported by the first time domain resource; an identifier of an AI / ML model not supported by the first time domain resource.

[0153] In some implementations, the AI / ML configuration information is used to configure multiple AI / ML models supported by the first time domain resources, and the multiple AI / ML models correspond to the same AI / ML function, and the multiple AI / ML models include a default AI / ML model.

[0154] In some implementations, the second information includes an identifier of AI / ML configuration information, where the identifier of the AI / ML configuration information is used to identify the AI / ML configuration information associated with the first time-domain resource.

[0155] In some implementations, the network device 1500 further includes: a second communication unit, configured to send first control information to the terminal device, wherein the first control information includes first indication information, and the first indication information is configured to indicate the first information.

[0156] In some implementations, the AI / ML configuration information is used to configure the first time domain resource to support multiple AI / ML models, and the multiple AI / ML models correspond to the same AI / ML function. The first control information also includes second indication information, and the second indication information is used to indicate one AI / ML model among the multiple AI / ML models.

[0157] In some implementations, the multiple AI / ML models further include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

[0158] In some implementations, the first control information is DCI, or MAC CE, or SCI.

[0159] In some implementations, the time domain location information includes one or more of the following: a starting time slot of the first time domain resource; and a starting symbol of the first time domain resource.

[0160] In some implementations, the time domain length information includes one or more of the following: the number of time slots occupied by the first time domain resource; the number of symbols occupied by the first time domain resource.

[0161] In some implementations, the resource configuration information is RRC configuration information or SIB.

[0162] In some implementations, the network device 1500 further includes: a third communication unit, configured to receive first capability information sent by the terminal device before the network device sends resource configuration information to the terminal device, wherein the first capability information is used to indicate the AI / ML function supported by the terminal device.

[0163] In some implementations, the first capability information includes one or more of the following: an identifier of an AI / ML function supported by the terminal device; an identifier of an AI / ML function not supported by the terminal device.

[0164] In some implementations, the network device 1500 further includes: a fourth communication unit, configured to send second capability information to the network device before the network device sends resource configuration information to the terminal device, wherein the second capability information is used to indicate an AI / ML model supported by the terminal device.

[0165] In some implementations, the second capability information includes one or more of the following: an identifier of an AI / ML model supported by the terminal device; an identifier of an AI / ML model not supported by the terminal device.

[0166] In some implementations, the second capability information indicates that the terminal device supports multiple AI / ML models, the multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates a default AI / ML model among the multiple AI / ML models.

[0167] In some implementations, the first physical channel is a data channel.

[0168] In some implementations, the data channel is a PDSCH, a PUSCH, or a PSSCH.

[0169] Figure 16 is a schematic block diagram of an apparatus for downlink transmission according to an embodiment of the present application. The dashed lines in Figure 16 indicate that the unit or module is optional. Apparatus 1600 may be used to implement the method described in the above method embodiment. Apparatus 1600 may be a chip, a terminal, or a network device.

[0170] The device 1600 may include one or more processors 1610. The processor 1610 may support the device 1600 to implement the method described in the above method embodiment. The processor 1610 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0171] The apparatus 1600 may further include one or more memories 1620. The memories 1620 store programs that can be executed by the processor 1610, causing the processor 1610 to perform the methods described in the above method embodiments. The memories 1620 may be independent of the processor 1610 or integrated into the processor 1610.

[0172] The apparatus 1600 may further include a transceiver 1630. The processor 1610 may communicate with other devices or chips via the transceiver 1630. For example, the processor 1610 may transmit and receive data with other devices or chips via the transceiver 1630.

[0173] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0174] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in the present application, and the program causes a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0175] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided in the embodiments of the present application, and the computer program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0176] It should be understood that in the embodiments of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0177] It should be understood that the term "and / or" in this document simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0178] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0179] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A resource allocation method, characterized in that, including: The terminal device receives resource configuration information sent by a network device, where the resource configuration information includes first information and second information; wherein, the first information is used to indicate the time-domain position information and time-domain length information of a first time-domain resource, and the first time-domain resource is used to carry a first physical channel; wherein, the second information is used to indicate the artificial intelligence (AI) / machine learning (ML) configuration information associated with the first time-domain resource.

2. The method according to claim 1, wherein The AI / ML configuration information is used to configure the AI / ML functions supported by the first time-domain resource.

3. The method according to claim 2, wherein The AI / ML configuration information includes one or more of the following: identifiers of the AI / ML functions supported by the first time-domain resource; identifiers of the AI / ML functions not supported by the first time-domain resource.

4. The method according to any one of claims 1 to 3, characterized in that, The AI / ML configuration information is used to configure the AI / ML models supported by the first time-domain resource.

5. The method according to claim 4, wherein The AI / ML configuration information includes one or more of the following: identifiers of the AI / ML models supported by the first time-domain resource; identifiers of the AI / ML models not supported by the first time-domain resource.

6. The method according to claim 4 or 5, characterized in that The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time-domain resource, and the multiple AI / ML models correspond to the same AI / ML function, and the multiple AI / ML models include a default AI / ML model.

7. The method according to any one of claims 1 to 6, characterized in that The second information includes identification information of the AI / ML configuration information.

8. The method according to any one of claims 1 to 7, characterized in that The method further includes: The terminal device receives first control information, where the first control information includes first indication information, and the first indication information is used to indicate the first information.

9. The method according to claim 8, wherein The method further includes: The terminal device determines the first time-domain resource according to the time-domain position information and time-domain length information of the first time-domain resource; The terminal device receives or transmits the first physical channel in the first time-domain resource according to the AI / ML configuration information associated with the first time-domain resource.

10. The method according to claim 8 or 9, characterized in that, The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time-domain resource, the multiple AI / ML models correspond to the same AI / ML function, and the first control information further includes second indication information, and the second indication information is used to indicate one AI / ML model among the multiple AI / ML models.

11. The method according to claim 10, wherein The multiple AI / ML models include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

12. The method according to any one of claims 8 to 11, characterized in that, The first control information is downlink control information (DCI), or media access control control element (MAC CE), or sidelink control information (SCI).

13. The method according to any one of claims 1 to 12, characterized in that, The time-domain position information includes one or more of the following: the starting time slot of the first time-domain resource; the starting symbol of the first time-domain resource.

14. The method according to any one of claims 1 to 13, characterized in that The time-domain length information includes one or more of the following: the number of time slots occupied by the first time-domain resource; the number of symbols occupied by the first time-domain resource.

15. The method according to any one of claims 1 to 14, characterized in that, The resource configuration information is radio resource control (RRC) configuration information or system information block (SIB).

16. The method according to any one of claims 1 to 15, characterized in that, Before the terminal device receives the resource configuration information sent by the network device, the method further includes: The terminal device sends first capability information to the network device, where the first capability information is used to indicate the AI / ML functions supported by the terminal device.

17. The method according to claim 16, characterized in that, The first capability information includes one or more of the following: Identifiers of the AI / ML functions supported by the terminal device; Identifiers of the AI / ML functions not supported by the terminal device.

18. The method according to any one of claims 1 to 17, characterized in that, Before the terminal device receives the resource configuration information sent by the network device, the method further includes: The terminal device sends second capability information to the network device, where the second capability information is used to indicate the AI / ML models supported by the terminal device.

19. The method according to claim 18, characterized in that, The second capability information includes one or more of the following: Identifiers of the AI / ML models supported by the terminal device; Identifiers of the AI / ML models not supported by the terminal device.

20. The method according to claim 18 or 19, characterized in that, The second capability information indicates that the terminal device supports multiple AI / ML models, the multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates the default AI / ML model among the multiple AI / ML models.

21. The method according to any one of claims 1 to 20, characterized in that, The first physical channel is a data channel.

22. The method according to claim 21, wherein The data channel is a Physical Downlink Shared Channel (PDSCH), a Physical Uplink Shared Channel (PUSCH), or a Physical Sidelink Shared Channel (PSSCH).

23. A resource allocation method, characterized in that, It includes: The network device sends resource configuration information to the terminal device, where the resource configuration information includes first information and second information; Among them, the first information is used to indicate the time-domain position information and time-domain length information of a first time-domain resource, and the first time-domain resource is used to carry a first physical channel; Among them, the second information is used to indicate the artificial intelligence (AI) / machine learning (ML) configuration information associated with the first time-domain resource.

24. The method according to claim 23, wherein The AI / ML configuration information is used to configure the AI / ML functions supported by the first time-domain resource.

25. The method according to claim 24, wherein The AI / ML configuration information includes one or more of the following: Identifiers of the AI / ML functions supported by the first time-domain resource; Identifiers of the AI / ML functions not supported by the first time-domain resource.

26. The method according to any one of claims 23 to 25, characterized in that, The AI / ML configuration information is used to configure the AI / ML models supported by the first time-domain resource.

27. The method according to claim 26, wherein The AI / ML configuration information includes one or more of the following: Identifiers of the AI / ML models supported by the first time-domain resource; Identifiers of the AI / ML models not supported by the first time-domain resource.

28. The method according to claim 26 or 27, characterized in that, The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time-domain resource, the multiple AI / ML models correspond to the same AI / ML function, and the multiple AI / ML models include a default AI / ML model.

29. The method according to any one of claims 23 to 28, characterized in that, The second information includes identification information of the AI / ML configuration information.

30. The method according to any one of claims 23 to 29, characterized in that, The method further includes: The network device sends first control information to the terminal device, where the first control information includes first indication information, and the first indication information is used to indicate the first information.

31. The method according to claim 30, wherein The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time-domain resource. The multiple AI / ML models correspond to the same AI / ML function. The first control information further includes second indication information, and the second indication information is used to indicate one AI / ML model among the multiple AI / ML models.

32. The method according to claim 31, wherein The multiple AI / ML models include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

33. The method according to any one of claims 30 to 32, characterized in that, The first control information is downlink control information DCI, or media access control control element MAC CE, or sidelink control information SCI.

34. The method according to any one of claims 23 to 33, characterized in that, The time-domain position information includes one or more of the following: The starting time slot of the first time-domain resource; The starting symbol of the first time-domain resource.

35. The method according to any one of claims 23 to 34, characterized in that, The time-domain length information includes one or more of the following: The number of time slots occupied by the first time-domain resource; The number of symbols occupied by the first time-domain resource.

36. The method according to any one of claims 23 to 35, characterized in that, The resource configuration information is radio resource control RRC configuration information or system information block SIB.

37. The method according to any one of claims 23 to 36, characterized in that, Before the network device sends resource configuration information to the terminal device, the method further includes: The network device receives first capability information sent by the terminal device, and the first capability information is used to indicate the AI / ML functions supported by the terminal device.

38. The method according to claim 37, wherein The first capability information includes one or more of the following: The identifier of the AI / ML functions supported by the terminal device; The identifier of the AI / ML functions not supported by the terminal device.

39. The method according to any one of claims 23 to 38, characterized in that, Before the network device sends resource configuration information to the terminal device, the method further includes: The network device receives second capability information sent by the terminal device, and the second capability information is used to indicate the AI / ML models supported by the terminal device.

40. The method according to claim 39, wherein The second capability information includes one or more of the following: The identifier of the AI / ML models supported by the terminal device; The identifier of the AI / ML models not supported by the terminal device.

41. The method according to claim 39 or 40, characterized in that, The second capability information indicates that the terminal device supports multiple AI / ML models. The multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates the default AI / ML model among the multiple AI / ML models.

42. The method according to any one of claims 23 to 41, characterized in that, The first physical channel is a data channel.

43. The method according to claim 42, wherein, The data channel is a physical downlink shared channel PDSCH, a physical uplink shared channel PUSCH, or a physical sidelink shared channel PSSCH.

44. A terminal device, characterized in that, Including: A first communication unit, configured to receive resource configuration information sent by a network device, where the resource configuration information includes first information and second information; Wherein, the first information is used to indicate time-domain position information and time-domain length information of a first time-domain resource, and the first time-domain resource is used to carry a first physical channel; Wherein, the second information is used to indicate artificial intelligence AI / machine learning ML configuration information associated with the first time-domain resource.

45. The terminal device according to claim 44, characterized in that, The AI / ML configuration information is used to configure the AI / ML functions supported by the first time-domain resource.

46. The terminal device according to claim 45, characterized in that, The AI / ML configuration information includes one or more of the following: Identity of the AI / ML function supported by the first time-domain resource; Identity of the AI / ML function not supported by the first time-domain resource.

47. The terminal device according to any one of claims 44 to 46, characterized in that, The AI / ML configuration information is used to configure the AI / ML model supported by the first time-domain resource.

48. The terminal device according to claim 47, characterized in that, The AI / ML configuration information includes one or more of the following: Identity of the AI / ML model supported by the first time-domain resource; Identity of the AI / ML model not supported by the first time-domain resource.

49. The terminal device according to claim 47 or 48, characterized in that, The AI / ML configuration information is used to configure the first time-domain resource to support multiple AI / ML models, and the multiple AI / ML models correspond to the same AI / ML function. The multiple AI / ML models include a default AI / ML model.

50. The terminal device according to any one of claims 44 to 49, characterized in that, The second information includes identification information of the AI / ML configuration information.

51. The terminal device according to any one of claims 44 to 50, characterized in that The terminal device further includes: A second communication unit, configured to receive first control information, where the first control information includes first indication information for indicating the first information.

52. The terminal device according to claim 51, characterized in that, The terminal device further includes: A third communication unit, configured to determine the first time-domain resource according to the time-domain position information and time-domain length information of the first time-domain resource; A fourth communication unit, configured to receive or transmit the first physical channel in the first time-domain resource according to the AI / ML configuration information associated with the first time-domain resource.

53. The terminal device according to claim 51 or 52, characterized in that, The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time-domain resource. The multiple AI / ML models correspond to the same AI / ML function. The first control information further includes second indication information for indicating one AI / ML model among the multiple AI / ML models.

54. The terminal device according to claim 53, characterized in that, The multiple AI / ML models include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

55. The terminal device according to any one of claims 51 to 54, characterized in that, The first control information is downlink control information DCI, or media access control control element MAC CE, or sidelink control information SCI.

56. The terminal device according to any one of claims 44 to 55, characterized in that, The time-domain position information includes one or more of the following: The starting time slot of the first time-domain resource; The starting symbol of the first time-domain resource.

57. The terminal device according to any one of claims 44 to 56, characterized in that, The time-domain length information includes one or more of the following: The number of time slots occupied by the first time-domain resource; The number of symbols occupied by the first time-domain resource.

58. The terminal device according to any one of claims 44 to 57, characterized in that, The resource configuration information is radio resource control RRC configuration information or system information block SIB.

59. The terminal device according to any one of claims 44 to 58, characterized in that, The terminal device further includes: A fifth communication unit, configured to send first capability information to the network device before the terminal device receives resource configuration information sent by the network device. The first capability information is used to indicate the AI / ML functions supported by the terminal device.

60. The terminal device according to claim 59, characterized in that, The first capability information includes one or more of the following: Identity of the AI / ML functions supported by the terminal device; Identity of the AI / ML functions not supported by the terminal device.

61. The terminal device according to any one of claims 44 to 60, characterized in that, The terminal device further includes: A sixth communication unit, configured to send second capability information to the network device before the terminal device receives resource configuration information sent by the network device, where the second capability information is used to indicate AI / ML models supported by the terminal device.

62. The terminal device according to claim 61, wherein, The second capability information includes one or more of the following: Identifiers of AI / ML models supported by the terminal device; Identifiers of AI / ML models not supported by the terminal device.

63. The terminal device according to claim 61 or 62, characterized in that, The second capability information indicates that the terminal device supports multiple AI / ML models, the multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates a default AI / ML model among the multiple AI / ML models.

64. The terminal device according to any one of claims 44 to 63, characterized in that, The first physical channel is a data channel.

65. The terminal device according to claim 64, wherein, The data channel is a Physical Downlink Shared Channel (PDSCH), a Physical Uplink Shared Channel (PUSCH), or a Physical Sidelink Shared Channel (PSSCH).

66. A network device, characterized in that, including: A first communication unit, configured to send resource configuration information to a terminal device, where the resource configuration information includes first information and second information; wherein the first information is used to indicate time domain position information and time domain length information of a first time domain resource, and the first time domain resource is used to carry a first physical channel; wherein the second information is used to indicate artificial intelligence (AI) / machine learning (ML) configuration information associated with the first time domain resource.

67. The network device according to claim 66, wherein, The AI / ML configuration information is used to configure an AI / ML function supported by the first time domain resource.

68. The network device according to claim 67, wherein The AI / ML configuration information includes one or more of the following: Identifiers of AI / ML functions supported by the first time domain resource; Identifiers of AI / ML functions not supported by the first time domain resource.

69. The network device according to any one of claims 66 to 68, characterized in that, The AI / ML configuration information is used to configure an AI / ML model supported by the first time domain resource.

70. The network device according to claim 69, wherein The AI / ML configuration information includes one or more of the following: Identifiers of AI / ML models supported by the first time domain resource; Identifiers of AI / ML models not supported by the first time domain resource.

71. The network device according to claim 69 or 70, characterized in that, The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time domain resource, the multiple AI / ML models correspond to the same AI / ML function, and the multiple AI / ML models include a default AI / ML model.

72. The network device according to any one of claims 66 to 71, characterized in that, The second information includes identification information of the AI / ML configuration information.

73. The network device according to any one of claims 66 to 72, characterized in that, The network device further includes: A second communication unit, configured to send first control information to the terminal device, where the first control information includes first indication information, and the first indication information is used to indicate the first information.

74. The network device according to claim 73, characterized in that, The AI / ML configuration information is used to configure multiple AI / ML models supported by the first time domain resource, the multiple AI / ML models correspond to the same AI / ML function, and the first control information further includes second indication information, and the second indication information is used to indicate an AI / ML model among the multiple AI / ML models.

75. The network device according to claim 74, wherein, The multiple AI / ML models further include a default AI / ML model, and the default AI / ML model is used when the first control information does not include the second indication information.

76. The network device according to any one of claims 73 to 75, characterized in that, The first control information is downlink control information DCI, or media access control control element MAC CE, or sidelink control information SCI.

77. The network device according to any one of claims 66 to 76, characterized in that, The time domain position information includes one or more of the following: The starting time slot of the first time domain resource; The starting symbol of the first time domain resource.

78. The network device according to any one of claims 66 to 77, characterized in that, The time domain length information includes one or more of the following: The number of time slots occupied by the first time domain resource; The number of symbols occupied by the first time domain resource.

79. The network device according to any one of claims 66 to 78, characterized in that, The resource configuration information is radio resource control RRC configuration information or system information block SIB.

80. The network device according to any one of claims 66 to 79, characterized in that, The network device further includes: A third communication unit, configured to receive first capability information sent by the terminal device before the network device sends resource configuration information to the terminal device, where the first capability information is used to indicate AI / ML functions supported by the terminal device.

81. The network device according to claim 80, characterized in that, The first capability information includes one or more of the following: An identifier of an AI / ML function supported by the terminal device; An identifier of an AI / ML function not supported by the terminal device.

82. The network device according to any one of claims 66 to 81, characterized in that, The network device further includes: A fourth communication unit, configured to send second capability information to the network device before the network device sends resource configuration information to the terminal device, where the second capability information is used to indicate AI / ML models supported by the terminal device.

83. The network device according to claim 82, characterized in that, The second capability information includes one or more of the following: An identifier of an AI / ML model supported by the terminal device; An identifier of an AI / ML model not supported by the terminal device.

84. The network device according to claim 82 or 83, characterized in that, The second capability information indicates that the terminal device supports multiple AI / ML models, the multiple AI / ML models correspond to the same AI / ML function, and the second capability information indicates a default AI / ML model among the multiple AI / ML models.

85. The network device according to any one of claims 66 to 84, characterized in that, The first physical channel is a data channel.

86. The network device according to claim 85, wherein, The data channel is a physical downlink shared channel PDSCH, a physical uplink shared channel PUSCH, or a physical sidelink shared channel PSSCH.

87. A terminal device, characterized in that, It includes a transceiver, a memory, and a processor. The memory is used to store a program, and the processor is used to call the program in the memory and control the transceiver to receive or send signals, so that the terminal device executes the method according to any one of claims 1 to 22.

88. A network device, characterized in that, It includes a transceiver, a memory, and a processor. The memory is used to store a program, and the processor is used to call the program in the memory and control the transceiver to receive or send signals, so that the network device executes the method according to any one of claims 23 to 43.

89. A device, characterized in that, It includes a processor, configured to call a program from a memory, so that the device executes the method according to any one of claims 1 to 22 or 23 to 43.

90. A chip, characterized in that, It includes a processor, configured to call a program from a memory, so that the device installed with the chip executes the method according to any one of claims 1 to 22 or 23 to 43.

91. A computer-readable storage medium, characterized in that, A program is stored thereon, and the program causes a computer to execute the method according to any one of claims 1 to 22 or 23 to 43.

92. A computer program product, characterized in that, It includes a program, and the program causes a computer to execute the method according to any one of claims 1 to 22 or 23 to 43.

93. A computer program, characterized in that, The computer program causes a computer to execute the method according to any one of claims 1 to 22 or 23 to 43.

Images