A communication method and a communication device

Abstract

The application provides a communication method and a communication device. The method comprises: a terminal device acquires association relationship information between at least one resource configuration and at least one AI function, and determines a first AI function associated with the first resource configuration based on the first resource configuration; further, the terminal device determines first channel information based on a reference signal indicated by the first resource configuration, and the first channel information is used for AI operation of the first AI function. Based on the above technical solution, different AI functions can be associated with resource configurations, so as to reasonably manage the constraint relationship between the RS resources corresponding to the multiple AI functions, thereby improving the efficiency and flexibility of AI-assisted channel acquisition.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0002] In wireless communication systems, accurate acquisition of channel state information (CSI) is crucial for improving system performance (such as spectral efficiency and link reliability). CSI acquisition relies on network devices or terminal devices transmitting reference signals (RS). For example, the channel state information reference signal (CSI-RS) is used for downlink channel measurement, and the sounding reference signal (SRS) is used for uplink channel measurement.

[0003] In one implementation, network devices can configure multiple independent RS resources for terminal devices, each RS resource corresponding to different CSI acquisition requirements. However, channel acquisition schemes based on artificial intelligence (AI) may involve multiple AI functions, and different AI functions may have different requirements for RS resources (such as measurement accuracy and update frequency). If the existing method of simply configuring RS resources independently continues, it may lead to wasted RS resources or limited performance of AI models.

[0004] Therefore, it is necessary to design an RS resource configuration scheme that can support multiple AI functions while also improving the efficiency and flexibility of AI-assisted channel acquisition. Summary of the Invention

[0005] Based on this, embodiments of this application provide a communication method and an RS configuration scheme, which is beneficial to improve the efficiency and flexibility of AI-assisted channel acquisition while supporting multiple AI functions.

[0006] Firstly, a communication method is provided, which can be executed by a terminal side. The terminal side can be a terminal-side device, or a chip or circuit of a terminal-side device. The terminal-side device can be replaced by a terminal device-side device, which can include at least one of a terminal device or an AI entity on the terminal device side. The AI ​​entity on the terminal device side can be the terminal device itself, or an AI entity serving the terminal device, such as a server, like an over-the-top (OTT) server or a cloud server.

[0007] The method includes: acquiring first association information, the first association information indicating that at least one resource configuration is associated with at least one AI function, wherein each resource configuration is associated with at least one AI function, and an AI function is associated with at least one resource configuration; determining first channel information based on a reference signal indicated by the first resource configuration, wherein the first resource configuration is one of the at least one resource configuration; the first channel information is used to perform an AI operation of a first AI function, wherein the first AI function is one or more of the at least one AI function associated with the first resource configuration, and the AI ​​operation is the AI ​​operation involved in the first AI function when the first resource configuration is applied to the first AI function.

[0008] In this embodiment of the application, the resource configuration is equivalent to the RS resource or RS resource configuration described in the background section above.

[0009] In the technical solution of this application, the terminal device acquires the association relationship between at least one resource configuration and at least one AI function, and determines the associated first AI function based on the first resource configuration. Further, it determines first channel information based on a reference signal indicated by the first resource configuration, wherein the first channel information is used to execute the AI ​​operation of the first AI function. Based on the above technical solution, different AI functions can be associated with resource configurations to reasonably manage the constraint relationships between the RS resources corresponding to these multiple AI functions, thereby improving the efficiency and flexibility of AI-assisted channel acquisition.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, obtaining the first association information includes: receiving the first association information sent by the network side.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving first indication information, the first indication information indicating a first AI function; and determining a first resource configuration based on the first AI function. Based on the above technical solution, determining the associated first resource configuration through the first AI function indicated by the first indication information can save signaling overhead.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining second association information, which indicates the association information between at least one resource configuration and at least one AI operation. Based on the above technical solution, AI functions, AI operations, and resource configurations can be linked together, so that the corresponding RS resources can be selected according to the specific operation of the AI ​​function, thereby supporting the RS resource requirements of different AI functions' AI operations.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, obtaining the second association information includes: receiving the second association information sent by the network side.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving second indication information, the second indication information indicating a first AI operation of a first AI function, the first AI operation being one or more of at least one AI operation; determining a first resource configuration based on the first AI operation of the first AI function; and using first channel information to execute the AI ​​operation of the first AI function, including: the first channel information being used to execute the first AI operation of the first AI function. Based on the above technical solution, the first resource configuration associated with the first AI function indicated by the second indication information can be determined, thereby saving signaling overhead.

[0015] For example, the first AI operation of the first AI function can also be default, i.e., the default configuration. When the first AI operation of the first AI function is indicated by the second instruction information, the first AI function and the first AI operation can be carried in different messages, or they can be carried in the same message. In some examples, the first AI function and the first AI operation are carried in different information elements within the same message; in other examples, the first AI function and the first AI operation are carried in the same information element within the same message.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, each AI operation in at least one AI operation includes at least one of the following: model inference, model training, model monitoring, model verification, model testing, and model evaluation.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining third association information, which indicates the association information between at least one of at least one AI operation, at least one AI function, and at least one resource configuration and at least one CSI reporting configuration, wherein the at least one AI operation includes the AI ​​operation of the first AI function. Based on the above technical solution, the AI ​​function, AI operation, resource configuration, and CSI reporting configuration can be linked together, so that the corresponding RS resources and CSI reporting configurations can be selected according to the AI ​​function, thereby supporting the different AI functions' requirements for RS resources and CSI reporting configurations.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, obtaining third association information includes: receiving third association information from the network side.

[0019] For example, one or more of the aforementioned first association information, second association information, and third association information can be carried in the same message or different messages. In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a first CSI reporting configuration corresponding to the first AI function, wherein the first CSI reporting configuration is one or more of at least one CSI reporting configuration; sending a first channel report based on the first CSI reporting configuration, wherein the first channel report is obtained by performing an AI operation of the first AI function, or, a first information report is used to perform an AI operation of the first AI function. Based on the above technical solution, the first CSI reporting configuration corresponding to the first AI function can be determined, ensuring the reception of RS and the reporting of RS measurement results.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining the first CSI reporting configuration based on the first AI function. Based on the above technical solution, the CSI reporting configuration corresponding to the first AI function can be determined, thereby saving signaling overhead.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining the first CSI reporting configuration based on the first AI operation of the first AI function. Based on the above technical solution, the CSI reporting configuration corresponding to the first AI operation of the first AI function can be determined, thereby saving signaling overhead.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the first AI function includes at least one of the following: channel estimation function, channel prediction function, and channel compression function.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, each resource configuration indicates information of at least one of the following: the frequency domain density of the reference signal, the port density, the transmission period, or the time domain location where the reference signal is not transmitted.

[0024] In conjunction with the first aspect, in certain implementations of the first aspect, the resource configuration includes one or more of the following: a first resource configuration and a second, a third, and a fourth resource configuration: The first resource configuration indicates the complete set of resources used for transmitting reference signals, the complete set including the complete set of REs transmitting reference signals on multiple first time units and the complete set of air interface resources; the second resource configuration indicates a first subset of the complete set of resources used for transmitting reference signals, the first subset including a subset of the complete set of REs transmitting reference signals on each first time unit and / or a subset of the complete set of air interface resources transmitting reference signals on each first time unit; the third resource configuration indicates a second subset of the complete set of resources used for transmitting reference signals, the second subset including some of the first time units; the fourth resource configuration indicates a third subset of the complete set of resources used for transmitting reference signals, the third subset including a subset of the complete set of REs on all or some of the first time units in some first time units and / or a subset of the complete set of air interface resources on all or some of the first time units in some first time units.

[0025] In conjunction with the first aspect, in certain implementations of the first aspect, when the first AI function includes channel estimation, the first resource configuration is a second resource configuration; or, when the first AI function includes channel prediction, the first resource configuration is a third resource configuration; or, when the first AI function includes channel compression, the first resource configuration is a first resource configuration; or, when the first AI function includes both channel estimation and channel prediction, the first resource configuration is a fourth resource configuration. Based on the above technical solutions, it is possible to clearly define which resource configuration corresponds to different AI functions, supporting the different resource configuration requirements of different AI functions.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the second resource configuration is determined jointly by the first resource configuration and the first information, where the first information indicates the complement of the first subset, and the resources corresponding to the complement of the first subset are not used to transmit reference signals; the third resource configuration is determined jointly by the first resource configuration and the second information, where the second information indicates the complement of the second subset, and the resources corresponding to the complement of the second subset are not used to transmit reference signals; the fourth resource configuration is determined jointly by the first resource configuration and the third information, where the third information indicates the complement of the third subset, and the resources corresponding to the complement of the third subset are not used to transmit reference signals. Based on the above technical solutions, different resource configurations can be indicated through mask indication, enabling flexible indication and avoiding resource waste.

[0027] For example, one or more of the first, second, and third information mentioned above may be from the network side, that is, the terminal side receives one or more of the first, second, and third information from the network side.

[0028] For example, in the embodiments of this application, at least two of the first information, the second information, or the third information can be carried by the same information element, or the first information, the second information, and the third information can be carried by different information elements, wherein the different information elements can be carried in the same message or in different messages.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the first resource configuration is one of the first resource configuration, the second resource configuration, the third resource configuration, and the fourth resource configuration.

[0030] In conjunction with the first aspect, in certain implementations of the first aspect, the CSI reporting configuration includes a CSI-RS configuration and a CSI report configuration. The CSI-RS configuration indicates that the first channel report is associated with any of the following resource densities: a first resource density, where the first resource density is greater than or equal to a first value; and a second resource density, where the second resource density is less than or equal to a second value, and the first value is greater than the second value. The CSI report configuration indicates that the first channel report is associated with any of the following CSI bit counts and / or quantization bit widths: a first CSI bit count and / or a first quantization bit width, where the first CSI bit count is greater than or equal to a third value, and the first quantization bit width is greater than or equal to a fourth value; and a second CSI bit count and / or a second quantization bit width, where the second CSI bit count is less than or equal to a fifth value, and the second quantization bit width is less than or equal to a sixth value; wherein the third value is greater than the fifth value, and the fourth value is greater than the sixth value. For example, the first and second values ​​are preset. In one possible implementation, the first value can be equal to the second value; that is, the first resource density and the second resource density can be distinguished using the same value in this case. This value can be classified into the range of the first resource density or the range of the second resource density.

[0031] For example, the CSI bit count indicates the number of bits used in the CSI channel report, and the quantization bit width indicates the quantization bit width (the number of bits used for each parameter element) used when representing CSI parameters (such as channel matrix elements, precoding matrix indicator PMI, channel quality indicator CQI, etc.) during the generation of the CSI channel report. In one possible case, the third value can also be equal to the fifth value; that is, in this case, the first and second CSI bit counts can be distinguished by the same value, which can fall within the range of the first or second CSI bit count. Similarly, the fourth value can also be equal to the sixth value.

[0032] In conjunction with the first aspect, in certain implementations of the first aspect, when the first AI function includes at least one of channel estimation, channel prediction, and channel compression, the first channel report obtained by performing model inference on the first AI function is associated with the second resource density; or, the first channel report used for performing model monitoring, model training, model verification, model testing, or model evaluation on the first AI function is associated with the first resource density; or, when the first AI function is a channel estimation function, the first channel report is associated with the second resource density; or, when the first AI function is a channel prediction function, the first channel report is associated with the second resource density; or, when the first AI function is a channel compression function, the first channel report is associated with the first resource density. Based on the above technical solutions, different AI functions can be associated with different CSI reporting configurations to achieve effective resource utilization and avoid resource waste.

[0033] Secondly, a communication method is provided, which can be executed by the network side. The network side can include at least one of a network device or an AI entity on the network device side. The AI ​​entity on the network device side can be the network device itself, or an AI entity serving the network device (which can also be replaced by intelligent network elements, etc., without limitation), such as a radio access network (RAN), an intelligent controller (RIC), operation administration and maintenance (OAM), a server, etc., such as a cloud server. Here, intelligent network elements can also be understood as network devices with AI functions, which can be applied in O-RAN architectures or non-O-RAN architectures, without limitation.

[0034] The method includes: determining first association information, the first association information indicating that at least one resource configuration is associated with at least one AI function, wherein each resource configuration is associated with at least one AI function, and an AI function is associated with at least one resource configuration; sending the first association information; wherein the at least one resource configuration includes a first resource configuration, the first resource configuration being used to determine first channel information based on an indicated reference signal, the first channel information being used to perform an AI operation of a first AI function, the first AI function being one or more of the at least one AI function associated with the first resource configuration, and the AI ​​operation being an AI operation involved in the first AI function when the first resource configuration is applied to the first AI function.

[0035] In the technical solution of this application, the network device sends at least one resource configuration and at least one AI function association information to the terminal device, which can associate different AI functions with resource configurations in order to reasonably manage the constraint relationship between the RS resources corresponding to these multiple AI functions, thereby improving the efficiency and flexibility of AI-assisted channel acquisition.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending first indication information, which indicates a first AI function. Based on the above technical solution, determining the associated first resource configuration through the first AI function indicated by the first indication information can save signaling overhead.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes sending second association information, which indicates the association information between at least one resource configuration and at least one AI operation. Based on the above technical solution, AI functions, AI operations, and resource configurations can be linked together, so that the corresponding RS resources can be selected according to the specific operation of the AI ​​function, thereby supporting the RS resource requirements of different AI functions' AI operations.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending second indication information, the second indication information indicating a first AI operation of a first AI function, the first AI operation being one or more of at least one AI operation, and the first AI operation of the first AI function being associated with a first resource configuration.

[0039] For example, the first AI operation of the first AI function can also be default, i.e., the default configuration. When the first AI operation of the first AI function is indicated by the second instruction information, the first AI function and the first AI operation can be carried in different messages, or they can be carried in the same message. In some examples, the first AI function and the first AI operation are carried in different information elements within the same message; in other examples, the first AI function and the first AI operation are carried in the same information element within the same message.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, each AI operation in at least one AI operation includes at least one of the following: model inference, model training, model monitoring, model validation, model testing, and model evaluation.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending third association information, the third association information indicating the association information between at least one of at least one AI operation, at least one AI function, and at least one resource configuration and at least one CSI reported configuration, wherein at least one AI operation includes the AI ​​operation of the first AI function.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: receiving a first channel report, the first channel report being obtained by performing an AI operation of a first AI function, or a first information report being used to perform an AI operation of a first AI function, wherein the first AI function corresponds to a first CSI reporting configuration, and the first CSI reporting configuration is one or more of at least one CSI reporting configuration.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the first AI function includes at least one of the following: channel estimation function, channel prediction function, and channel compression function.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, each resource configuration indicates information of at least one of the following: the frequency domain density of the reference signal, the port density, the transmission period, or the time domain location where the reference signal is not transmitted.

[0045] In conjunction with the second aspect, in certain implementations of the second aspect, the resource configuration includes one or more of the following: a first resource configuration and a second, third, and fourth resource configuration: The first resource configuration indicates the complete set of resources used for transmitting reference signals, the complete set including the complete set of REs transmitting reference signals on multiple first time units and the complete set of air interface resources; the second resource configuration indicates a first subset of the complete set of resources used for transmitting reference signals, the first subset including a subset of the complete set of REs transmitting reference signals on each first time unit and / or a subset of the complete set of air interface resources transmitting reference signals on each first time unit; the third resource configuration indicates a second subset of the complete set of resources used for transmitting reference signals, the second subset including some of the first time units; the fourth resource configuration indicates a third subset of the complete set of resources used for transmitting reference signals, the third subset including a subset of the complete set of REs on all or some of the first time units in some first time units and / or a subset of the complete set of air interface resources on all or some of the first time units in some first time units.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, when the first AI function includes a channel estimation function, the first resource configuration is a second resource configuration; or, when the first AI function includes a channel prediction function, the first resource configuration is a third resource configuration; or, when the first AI function includes a channel compression function, the first resource configuration is a first resource configuration; or, when the first AI function includes both a channel estimation function and a channel prediction function, the first resource configuration is a fourth resource configuration.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the second resource configuration is determined jointly by the first resource configuration and the first information, where the first information indicates the complement of the first subset, and the resources corresponding to the complement of the first subset are not used to transmit reference signals; the third resource configuration is determined jointly by the first resource configuration and the second information, where the second information indicates the complement of the second subset, and the resources corresponding to the complement of the second subset are not used to transmit reference signals; the fourth resource configuration is determined jointly by the first resource configuration and the third information, where the third information indicates the complement of the third subset, and the resources corresponding to the complement of the third subset are not used to transmit reference signals.

[0048] For example, one or more of the first, second, or third information mentioned above may be sent from the network side to the terminal device, and correspondingly, the terminal side receives one or more of the first, second, or third information from the network side.

[0049] For example, in embodiments of this application, at least two of the first, second, or third information can be carried by the same information element, or the first, second, and third information can be carried by different information elements, wherein the different information elements can be carried in the same message or in different messages. In conjunction with the second aspect, in some implementations of the second aspect, the first resource configuration is one of a first resource configuration, a second resource configuration, a third resource configuration, and a fourth resource configuration.

[0050] In conjunction with the second aspect, in some implementations of the second aspect, the CSI reporting configuration includes a CSI-RS configuration and a CSI report configuration. The CSI-RS configuration indicates that the first channel report is associated with any of the following resource densities: a first resource density, where the first resource density is greater than or equal to a first value; and a second resource density, where the second resource density is less than or equal to a second value, and the first value is greater than the second value. The CSI report configuration indicates that the first channel report is associated with any of the following CSI bit counts and / or quantization bit widths: a first CSI bit count and / or a first quantization bit width, where the first CSI bit count is greater than or equal to a third value, and the first quantization bit width is greater than or equal to a fourth value; and a second CSI bit count and / or a second quantization bit width, where the second CSI bit count is less than or equal to a fifth value, and the second quantization bit width is less than or equal to a sixth value; wherein the third value is greater than the fifth value, and the fourth value is greater than the sixth value. For example, the first and second values ​​are preset. Optionally, in one possible implementation, the first value can be equal to the second value; that is, the first resource density and the second resource density can be distinguished using the same value in this case.

[0051] For example, the CSI bit count indicates the number of bits used in the CSI channel report, and the quantization bit width indicates the quantization bit width (the number of bits used for each parameter element) used when representing CSI parameters (such as channel matrix elements, precoding matrix indicator PMI, channel quality indicator CQI, etc.) during the generation of the CSI channel report. Optionally, in one possible case, the third value can also be equal to the fifth value; that is, in this case, the first CSI bit count or the second CSI bit count can be distinguished by the same value. Similarly, the fourth value can also be equal to the sixth value.

[0052] In conjunction with the second aspect, in certain implementations of the second aspect, when the first AI function includes at least one of channel estimation, channel prediction, and channel compression, the first channel report obtained by performing model inference on the first AI function is associated with the second resource density; or, the first channel report used for performing model monitoring, model training, model verification, model testing, or model evaluation on the first AI function is associated with the first resource density; or, when the first AI function is a channel estimation function, the first channel report is associated with the second resource density; or, when the first AI function is a channel prediction function, the first channel report is associated with the second resource density; or, when the first AI function is a channel compression function, the first channel report is associated with the first resource density.

[0053] Thirdly, a communication device is provided, which can be a terminal-side device, or a device or module for performing corresponding functions of the terminal-side device.

[0054] One possible implementation is that the communication device may include modules or units corresponding to the methods / operations / steps / actions described in the first aspect, which may be hardware circuits, software, or a combination of hardware circuits and software.

[0055] The aforementioned terminal-side devices can be terminal devices or AI entities on the terminal device side, without limitation.

[0056] Fourthly, a communication device is provided, which may be a network-side device, or a device or module for performing corresponding functions of a network-side device.

[0057] One possible implementation is that the communication device may include modules or units corresponding to the methods / operations / steps / actions described in the second aspect, which may be hardware circuits, software, or a combination of hardware circuits and software.

[0058] The aforementioned network-side devices can be network devices or AI entities on the network device side.

[0059] Fifthly, a communication device is provided, including a processor configured to, by executing a computer program or instructions, or by logic circuitry, cause the communication device to perform the method described in the first aspect and any possible manner of the first aspect; or cause the communication device to perform the method described in the second aspect and any possible manner of the second aspect.

[0060] In one possible implementation, the communication device further includes a memory for storing the computer program or instructions.

[0061] In one possible implementation, the communication device also includes a communication interface for inputting and / or outputting signals.

[0062] A sixth aspect provides a communication device including logic circuitry and an input / output interface for inputting and / or outputting signals, the logic circuitry being configured to perform the method described in the first aspect and any possible mode of the first aspect; or the logic circuitry being configured to perform the method described in the second aspect and any possible mode of the second aspect.

[0063] In a seventh aspect, a computer-readable storage medium is provided, on which a computer program or instructions are stored, which, when executed on a computer, cause the method described in the first aspect and any possible manner of the first aspect to be performed; or cause the method described in the second aspect and any possible manner of the second aspect to be performed.

[0064] Eighthly, a computer program product is provided, comprising instructions that, when executed on a computer, cause the method described in the first aspect and any possible mode of the first aspect to be performed; or cause the method described in the second aspect and any possible mode of the second aspect to be performed.

[0065] A ninth aspect provides a chip or chip system comprising: one or more processors configured to execute computer programs or instructions in the memory, such that the chip or chip system implements the methods of the first aspect and any possible implementation thereof; or, such that the chip or chip system implements the methods of the second aspect and any possible implementation thereof.

[0066] For a description of the beneficial effects of any of the second to ninth aspects, please refer to the description of the beneficial effects of the first aspect, which will not be repeated here. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of an application framework applicable to an embodiment of this application.

[0068] Figure 2 This is a schematic diagram of another application framework applicable to the embodiments of this application.

[0069] Figure 3 This is a schematic diagram of a communication system applicable to an embodiment of this application.

[0070] Figure 4 This is a schematic diagram of another communication system to which the embodiments of this application apply.

[0071] Figure 5 This is a schematic diagram of an AI model used to implement channel prediction.

[0072] Figure 6 This is a schematic diagram of an AI model used to implement channel compression and reconstruction (or reconfiguration).

[0073] Figure 7 This is a schematic diagram of an AI model used to implement channel estimation.

[0074] Figure 8 This is a schematic flowchart of a communication method 800 provided in an embodiment of this application.

[0075] Figure 9 The first resource configuration, the second resource configuration, the third resource configuration, and the fourth resource configuration are shown.

[0076] Figure 10 This is a schematic flowchart of a communication method 1000 provided in an embodiment of this application.

[0077] Figure 11 This is a schematic flowchart of a communication method 800 provided in another embodiment of this application.

[0078] Figure 12 This is a schematic flowchart of a communication method 1200 provided in an embodiment of this application.

[0079] Figure 13 This is a schematic flowchart of a communication method 800 provided in another embodiment of this application.

[0080] Figure 14 This is a schematic flowchart of a communication method 1400 provided in an embodiment of this application.

[0081] Figure 15 This is a schematic block diagram of a communication device according to an embodiment of this application.

[0082] Figure 16 This is another schematic block diagram of the communication device according to an embodiment of this application.

[0083] Figure 17 This is a schematic diagram of the structure of a possible AI processor 1700 provided in an embodiment of this application. Detailed Implementation

[0084] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0085] To facilitate understanding of the embodiments of this application, the following points will be explained first.

[0086] I. In this application, unless otherwise stated, "multiple" means two or more.

[0087] II. In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0088] III. The various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of protection of this application. The magnitude of the serial numbers used in this application does not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic. For example, the terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0089] Furthermore, any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0090] IV. The terms “comprising” and “having” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or that are inherent to such process, method, product or device.

[0091] V. In this application, "for indicating" can be understood as "enabling". "Enabling" can include direct enabling and indirect enabling. When describing information for enabling A, it can include whether the information directly enables A or indirectly enables A, but it does not mean that the information necessarily carries A.

[0092] The information that enables the information is called the information to be enabled. In the specific implementation process, there are many ways to enable the information to be enabled, such as, but not limited to, directly enabling the information to be enabled, such as the information to be enabled itself or its index. It can also be indirectly enabled by enabling other information, where there is a relationship between the other information and the information to be enabled. It can also enable only a part of the information to be enabled, while the other parts are known or pre-agreed upon. For example, enabling specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing enabling overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and enabled uniformly to reduce the enabling overhead caused by individually enabling the same information.

[0093] VI. In this application, "pre-configuration" may include pre-defined terms, such as protocol definitions. These "pre-defined terms" can be implemented by pre-storing corresponding codes, tables, or other means of indicating relevant information in the device (e.g., including various network elements). This application does not limit the specific implementation method.

[0094] VII. The term "storage" or "preservation" in this application can refer to storage in one or more memory devices. These memory devices can be separately configured or integrated into an encoder or decoder, processor, or communication device. Alternatively, some memory devices can be separately configured, while others can be integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this is not limited.

[0095] 8. The “protocol” involved in this application may refer to standard protocols in the field of communications, such as fourth-generation (4G) network protocols, fifth-generation (5G) network protocols, new radio (NR) protocols, 5.5G network protocols, and related protocols applied in future communication systems. This application does not limit the scope of the term.

[0096] 9. The arrows or boxes indicated by dashed lines in the schematic diagrams in the accompanying drawings of this application represent optional steps or optional modules.

[0097] 10. In this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. In this application, "and / or" is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0098] XI. In this application, the indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication information A means including information A. Implicit indication information A means indicating information A through the correspondence between information A and information B, and through direct indication information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0099] 12. In this application, information C is used to determine information D, including both when information D is determined solely based on information C and when it is determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, when information D is determined based on information E, and information E is determined based on information C.

[0100] Thirteen, in this application, "device A sends information A to device B" can be understood as device B being the destination of information A or an intermediate network element in the transmission path between the destination and the destination, which may include sending information to device B directly or indirectly.

[0101] 14. In this application, "device B receives information A from device A" can be understood as device A being the source of information A or an intermediate network element in the transmission path between device B and device A. This can include receiving information directly or indirectly from device A. Information may undergo necessary processing, such as format changes, between the source and destination ends, but the destination end can understand the valid information from the source end. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0102] First, the communication system to which the embodiments of this application are applicable will be described.

[0103] The technical solutions provided in this application can be applied to various communication systems, such as 5G or NR systems, Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Wireless Local Area Network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0104] In a communication system, a device can send signals to or receive signals from another device. Signals may include information, signaling, or data. A device can also be replaced by an entity, network entity, equipment, communication device, communication module, node, communication node, etc. This application describes a device as an example. For instance, a communication system may include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device, and / or, the terminal device can send sidelink signals to another terminal device, and / or, the network device can send signals to another network device.

[0105] In this application embodiment, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0106] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0107] As an example, and not a limitation, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functionality without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0108] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0109] The network device in this application embodiment may include a device for communicating with a terminal device. This network device may include an access network device or a radio access network device, such as a base station. The network device in this application embodiment may also include a radio access network (RAN) node (or device) for connecting the terminal device to a wireless network.

[0110] A base station can broadly encompass various names like the following, or be replaced by them, such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, RAN intelligent controller (RIC), etc.

[0111] A base station can also be a macro base station, micro base station, relay node, donor node, or similar entity, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center and equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in future communication networks, or equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies.

[0112] Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technology or equipment form used in the network devices.

[0113] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0114] In some deployments, network devices can be devices that include CUs or DUs, or devices that include both CUs and DUs, or devices with control plane CU nodes (central unit-control plane, CU-CP) and user plane CU nodes (central unit-user plane, CU-UP) and DU nodes. For example, network devices include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0115] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0116] RAN nodes can support one or more types of fronthaul interfaces, and different fronthaul interfaces correspond to DU and RU with different functions.

[0117] If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions.

[0118] If the fronthaul interface between DU and RU is a different interface, relative to CPRI, some baseband functions for downlink and / or uplink, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast fourier transform (IFFT) / adding a cyclic prefix (CP), are moved from DU to RU; and for uplink, digital beamforming (BF), or one or more of fast fourier transform (FFT) / removing a cyclic prefix (CP), are moved from DU to RU.

[0119] One possible implementation is that the interface can be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0120] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to RU. For uplink transmission, de-RE mapping is used as the dividing line. DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-mapping, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions following de-mapping (e.g., digital BF or fast Fourier transform (FFT) / CP removal) are moved to RU. Understandably, the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0121] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0122] In different communication systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open RAN (ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0123] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0124] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0125] Furthermore, terminal devices and network devices can be hardware devices, software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of terminal devices and network devices.

[0126] In wireless communication networks (such as mobile communication networks), the services supported by the networks are becoming increasingly diverse, and the requirements they need to meet are also becoming more varied. For example, networks need to support ultra-high speeds, ultra-low latency, and massive connectivity. This characteristic makes network planning, network configuration, and resource scheduling increasingly complex. As network functions become more powerful, such as supporting higher spectrum, supporting higher-order multiple-input multiple-output (MIMO) technology, supporting beamforming, and / or supporting beam management and other new technologies, network energy saving has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet these challenges, AI technology can be introduced into wireless communication networks to achieve network intelligence.

[0127] To support AI technology in wireless networks, AI nodes (also known as AI entities) may be introduced into the network.

[0128] Optionally, the AI ​​entity can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, or the AI ​​entity can be deployed independently, for example, in a location other than any of the aforementioned devices, such as the host or cloud server of an OTT system. The AI ​​entity can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or network elements of the core network. Based on the object served by the AI ​​entity, the AI ​​entity can include an AI entity on the network device side, an AI entity on the terminal device side, or an AI entity on the core network side.

[0129] It is understood that this application does not limit the number of AI entities. For example, when there are multiple AI entities, they can be divided based on function, such as different AI entities being responsible for different functions.

[0130] It can also be understood that AI entities can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network components in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI entities.

[0131] AI entities can be AI network elements or AI modules. AI entities are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the different parameter configurations, the AI ​​model within an AI entity can achieve different functions. The AI ​​model within an AI entity can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0132] An AI entity can have one or more models. The learning, training, or inference processes of different models can be deployed in different entities or devices, or they can be deployed in the same entity or device.

[0133] Figure 1 This is a schematic diagram of an application framework applicable to an embodiment of this application. For example... Figure 1 As shown, the devices are connected via interfaces (e.g., NG, Xn) or air interfaces. These device nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 1 (Only one is shown in the image). An access network node can be a single RAN node or can include multiple RAN nodes, such as RU, CU, and DU. One or more of the RU, CU, or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI modules are configured in CU-CP and / or CU-UP.

[0134] This AI module is used to implement corresponding AI functions. AI modules deployed in different devices can be the same or different. Depending on the parameter configuration, the AI ​​module can achieve different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0135] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0136] Figure 2 This is a schematic diagram illustrating another application framework applicable to the embodiments of this application. For example... Figure 2 As shown, the communication system includes a RIC. For example, the RIC could be... Figure 1 The AI ​​module in the RAN node shown is used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (Non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0137] Near real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Near real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data.

[0138] Optionally, near real-time RIC can deliver inference results to RAN nodes and / or terminals.

[0139] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, near real-time RIC submits inference results to DU, and DU sends them to RU.

[0140] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals.

[0141] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, a non-real-time RIC can submit inference results to DU, which in turn can send them to RU.

[0142] Near real-time RICs and non-real-time RICs can also be configured as separate devices. Alternatively, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be configured in RAN nodes (e.g., CU, DU), while non-real-time RICs can be configured in OAM, cloud servers, core network devices, or other devices.

[0143] Figure 3 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 3 As shown, the communication system may include at least one network device, such as network device 110; the communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130. Network device 110 and terminal devices (such as terminal devices 120 and 130) can communicate via a wireless link. The communication devices in the communication system, for example, network device 110 and terminal device 120, can communicate with each other via multi-antenna technology.

[0144] Figure 4 This is a schematic diagram of another communication system to which embodiments of this application apply. Compared to Figure 3 Regarding the aforementioned communication system, Figure 4 The communication system shown also includes an AI device 140, which is used to perform AI-related operations, such as building training datasets or training AI models. The AI ​​device 140 is the aforementioned AI node or AI entity.

[0145] In one possible implementation, network device 110 sends data related to the training of the AI ​​model to AI device 140, whereby AI device 140 constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. AI device 140 sends the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model is deployed on network device 110, and another portion is deployed on the terminal device. Alternatively, the trained AI model is deployed on network device 110. Or, the trained AI model is deployed on the terminal device.

[0146] It should be understood that Figure 4 Taking the direct connection between AI device 140 and network device 110 as an example, in other scenarios, AI device 140 can also be connected to a terminal device; AI device 140 can also be connected to both network device 110 and a terminal device simultaneously; AI device 140 can also be connected to network device 110 through a third-party device, etc. Therefore, this application does not limit the connection relationship between AI device and other devices.

[0147] The AI ​​device 140 can also be installed as a module in network devices and / or terminal devices, for example, installed in Figure 3 Among the network devices 110 or terminal devices shown.

[0148] It should be noted that, Figure 3 and Figure 4 This is a simplified illustration for ease of understanding only. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices. Figure 3 and Figure 4 Not shown in the diagram. In practical applications, this communication system may include multiple network devices (such as network device 110 and network device 150). Figure 3 (Not shown) It may also include multiple terminal devices. Therefore, this application does not limit the number of network devices and terminal devices included in the communication system.

[0149] The following description, in conjunction with the accompanying drawings, details some of the AI ​​functions involved in the embodiments of this application.

[0150] Channel prediction: Figure 5This is a schematic diagram of an AI model used to implement channel prediction. As shown, the model's input is historical channel information, and its output is the predicted future channel information, i.e., the predicted value of the channel information. Model training data can include historical channel information and the ground truth values ​​of future channel information. Model training can involve updating model parameters with the objective of minimizing the error between the predicted and ground truth values ​​(e.g., minimum square error (MSE)). The model's performance is evaluated by the error (e.g., MSE) or similarity (e.g., square generalized cosine similarity (SGCS)) between the predicted and actual future channel information; the smaller the error or the higher the similarity, the better the performance.

[0151] Channel compression and reconstruction: can be achieved through channel compression models and channel reconstruction models. Figure 6 This diagram illustrates an AI model used to implement channel compression and reconstruction (or reconfiguration). As shown, the input to the channel compression model can be the original channel information, such as a channel matrix, precoding matrix, or eigenvector, and the output can be compressed bits. The input to the channel reconstruction model (or channel reconfiguration model) can be compressed bits, and the output can be reconstructed (or reconfigured) channel information. Model training data includes the original channel information. Model training can involve updating model parameters with the goal of minimizing the error (e.g., MSE) between the reconstructed channel obtained through the channel compression model and the original channel and the original channel. The model's performance is evaluated by the error (e.g., MSE) or similarity (e.g., SGCS) between the reconstructed channel and the original channel; the smaller the error or the higher the similarity, the better the performance.

[0152] Channel estimation: Figure 7This diagram illustrates an AI model used for channel estimation. As shown, the model's input is the received signal, including multiple resource elements (REs). Some of these REs carry reference signals (RS), also known as pilot signals. The model's output is the estimated channel information corresponding to the multiple REs. Training data can include the channel information corresponding to the received signal or pilot REs, as well as the channel information of all REs (e.g., true channel information, i.e., the ground truth of the channel information). Model training can involve updating model parameters with the objective of minimizing the error (MSE) between the estimated channel information of all REs and the true channel information of all REs. Model performance is evaluated by the error (MSE) or similarity (SGCS) between the estimated channel information and the true channel information; smaller errors or higher similarity indicate better performance.

[0153] It should be understood that the AI ​​functions involved in the embodiments of this application are not limited to the examples described above.

[0154] As described in the background section above, this application aims to provide an RS configuration scheme that can support multiple AI functions while also reasonably managing the constraints between the RS resources corresponding to these multiple AI functions (such as frequency domain / time domain multiplexing, conflict avoidance, etc.) to improve the efficiency and flexibility of AI-assisted channel acquisition.

[0155] To facilitate understanding, before introducing the embodiments of this application, the technical terms involved will be briefly introduced first.

[0156] Channel information, reference signal, channel report:

[0157] In communication systems (e.g., LTE or NR systems), network devices determine one or more configurations, such as data channel resources, MCS (Multi-Channel System), and precoding, for scheduling terminal devices based on channel information. Channel information, also known as channel state information (CSI) or channel environment information, is information that reflects channel characteristics and quality.

[0158] Channel information measurement refers to the process by which the receiver deciphers the channel information based on a reference signal transmitted by the transmitter; that is, it involves estimating the channel information using channel estimation methods. For example, the reference signal may include one or more of the following: channel state information reference signal (CSI-RS), synchronizing signal / physical broadcast channel block (SSB), sounding reference signal (SRS), or demodulation reference signal (DMRS). One or more of CSI-RS, SSB, and DMRS can be used to measure downlink channel information. SRS and / or DMRS can be used to measure uplink channel information.

[0159] Channel information can be determined based on channel measurement results of a reference signal. Alternatively, channel information can be the channel measurement results of a reference signal. In the embodiments of this application, the channel measurement results of the reference signal or the channel measurement results can also be replaced by channel information.

[0160] Taking FDD communication as an example, in FDD communication, because uplink and downlink channels lack reciprocity or cannot guarantee reciprocity, network devices need to obtain downlink CSI through uplink feedback from terminal devices. Network devices typically send a downlink reference signal to the terminal device, which receives this signal. Since the terminal device knows the transmission information of the downlink reference signal, it can perform channel measurement and interference measurement based on the received signal to estimate the downlink channel traversed by the downlink reference signal. The terminal device then generates the downlink CSI based on this measurement and the resulting downlink channel matrix. The terminal device generates a CSI report according to a predefined protocol method or a network device configuration method and feeds it back to the network device so that it can obtain the downlink CSI.

[0161] In this application, the meaning of CSI is broader than that of CSI in traditional schemes. It is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI). It can also be channel response information (such as channel response matrix, frequency domain channel response information, time domain channel response information), weight information corresponding to the channel response, reference signal receiving power (RSRP), or signal to interference plus noise ratio (SINR) or one or more of these.

[0162] In this context, RI indicates the recommended number of downlink transmission layers for the receiving end of the reference signal, such as a terminal device; CQI indicates the modulation and coding schemes supported by the current channel conditions for the receiving end of the reference signal, such as a terminal device; and PMI indicates the recommended precoding for the receiving end of the reference signal, such as a terminal device. The number of precoding layers indicated by PMI corresponds to RI.

[0163] As mentioned earlier, channel information can be obtained by measuring the reference signal. Compressing and / or quantizing this channel information yields feedback information. Decompressing and / or dequantizing this feedback information recovers the channel information. Decompression can also be understood as recovery or reconstruction, which will not be elaborated upon further below.

[0164] It should be understood that feedback information can also be referred to as channel information feedback information, CSI feedback information, CSI feedback information, compressed information, channel information compressed information, CSI compressed information, compressed channel information, or compressed CSI, etc., and the embodiments of this application do not limit this.

[0165] It should also be understood that feedback information can be reported through channel information reports, such as CSI reports. Therefore, feedback information can also be referred to as channel reports. In the embodiments of this application, a channel report may include at least one sub-channel report.

[0166] The communication method provided in the embodiments of this application will be described in detail below with reference to specific accompanying drawings. It should be noted in advance that... Figures 8 to 13 This explanation uses the terminal device as the terminal side and the network device as the network side as an example. For ease of understanding, in... Figures 8 to 13In the relevant content and descriptions, terminal devices are used instead of terminal side and network devices are used instead of network side.

[0167] For example, the terminal side can be a terminal-side device, or a chip or circuit of a terminal-side device. The terminal-side device can be replaced by a terminal device-side device, which can include at least one of a terminal device or an AI entity on the terminal device side. The AI ​​entity on the terminal device side can be the terminal device itself, or an AI entity serving the terminal device, such as a server, like an over-the-top (OTT) server or a cloud server.

[0168] For example, the network side may include at least one of a network device or an AI entity on the network device side. The AI ​​entity on the network device side can be the network device itself, or an AI entity serving the network device (which can also be replaced by intelligent network elements, etc., without limitation), such as a radio access network (RAN), a RAN intelligent controller (RIC), operation administration and maintenance (OAM), a server, etc., such as a cloud server. Here, an intelligent network element can also be understood as a network device with AI functionality, which can be applied in O-RAN architectures or non-O-RAN architectures, without limitation.

[0169] It is understood that the terminal device in the embodiments of this application can also be replaced by a terminal side, or other devices including the terminal side, such as an AI entity on the terminal device side, such as a server. Correspondingly, the network device in the embodiments of this application can also be replaced by a network side, or other devices including the network side, such as an AI entity on the network device side, such as a server.

[0170] Figure 8 A schematic flowchart of a communication method 800 provided in an embodiment of this application is shown below. Figure 8 As shown, the method includes at least the following steps.

[0171] S810, the terminal device obtains the first association information.

[0172] Optionally, S810 can also be executed by other entities on the terminal side, such as servers with AI capabilities, which obtain the first association information from the terminal device.

[0173] The first association information indicates that at least one resource configuration is associated with at least one AI function. Specifically, each resource configuration is associated with at least one AI function, and an AI function is associated with at least one resource configuration. The association of each resource configuration with at least one AI function can be understood as one or more resource configurations within the at least one resource configuration being associated with one AI function, and / or one or more resource configurations within the at least one resource configuration being associated with at least two AI functions. It should be understood that in the embodiments of this application, "association" can be replaced with "related," "corresponding," etc., and is not limited thereto.

[0174] The AI ​​functions may include any one of the following: channel estimation, channel prediction, and channel compression. Descriptions of the channel estimation, channel prediction, and channel compression functions can be found above. It should be understood that the above AI functions are merely examples, and the embodiments of this application do not impose limitations on them.

[0175] In this application embodiment, resource configuration may include the following two implementation methods:

[0176] Optionally, in one possible implementation, the resource configuration indicates at least one of the following: frequency domain density, port density, transmission period of the reference signal, or time domain position where the reference signal is not transmitted. It should be noted that in this implementation, the resource configuration indication information can be transmitted through a single cell; for example, the frequency domain density and port density of the resource configuration indication are carried in the same cell. Alternatively, the resource configuration indication information can be transmitted through multiple cells; for example, the frequency domain density and port density of the resource configuration indication are carried in different cells, and these different cells can be included in the same message or different messages. It should be understood that the embodiments of this application do not impose limitations in this regard.

[0177] Alternatively, in another possible implementation, the resource configuration includes one or more of the first, second, third, and fourth resource configurations. For example, the following describes... Figure 9 Please explain the first, second, third, and fourth resource allocations. (Note: This requires further explanation.) Figure 9 This explanation uses two time units as an example. A time unit can be understood as the moment or opportunity to send a reference signal, or it can be understood as the time spent sending the reference signal. It should be understood that... Figure 9 The examples shown are merely illustrative and are not intended to limit the scope of this application. For instance, a time unit can be a single time slot, a single symbol, multiple symbols, multiple time slots, a single subframe, or multiple subframes; these are not limited here.

[0178] Specifically, the first resource configuration indicates the complete set of resources used to transmit reference signals, wherein the complete set includes the complete set of REs transmitting reference signals on multiple first time units and the complete set of air interface resources. For example, as Figure 9 As shown in (a), the first resource configuration indicates all REs and / or all air interface resources that transmit reference signals on two time units.

[0179] The second resource configuration indicates a first subset of the entire set of resources used to transmit reference signals, wherein the first subset includes a subset of the entire set of REs transmitting reference signals in each first time unit and / or a subset of the entire set of air interface resources transmitting reference signals in each first time unit. For example, such as Figure 9 As shown in (b), the second resource configuration indicates that a portion of the REs and / or a portion of the air interface resources that transmit reference signals in two time units transmit reference signals in two time units, while the remaining portion of the REs and / or air interface resources do not transmit reference signals.

[0180] It should be noted that, in this embodiment, the second resource configuration is determined jointly by the first resource configuration and the first information. The first information indicates the complement of the first subset, and the resources corresponding to the complement of the first subset do not send reference signals. For example, the first information indicates... Figure 9 (b) specifies the ports and / or REs that do not transmit reference signals on each first time unit. For example, the first information could be bitmap information indicating the ports and / or REs that do not transmit reference signals. Specifically, a maskTypeList indicator can be added to the resource configuration to indicate the locations (ports and / or REs) where reference signals are not transmitted via a mask, as follows:

[0181] CSI-RS-ResourceMapping{

[0182] frequencyDomainAllocation{},

[0183] nrofPorts{},

[0184] density{},

[0185] maskTypeList{port,RE},…

[0186] }

[0187] The third resource configuration indicates a second subset of the entire set of resources used to transmit reference signals, wherein the second subset includes a portion of the first time units from a plurality of first time units. For example, such as Figure 9As shown in (c), the third resource configuration indicates that a reference signal is sent in one time unit and not sent in another time unit. The third resource configuration can be understood as a time-domain sparse resource configuration, that is, no reference signal is sent in a subset of time units.

[0188] It should be noted that, in this embodiment, the third resource configuration is determined jointly by the first resource configuration and the second information. The second information indicates the complement of the second subset, and the resources corresponding to the complement of the second subset do not transmit reference signals. For example, the second information indicates that reference signals are not transmitted on certain time units, such as... Figure 9 As shown in (c), the second information indicates that a reference signal is not transmitted in one of the two time units. For example, the second information could be bitmap information used to indicate the location in the time domain where the reference signal is not transmitted, such as indicating the time unit in which the reference signal is not transmitted. Specifically, the time domain location where the reference signal is not transmitted can be indicated by a mask, for example, by adding a `predictResourceMask` indicator in the resource configuration, as follows:

[0189] CSI-MeasConfig{

[0190] CSI-ResourceConfig{

[0191] nzp-CSI-RS-ResourceSet{

[0192] nzp-CSI-RS-Resource{

[0193] resourceMapping{CSI-RS-ResourceMapping},

[0194] periodicityAndOffset

[0195] predictResourceMask,…}}}}.

[0196] Here, predictResourceMask represents the mask used when the periodic reference signal is transmitted.

[0197] The fourth resource configuration indicates a third subset of the complete set of resources used to transmit reference signals, wherein the third subset includes a subset of the complete set of REs on all or part of the first time units and / or a subset of the complete set of air interface resources on all or part of the first time units. For example, as Figure 9As shown in (d), the fourth resource configuration indicates that a reference signal is sent on a portion of the REs in one of the two time units, while the other portion of the REs does not send a reference signal, and the fourth resource configuration indicates that all REs in the other time unit do not send a reference signal.

[0198] The fourth resource configuration can be determined jointly by the first resource configuration and the third information. The third information indicates the complement of the third subset, and the resources corresponding to the complement of the third subset do not send reference signals. For example, ... Figure 9 As shown in (d), the third information indicates that all REs in one time unit do not transmit reference signals, and also indicates that some REs in another time unit do not transmit reference signals.

[0199] In the embodiments of this application, the resource configuration can be interchanged with the RS resource configuration or RS resource described above.

[0200] It should also be noted that, in step S810, the terminal device may obtain the first association information in the following possible ways:

[0201] Alternatively, in one possible implementation, the terminal device can obtain the first association information through a method predefined by the protocol or a method pre-configured by the protocol.

[0202] Optionally, in another possible implementation, before step S810, the method may further include: the network device sending first association information to the terminal device, and correspondingly, the terminal device receiving the first association information.

[0203] In this implementation, before the network device sends the first association information to the terminal device, the method may optionally further include: the network device determining one or more AI functions supported by the terminal device; subsequently, the network device configuring corresponding resource configurations for the one or more AI functions, that is, the network device determining association information (i.e., the first association information) between at least one resource configuration and multiple AI functions. The network device determining the one or more AI functions supported by the terminal device may include the following two approaches:

[0204] Method 1: Network devices can learn about one or more AI functions supported by terminal devices through pre-configuration or protocol predefined methods.

[0205] Method 2: The terminal device reports one or more AI functions it supports to the network device.

[0206] It should be noted that one or more AI functions supported by a terminal device can be understood as the terminal device supporting one or more AI-based functions / features, such as AI-based channel estimation, AI-based channel prediction, AI-based channel compression, etc.

[0207] For example, taking AI functions including channel estimation, channel prediction, and channel compression as examples, the association between at least one AI function and at least one resource configuration (i.e., the association indicated by the first association information) is illustrated. For instance, the association between at least one AI function and at least one resource configuration can be shown in Table 1.

[0208] Table 1. Relationship between at least one AI function and at least one resource configuration

[0209] AI Functions Resource allocation Channel estimation Resource Allocation #1 Channel prediction Resource Allocation #2 Channel compression Resource Allocation #3 Channel estimation and channel prediction Resource Allocation #4

[0210] As shown in Table 1, when the AI ​​function is channel estimation, the associated resource configurations are resource configuration #1 and resource configuration #4; when the AI ​​function is channel prediction, the associated resource configurations are resource configuration #2 and resource configuration #4; when the AI ​​function is channel compression, the associated resource configuration is resource configuration #3; and when the AI ​​function is both channel estimation and channel prediction, the associated resource configuration is resource configuration #4.

[0211] Based on the preceding text, resource configuration (resource configuration #1 to resource configuration #4) may include different implementation methods, which will be explained in detail below.

[0212] For example, in one possible implementation, the resource configuration indicates information of at least one of the following: frequency domain density, port density, transmission period of the reference signal, or time domain location where the reference signal is not transmitted.

[0213] For example, resource configuration #1 indicates the following information: frequency domain density and port density. It should be noted that resource configuration #1 can directly indicate frequency domain density and port density, or it can indirectly indicate frequency domain density and port density.

[0214] In one example, resource configuration #1 directly indicates that the frequency domain density value is a first density value (e.g., 0.5) and the port density value is a second density value (e.g., 0.5). In this example, resource configuration #1 includes both the first and second density values.

[0215] In another example, resource configuration #1 can also indicate the frequency domain density value and port density value indirectly. Specifically, the terminal device learns the basic resource configuration, where the basic resource configuration indicates a frequency domain density value of 1 and a port density value of 1. In this case, resource configuration #1 indicates a frequency domain sparsity factor of 1 / 2 and a port sparsity factor of 1 / 2. That is, the frequency domain density and port density indicated by resource configuration #1 are both half of the frequency domain density and port density indicated by the basic resource configuration. Based on this, the terminal device can determine that the frequency domain density value indicated by resource configuration #1 is 0.5 and the port density value is also 0.5.

[0216] For example, resource configuration #2 indicates the base density, the period for transmitting reference signals, and the time-domain location where reference signals are not transmitted.

[0217] For example, resource configuration #3 indicates the base density and the period for sending reference signals.

[0218] For example, resource configuration #4 indicates a low-density CSI-RS, periodic RS, and time-domain location where no reference signal is transmitted.

[0219] It should be understood that resource configurations #2 to #4 may also include direct and indirect instructions, as described in the relevant description of resource configuration #1, which will not be repeated here for simplicity. Furthermore, it should be understood that the above examples are merely illustrative and the embodiments of this application do not impose limitations.

[0220] For example, in another possible implementation, the resource configuration may be one or more of the first, second, third and fourth resource configurations described above.

[0221] For example, resource configuration #1 can also be the second type of resource configuration mentioned above, that is, the resource configuration associated with the channel estimation function is the second type of resource configuration.

[0222] For example, resource configuration #2 can also be the third type of resource configuration mentioned above, that is, the resource configuration associated with the channel prediction function is the third type of resource configuration.

[0223] For example, resource configuration #3 could also be the first type of resource configuration mentioned above, that is, the resource configuration associated with the channel compression function is the first type of resource configuration.

[0224] For example, resource configuration #4 can also be the fourth type of resource configuration mentioned above, that is, the resource configuration associated with the channel estimation function and the channel prediction function is the fourth type of resource configuration.

[0225] It should be understood that Table 1 above is merely an example, and the embodiments of this application do not impose limitations thereon. Optionally, the resource configuration associated with the channel estimation function and the channel compression function can be a second resource configuration, the resource configuration associated with the channel prediction function and the channel compression function can be a third resource configuration, and the resource configuration associated with the channel estimation function, the channel compression function, and the channel prediction function is a fourth resource configuration. It should be understood that the embodiments of this application do not impose limitations thereon.

[0226] See also Figure 8 The method may further include: S820, the terminal device determines the first channel information based on the reference signal of the first resource configuration indication.

[0227] The first resource configuration is one of at least one resource configuration, for example, it can be one of the resource configurations #1 to #4 mentioned above. First, the terminal device determines the first resource configuration. Then, the terminal device determines the first channel information based on the reference signal indicated by the first resource configuration. It should be understood that the terminal device can determine the first resource configuration in several ways, including the following implementation methods:

[0228] Optionally, in one possible implementation, the first resource configuration can be semi-statically configured, meaning the terminal device determines which first resource configuration to use based on the semi-static configuration. For example, if the semi-static configuration information indicates resource configuration #1, the terminal device determines to use resource configuration #1 to receive the reference signal based on the semi-static configuration information. In this example, resource configuration #1 is the first resource configuration. Furthermore, the terminal device can determine that the first AI function associated with resource configuration #1 is a channel estimation function based on the first association information.

[0229] Optionally, in one possible implementation, before step S820, the method may further include: S811, the network device sends first indication information to the terminal device, and correspondingly, the terminal device receives the first indication information.

[0230] The first instruction information instructs a first AI function, which can be understood as instructing the activation of the first AI function. Specifically, after receiving the first instruction information, the terminal device determines the first resource configuration associated with the first AI function based on the first AI function indicated by the first instruction information.

[0231] For example, taking the first AI function as channel estimation as an example, as shown in Table 1, the terminal device activates the channel estimation function according to the first indication information. At this time, the terminal device determines the resource configuration #1 associated with the channel estimation function according to the first indication information, that is, the first resource configuration is resource configuration #1. Further, the terminal device determines the channel information #1 based on the reference signal indicated by resource configuration #1.

[0232] For example, taking the first AI function as channel estimation and channel prediction as an example, as shown in Table 1, the terminal device activates these two AI functions according to the first indication information. At this time, the terminal device determines the resource configuration #4 associated with the channel estimation and channel prediction functions according to the first indication information; that is, the first resource configuration is resource configuration #4. Further, the terminal device determines the channel information #4 based on the reference signal indicated by resource configuration #4.

[0233] For example, taking the first AI function as channel compression as an example, as shown in Table 1, the terminal device activates the channel compression function according to the first indication information. At this time, the terminal device determines the resource configuration #3 associated with the channel compression function according to the first indication information, that is, the first resource configuration is resource configuration #3. Further, the terminal device determines the channel information #3 based on the reference signal indicated by resource configuration #3.

[0234] Optionally, the method may further include: S830, where an entity deploying the first AI function, such as a terminal device, performs an AI operation of the first AI function based on the first channel information. It should be understood that step S830 may be optional for the terminal device. This step may be performed by another entity on the terminal device side, such as a server, which obtains the first channel information from the terminal device.

[0235] For example, in one possible implementation, when the first AI function is a channel estimation function, the terminal device performs the AI ​​operation of the first AI function based on resource configuration 1. This can be understood as the terminal device performing the AI ​​operation corresponding to the channel estimation function on the determined first channel information based on the received reference signal or estimated channel on some REs or ports. For example, model inference operation, to obtain the channel on all REs or all ports. The AI ​​operation corresponding to the channel estimation function includes one or more of the following: model monitoring, model evaluation, model testing, model verification, model training, and model inference.

[0236] For example, in one possible implementation, when the first AI function is a channel prediction function, the terminal device performs the AI ​​operation of the first AI function based on resource configuration 2. This can be understood as the terminal device performing the AI ​​operation corresponding to the channel prediction function on the first channel information obtained by measurement based on the reference signal. The AI ​​operation corresponding to the channel prediction function includes one or more of the following: model monitoring, model evaluation, model testing, model verification, model inference, and model training.

[0237] For example, in one possible implementation, when the first AI function is a channel compression function, the terminal device performs the AI ​​operation of the first AI function based on resource configuration 3. This can be understood as the terminal device performing the AI ​​operation corresponding to the channel compression function on the first channel information obtained by measurement based on the reference signal. The AI ​​operation corresponding to the channel compression function includes model monitoring, model evaluation, model testing, model verification, model training, and model inference.

[0238] For example, in one possible implementation, when the first AI function is a channel estimation function and a channel prediction function, the terminal device executes the operation of the first AI function based on resource configuration. This can be understood as the terminal device performing the AI ​​operations corresponding to the channel estimation function and the channel prediction function on the first channel information obtained based on a reference signal or through measurement. A description of the relevant AI operations corresponding to the channel estimation function and the channel prediction function can be found above and will not be repeated here.

[0239] It should be understood that the above are merely examples, and the embodiments of this application are not intended to limit the scope of the application.

[0240] Figure 10 This is a schematic flowchart illustrating a communication method 1000 provided in an embodiment of this application. It should be noted in advance that... Figure 10 Method 1000 shown corresponds to method 800 described above. For ease of understanding, CSI-RS will be used uniformly in the following text to replace the reference signal described above. Correspondingly, CSI-RS configuration will also be used to replace the resource configuration described above. For simplicity, only aspects not mentioned above will be described in detail below, such as... Figure 10 As shown, the method may include at least the following steps.

[0241] S1010, the terminal device reports one or more supported AI functions to the network device. Specifically, during the interaction between the terminal device and the network device, the terminal device reports one or more supported AI functions to the network device.

[0242] S1020, the network device sends the first association information to the terminal device, and the terminal device receives the first association information accordingly.

[0243] Specifically, after receiving one or more AI functions from the terminal device, the network device configures the corresponding CSI-RS configuration for one or more AI functions; that is, the network device determines the first association information. Subsequently, the network device sends the first association information to the terminal device. For example, the network device sends the association information between the CSI-RS configuration and the AI ​​functions to the terminal device through multiple ResourceSets.

[0244] Optionally, each ResourceSet includes CSI-RS configuration and associated AI functionality, as follows:

[0245] CSI-MeasConfig{

[0246] CSI-ResourceConfig{

[0247] nzp-CSI-RS-ResourceSet-0{

[0248] nzp-CSI-RS-Resource{

[0249] resourceMapping{CSI-RS-ResourceMapping-1},

[0250] periodicityAndOffset-0,

[0251]

[0252] S1030, the network device sends instruction information #1 to the terminal device, and the terminal device receives instruction information #1 accordingly.

[0253] Specifically, instruction information #1 indicates the first AI function. Assuming the first AI function is the channel prediction function, instruction information #1 indicates activation of the channel prediction function. The terminal device determines to activate the channel prediction function based on instruction information #1. Furthermore, the terminal device determines the CSI-RS configuration associated with the channel prediction function, such as the resource configuration #2 mentioned above.

[0254] S1040, the network device sends a CSI-RS associated with the AI ​​function to the terminal device.

[0255] Specifically, after receiving the CSI-RS, the terminal device obtains the first channel information based on the CSI-RS. For example, taking the AI ​​function as a channel prediction function, the network device sends the CSI-RS based on the CSI-RS configuration associated with the channel prediction function (e.g., no reference signal is sent at the prediction time). The terminal device obtains the first channel information based on the channel of the CSI-RS before the prediction time. Optionally, after step S1040, the method may further include: S1050, the entity that has deployed the first AI function, such as the terminal device, performs the operation of the first AI function based on the first channel information. The entity that has deployed the first AI function may also be a server, such as an OTT device, which obtains the first channel information from the terminal device.

[0256] For example, taking the first AI function as channel prediction function as an example, the terminal device obtains the first channel information based on the CSI-RS measurement in the resource configuration #1 receiving step S1040. Subsequently, after the terminal device obtains the first channel information, optionally, the terminal device can perform the AI ​​operation corresponding to the channel prediction function based on the first channel information.

[0257] Optionally, the method may further include: S1060, the terminal device reports a CSI channel report to the network device.

[0258] Specifically, the terminal device performs model inference operations on the first channel information obtained by measuring the received CSI-RS to obtain a CSI channel report, and then reports the CSI channel report to the network device.

[0259] It should be understood that CSI channel reports can be replaced by CSI reports, or first CSI feedback information, or first CSI compressed information, etc. This application does not impose any limitations on this.

[0260] Alternatively, in one possible implementation, such as Figure 11 As shown, Figure 11 This is a schematic flowchart of a communication method 800 provided in another embodiment of this application. Before step S820, the method may further include: S812, whereby the terminal device obtains second association information. Specifically, the second association information indicates the association between at least one resource configuration and at least one AI operation. The AI ​​operation indicates the AI ​​operation involved in the first AI function when the first resource configuration is applied. The AI ​​operation includes at least one of the following: model inference, model training, model monitoring, model verification, model testing, and model evaluation. It should be understood that the above is merely illustrative, and the embodiments of this application are not intended to limit the scope of the application.

[0261] It should be noted that the terminal device can obtain the second association information in the following ways:

[0262] In one possible implementation, the terminal device obtains the second association information through a predefined or pre-configured method.

[0263] In one possible implementation, the terminal device receives second association information from the network device. That is, the method may further include: the network device sending the second association information to the terminal device.

[0264] In this embodiment, after obtaining the first association information and the second association information, the terminal device has essentially obtained association information between at least one resource configuration, multiple AI functions, and at least one AI operation. For example, the association information indicating the at least one resource configuration, multiple AI functions, and at least one AI operation is shown in all or part of Table 2. It is understood that the associations in Table 2 can also be represented by multiple tables, formulas, or one or more strings, which is not limited in this application.

[0265] Table 2 shows the relationships between at least one resource configuration, multiple AI functions, and at least one AI operation.

[0266]

[0267] As shown in Table 2, when the channel estimation function performs AI operations for model inference, resource configuration #1 is associated; when the channel estimation function performs at least one AI operation among model monitoring, model evaluation, model testing, and model training, resource configuration #2 is associated; when the channel prediction function performs AI operations for model inference, resource configuration #3 is associated; when the channel prediction function performs at least one AI operation among model monitoring, model evaluation, model testing, and model training, resource configuration #4 is associated; when the channel compression function performs AI operations for model inference, resource configuration #5 is associated; when the channel compression function performs at least one AI operation among model monitoring, model evaluation, model testing, and model training, resource configuration #6 is associated; when the channel estimation and channel prediction functions perform AI operations for model inference, resource configuration #7 is associated; and when the channel estimation and channel prediction functions perform at least one AI operation among model evaluation, model monitoring, model testing, and model training, resource configuration #8 is associated.

[0268] It should be noted that, optionally, before the network device sends the second association information and the first association information to the terminal device, the method may further include: the network device determining one or more AI functions and at least one AI operation supported by the terminal device; subsequently, the network device configuring corresponding resource configurations for the one or more AI functions and at least one AI operation, that is, the network device determining at least one resource configuration and association information of multiple AI functions (e.g., the association information corresponding to the association relationships shown in Table 2). The network device determining one or more AI functions and AI operations supported by the terminal device may include the following two approaches:

[0269] Method 1: Network devices can learn about one or more AI functions and AI operations supported by terminal devices through pre-configuration or protocol predefined methods.

[0270] Method 2: The terminal device reports one or more AI functions and AI operations it supports to the network device.

[0271] Further, after the terminal device obtains the first association information and the second association information, the method may optionally include: S813, the network device sends second indication information to the terminal device, and correspondingly, the terminal device receives the second indication information. Specifically, the second indication information indicates that a first AI operation is performed on the first AI function, and the first AI operation is one or more of at least one AI operation. After receiving the second indication information, the terminal device determines the first resource configuration associated with the first AI function and the first AI operation based on the second indication information and in conjunction with Table 2.

[0272] For example, when the second indication information indicates that model inference is performed on the channel estimation function, the terminal device determines that the associated resource configuration is resource configuration #1, and at this time, the first resource configuration is resource configuration #1.

[0273] For example, when the second indication information indicates that model monitoring is performed on the channel prediction function, the terminal device determines that the associated resource configuration is resource configuration #4, and at this time, the first resource configuration is resource configuration #4.

[0274] For example, when the second indication information indicates that model training is performed on the channel estimation function and the channel prediction function, the terminal device determines the associated resource configuration as resource configuration #8. At this time, the first resource configuration is resource configuration #8.

[0275] It should be understood that the above are merely examples, and the embodiments of this application are not intended to limit the scope of the application.

[0276] Figure 12 This is a schematic flowchart illustrating a communication method 1200 provided in an embodiment of this application. It should be noted in advance that... Figure 12 Method 1200 shown corresponds to the previous text Figure 11 For ease of understanding, the method described below will uniformly use CSI-RS instead of the reference signal mentioned above. Correspondingly, CSI-RS configuration will also be used instead of the resource configuration mentioned above. For simplicity, only aspects not mentioned above will be described in detail below, such as... Figure 12 As shown, the method may include at least the following steps.

[0277] S1210, the terminal device reports one or more supported AI functions and at least one AI operation to the network device.

[0278] S1220, the network device sends association relationship information #1 to the terminal device, and the terminal device receives the association relationship information #1 accordingly.

[0279] Specifically, after receiving one or more AI functions and at least one AI operation from the terminal device, the network device configures the corresponding CSI-RS configuration for the one or more AI functions and at least one AI operation. That is, the network device determines the association relationship information #1, where the association relationship information #1 can be the association relationship information of at least one AI function, at least one AI operation, and at least one CSI-RS configuration. Subsequently, the network device sends the aforementioned association relationship information #1 to the terminal device. For example, each ResourceSet includes a CSI-RS configuration and the associated AI function and AI operation, as follows:

[0280]

[0281]

[0282] S1230, the network device sends instruction information #2 to the terminal device, and the terminal device receives instruction information #2 accordingly.

[0283] Specifically, instruction #2 indicates the first AI operation of the first AI function. Assuming the first AI function is a channel prediction function and the first AI operation is an inference operation, instruction #2 indicates that the channel prediction function is activated and an inference operation is performed on the channel prediction function. The terminal device determines the CSI-RS configuration associated with the channel prediction function and the inference operation based on the inference operation of the channel prediction function indicated by instruction #2, such as the resource configuration #3 mentioned above.

[0284] S1240, the network device sends a CSI-RS associated with the AI ​​function to the terminal device.

[0285] Specifically, after receiving CSI-RS, the terminal device obtains the first channel information based on CSI-RS. For example, taking the AI ​​function as channel prediction, the network device sends CSI-RS based on the CSI-RS configuration associated with the channel prediction function (for example, no reference signal is sent at the prediction time). The terminal device obtains the first channel information based on the channel of CSI-RS before the prediction time.

[0286] Optionally, after step S1240, the method may further include: S1250, whereby the entity deploying the first AI function, such as a terminal device, performs a first AI operation of the first AI function based on the first channel information. Optionally, the entity deploying the first AI function may be a server, such as an OTT device, which can obtain the first channel information from the terminal device.

[0287] For example, taking the first AI function as channel prediction function as an example, the terminal device obtains the first channel information based on the CSI-RS measurement in the resource configuration #1 receiving step S1040. Subsequently, after the terminal device obtains the first channel information, optionally, the terminal device can perform the model inference operation of the channel prediction function based on the first channel information to infer the future channel information.

[0288] Optionally, the method may further include: the terminal device reporting a CSI channel report to the network device.

[0289] After obtaining the first channel information, the terminal device performs model inference operations on the first channel information to obtain the CSI channel report, and finally reports the CSI channel report to the network device.

[0290] like Figure 13 As shown, Figure 13 A schematic flowchart of a communication method 900 provided in another embodiment of this application, the method comprising:

[0291] S814, the terminal device obtains third association information. The third association information indicates the association between at least one of at least one AI operation, at least one AI function, and at least one resource configuration and at least one CSI reported configuration.

[0292] For example, the third association information indicates the association between at least one AI operation and at least one CSI reporting configuration; or the third association information indicates the association between at least one AI function and at least one CSI reporting configuration; or the third association information indicates the association between at least one AI function, at least one AI operation, and at least one CSI reporting configuration.

[0293] It should be noted that, in one implementation, step S814 may include the preceding text. Figure 8 In the corresponding embodiment, steps S810 and S812 mean that, in this example, the terminal device can simultaneously obtain the first association information, the second association information, and the third association information. In another implementation, steps S810 and S812 do not need to be executed before step S814; that is, the terminal device only needs to obtain the third association information. In other words, this embodiment can be compared with... Figure 8 The illustrated embodiments can be used in combination or independently. Figure 8 The example shown.

[0294] For example, in the embodiments of this application, the CSI reporting configuration includes CSI-RS configuration and CSI report configuration, wherein the CSI-RS configuration indicates the resource density associated with the first channel report (i.e., CSI channel report), and the CSI report configuration indicates the number of CSI bits or quantization bit width associated with the first channel report (i.e., CSI channel report).

[0295] For example, the CSI reporting configuration is used to indicate that the first channel report (i.e., the CSI channel report) is associated with the following resource densities:

[0296] For example, there are a first resource density and a second resource density, where the first resource density is higher than or equal to a first value, and the second resource density is lower than or equal to a second value. It should be noted that the first and second values ​​are preset. Optionally, in one possible implementation, the first value can be equal to the second value; that is, the first resource density and the second resource density can be distinguished using the same value in this case.

[0297] For example, the CSI reporting configuration is used to indicate that the first channel report (i.e., the CSI channel report) is associated with the following CSI bit count and / or quantization bit width. It should be noted that the CSI bit count indicates the number of bits used in the CSI channel report, and the quantization bit width indicates the quantization bit width (indicating the number of bits used for each parameter element) used when representing CSI parameters (such as channel matrix elements, precoding matrix indicator PMI, channel quality indicator CQI, etc.) when generating the CSI channel report.

[0298] For example, the first CSI bit count and / or the first quantization bit width, wherein the first CSI bit count is greater than or equal to the third value, and the first quantization bit width is greater than or equal to the fourth value;

[0299] For example, the second CSI bit count and / or the second quantization bit width, wherein the second CSI bit count is lower than or equal to the fifth value, and the second quantization bit width is lower than or equal to the sixth value. It should be noted that the third to sixth values ​​are preset, with the third value being greater than the fifth value. Optionally, in one possible case, the third value can also be equal to the fifth value; that is, in this case, the first CSI bit count and the second CSI bit count can be distinguished using the same value. Similarly, the fourth value can also be equal to the sixth value.

[0300] It should be noted that, in the embodiments of this application, CSI channel report may also be referred to as CSI report, channel report, feedback information, feedback report, or CSI feedback, etc., and it should be understood that the embodiments of this application do not limit this.

[0301] For example, the relationship between at least one AI function, at least one AI operation, at least one resource configuration, and at least one CSI reporting configuration may include one or more of the relationships shown in Table 3. It is understood that Table 3 may also be represented by multiple tables, strings, or formulas, which is not limited here.

[0302] Table 3 shows the relationships between at least one AI function, at least one AI operation, at least one resource configuration, and at least one CSI reporting configuration.

[0303]

[0304] As shown in Table 3, the first channel report obtained by performing model inference on the CSI-RS based on resource configuration #1 for the channel estimation function is associated with the second resource density and the second CSI bit count or the second quantization bit width; the first channel report used for model monitoring on the CSI-RS based on resource configuration #2 for the channel estimation function is associated with the first resource density and the first CSI bit count and / or the first quantization bit width; the first channel report obtained by performing model inference on the CSI-RS based on resource configuration #3 for the channel prediction function is associated with the second resource density and the second CSI bit count and / or the second quantization bit width; the first channel report used for model monitoring on the CSI-RS based on resource configuration #4 for the channel prediction function is associated with the first resource density and the first CSI bit count or the first quantization bit width; the first channel report obtained by performing model inference on the channel information obtained by the channel compression function based on resource configuration #5 is associated with the first resource density and the second CSI bit count and / or the second quantization bit width; and the first channel report used for model monitoring on the channel information obtained by the channel compression function based on resource configuration #6 is associated with the first resource density and the first CSI bit count or the first quantization bit width.

[0305] Optionally, in one possible implementation, before step S820, the method may further include: S815, the network device sends third indication information to the terminal device, the third indication information indicating a first AI function. It should be understood that the third indication information indicating the first AI function can be considered as indicating that the first AI function is activated. Further, the terminal device determines a first CSI reporting configuration corresponding to the first AI function based on the third indication information, wherein the first CSI reporting configuration is one or more of at least one CSI reporting configuration.

[0306] Referring to Table 3, taking the first AI function as channel compression as an example, the channel compression function includes model inference operations. In this example, the first CSI reporting configuration corresponding to the first AI function can be understood as the CSI reporting configuration corresponding to the channel compression function when performing model inference operations. This CSI reporting configuration indicates that the CSI channel report is associated with the second CSI bit count and / or the second quantization bit width. That is to say, after the terminal device performs model inference on the first channel information based on the channel compression function, it obtains the CSI channel report. Subsequently, the terminal device sends the CSI channel report to the network device with the second CSI bit count or the second quantization bit width indicated by the CSI reporting configuration.

[0307] Taking the first AI function as channel estimation as an example, the operation of the channel estimation function can include model inference and model monitoring. In this example, the first CSI reporting configuration corresponding to the first AI function can be understood as the CSI reporting configuration corresponding to the channel estimation function when performing model inference, and the CSI reporting configuration corresponding to the channel estimation function when performing model monitoring. That is, after the terminal device performs model inference on the CSI-RS with the second resource density indicated by the CSI-RS configuration based on the channel estimation function, it obtains CSI channel report 1. Subsequently, the terminal device sends CSI channel report 1 to the network device with the second CSI bit number or the first quantization bit width indicated by the CSI reporting configuration. Similarly, after the terminal device performs model monitoring on the CSI-RS with the first resource density indicated by the CSI-RS configuration based on the channel estimation function, it obtains CSI channel report 2. Subsequently, the terminal device sends CSI channel report 2 to the network device with the first CSI bit number or the first quantization bit width indicated by the CSI reporting configuration.

[0308] Optionally, in one possible implementation, before step S820, the method may further include: the network device sending fourth indication information to the terminal device, the fourth indication information indicating a first AI operation of the first AI function, and further, the terminal device determining a first CSI reporting configuration associated with the first AI operation of the first AI function based on the fourth indication information.

[0309] Referring to Table 3, for example, taking the first AI function as channel estimation and the first AI operation as model inference, the terminal device can determine the CSI reporting configuration associated with the channel estimation function and the model inference operation based on the fourth indication information. That is, after the terminal device performs model inference on the CSI-RS with the second resource density indicated by the CSI-RS configuration based on the channel estimation function, it obtains CSI channel report 1. Subsequently, the terminal device sends CSI channel report 1 to the network device with the second CSI bit number and / or the second quantization bit width indicated by the CSI reporting configuration.

[0310] For example, taking the first AI function as channel estimation and the first AI operation as model monitoring, the terminal device can determine the CSI reporting configuration associated with the channel estimation function and the model monitoring operation based on the fourth indication information. That is, after the terminal device performs model monitoring on the CSI-RS with the first resource density indicated by the CSI-RS configuration based on the channel estimation function, it obtains CSI channel report 2. Subsequently, the terminal device sends CSI channel report 2 to the network device with the first CSI bit number and / or the first quantization bit width indicated by the CSI reporting configuration.

[0311] For example, taking the first AI function as channel prediction and the first AI operation as model monitoring, the terminal device can determine the CSI reporting configuration associated with the channel prediction function and the model monitoring operation based on the fourth indication information. That is, after the terminal device performs model monitoring on the CSI-RS with the first resource density indicated by the CSI-RS configuration based on the channel prediction function, it obtains CSI channel report 3. Subsequently, the terminal device sends CSI channel report 3 to the network device with the first CSI bit number and / or the first quantization bit width indicated by the CSI reporting configuration.

[0312] Figure 14 This is a schematic flowchart illustrating a communication method 1400 provided in an embodiment of this application. It should be noted in advance that... Figure 14 Method 1400 shown corresponds to the previous text Figure 13 For ease of understanding, the method described below will uniformly use CSI-RS instead of the reference signal mentioned above. Correspondingly, CSI-RS configuration will also be used instead of the resource configuration mentioned above. For simplicity, only aspects not mentioned above will be described in detail below, such as... Figure 14 As shown, the method may include at least the following steps.

[0313] S1410, the terminal device reports one or more supported AI functions and at least one AI operation to the network device.

[0314] S1420, the network device sends association information #2 to the terminal device, and the terminal device receives association information #2 accordingly.

[0315] Specifically, after receiving one or more AI functions and at least one AI operation from the terminal device, the network device configures corresponding CSI-RS configurations and CSI reporting configurations for the one or more AI functions and at least one AI operation. That is, the network device determines the association relationship information #2, where the association relationship information #2 can be the association relationship information of at least one AI function, at least one AI operation, at least one CSI-RS configuration, and CSI reporting configuration. Subsequently, the network device sends the association relationship information #2 to the terminal device.

[0316] S1430, the network device sends instruction information #3 to the terminal device, and the terminal device receives instruction information #3 accordingly.

[0317] Specifically, instruction #3 instructs the first AI operation of the first AI function. Assuming the first AI function is a channel prediction function, the first AI operation is a model inference operation. That is, instruction #3 instructs the activation of the channel prediction function and the execution of a model inference operation on the channel information obtained from the channel prediction function. Based on instruction #3, the terminal device determines to activate the channel prediction function and execute the model inference operation, and determines the associated CSI-RS configuration, such as the resource configuration #2 mentioned above. Furthermore, it can also determine that the CSI reporting configuration is a second CSI bit count or a second quantization bit width.

[0318] S1440, the network device sends a CSI-RS associated with the AI ​​function to the terminal device.

[0319] Specifically, after receiving CSI-RS, the terminal device obtains the first channel information based on CSI-RS. For example, taking the AI ​​function as channel prediction, the network device sends CSI-RS based on the CSI-RS configuration associated with the channel prediction function (for example, no reference signal is sent at the prediction time). The terminal device obtains the first channel information based on the channel of CSI-RS before the prediction time.

[0320] Optionally, after step S1440, the method may further include: S1450, an entity that has deployed the first AI function, such as a terminal device, performs a first AI operation of the first AI function based on the first channel information. Optionally, the entity may also be a server, such as an OTT device, which can obtain the first channel information from the terminal device.

[0321] For example, taking the first AI function as channel prediction function as an example, the terminal device obtains the first channel information based on the CSI-RS measurement in the resource configuration #1 receiving step S1040. Subsequently, after the terminal device obtains the first channel information, optionally, the terminal device can perform the model inference operation of the channel prediction function based on the first channel information to infer the future channel information.

[0322] Furthermore, the method may also include: S1460, the terminal device reporting a CSI channel report to the network device.

[0323] Specifically, the terminal device performs model inference operations on the first channel information obtained by measuring the received CSI-RS to obtain a CSI channel report, and then reports the CSI channel report to the network device.

[0324] According to the technical solution provided in this application, while supporting multiple AI functions, it is also possible to reasonably manage the constraint relationship between the RS resources corresponding to these multiple AI functions (such as frequency domain / time domain multiplexing) to improve the efficiency and flexibility of AI-assisted channel acquisition.

[0325] Finally, the device embodiments of this application will be described.

[0326] To implement the functions of the methods provided in this application, both the terminal side and the network side may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0327] Figure 15 This is a schematic block diagram of a communication device according to an embodiment of this application. The communication device includes a processing circuit 1510 and a transceiver circuit 1520, which can be interconnected or coupled, for example, interconnected via a bus 1530. The communication device can be a terminal-side device or a network-side device.

[0328] Optionally, the communication device may also include a memory 1540. The memory 1540 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for related instructions and data.

[0329] The processing circuit 1510 may be all or part of the processing or control circuitry of one or more processors, or it may be one or more processors. The processor may be a central processing unit (CPU). If the processing circuit 1510 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.

[0330] The processing circuit 1510 may be a signal processor, a chip, or other integrated circuit that can implement the method of this application, or a portion of the aforementioned processor, chip, or integrated circuit used for processing functions.

[0331] The transceiver circuit 1520 can also be a transceiver, or an input / output interface. An input / output interface is used for the input or output of signals or data and can also be called an input / output circuit.

[0332] When the communication device is a terminal, the transceiver circuit 1520 is used to perform the following operations: obtain a first association relationship, the first association relationship indicating that at least one resource configuration is associated with at least one AI function, each resource configuration is associated with at least one AI function, and an AI function is associated with at least one resource configuration.

[0333] The processing circuit 1510 is used to determine first channel information based on a reference signal indicating a first resource configuration, wherein the first resource configuration is one of at least one resource configuration; the first channel information is used to perform an AI operation of a first AI function, wherein the first AI function is one or more of at least one AI function associated with the first resource configuration, and the AI ​​operation indicates the AI ​​operation involved in the first AI function when the first resource configuration is applied to the first AI function.

[0334] Optionally, in some examples, the transceiver circuit 1520 is used to receive first indication information, which indicates a first AI function.

[0335] The processing circuit 1510 is used to determine the first resource configuration based on the first AI function.

[0336] Optionally, in some examples, the transceiver circuit 1520 is used to receive second indication information, which indicates a first AI operation of the first AI function, wherein the first AI operation is one or more of at least one AI operation.

[0337] The processing circuit 1510 is used to determine the first resource configuration based on the first AI operation of the first AI function.

[0338] Optionally, in some examples, the transceiver circuit 1520 is used to obtain a third association, which indicates the association between at least one of at least one AI operation, at least one AI function, and at least one resource configuration and at least one CSI reporting configuration.

[0339] Optionally, in some examples, the processing circuit 1510 is used to determine a first CSI reporting configuration corresponding to a first AI function, the first CSI reporting configuration being one or more of at least one CSI reporting configuration; and to send a first channel report based on the first CSI reporting configuration, the first channel report being obtained by performing an AI operation on the first AI function, or a first information report being used by the first AI function to perform an AI operation.

[0340] Optionally, in some examples, the transceiver circuit 1520 is used to receive third indication information, which indicates the first AI function.

[0341] The processing circuit 1510 is used to determine the first CSI reporting configuration based on the first AI function.

[0342] When the communication device is a second device, the processing circuit 1510 is configured to perform the following operations: determine a first association relationship, the first association relationship indicating that at least one resource configuration is associated with at least one AI function, each resource configuration is associated with at least one AI function, and an AI function is associated with at least one resource configuration.

[0343] The transceiver circuit 1520 is used to perform the following operation: send the first association.

[0344] Optionally, in some examples, the transceiver circuit 1520 is used to send a first indication message that indicates a first AI function.

[0345] Optionally, in some examples, the transceiver circuit 1520 is used to send a second association, which indicates an association between at least one resource configuration and at least one AI operation.

[0346] Optionally, in some examples, the transceiver circuit 1520 is used to send a second indication information, the second indication information indicating a first AI operation of a first AI function, the first AI operation being one or more of at least one AI operation, the first AI operation of the first AI function being associated with a first resource configuration.

[0347] Optionally, in some examples, the transceiver circuit 1520 is used to send a third association, which indicates the association between at least one of at least one AI operation, at least one AI function, and at least one resource configuration and at least one CSI reporting configuration.

[0348] Optionally, in some examples, the transceiver circuit 1520 is used to receive a first channel report, which is obtained from performing AI operations of the first AI function, or a first information report is used for performing AI operations of the first AI function.

[0349] Optionally, in some examples, the transceiver circuit 1520 is used to send a third indication message that indicates the first AI function.

[0350] The above description is for illustrative purposes only. When the communication device is on the terminal side or the network side, it will be responsible for executing the methods or steps related to the terminal side or the network side in the foregoing method embodiments.

[0351] When the communication device is a terminal side or a network side, the transceiver circuit 1520 can be a transceiver or an interface circuit.

[0352] When the communication device is a chip used on the terminal side or network side, the transceiver circuit 1520 can be an input / output circuit.

[0353] For details, please refer to the content shown in the above method embodiments.

[0354] Figure 15 The implementation of each operation can also be found by referring to... Figures 6 to 14 The corresponding description of the method embodiments shown.

[0355] Figure 16 This is another schematic block diagram of a communication device according to an embodiment of this application. The communication device can be on the terminal side or the network side, used to implement the methods involved in the above embodiments.

[0356] The communication device includes a transceiver unit 1610 and a processing unit 1620. The transceiver unit 1610 may include a sending unit and a receiving unit. The sending unit is used to perform the sending action of the communication device, and the receiving unit is used to perform the receiving action of the communication device. For ease of description, the sending unit and the receiving unit are combined into one transceiver unit in this embodiment. This will be explained uniformly here and will not be repeated later.

[0357] When the communication device is a terminal, for example, the transceiver unit 1610 is used to obtain a first association relationship, etc.; the processing unit 1620 is used to perform the processing, control, and other steps involved on the terminal side. For example, the processing unit 1620 is used to determine first channel information based on a reference signal of a first resource configuration indication, etc.

[0358] When the communication device is on the network side, exemplarily, the processing unit 1620 is used to perform network-side steps involving processing, control, etc. For example, the processing unit 1620 is used to determine a first association relationship, etc.; the transceiver unit 1610 is used to send the first association relationship, etc.

[0359] When the communication device is a terminal side or a network side, it will be responsible for executing one or more of the methods or steps related to the terminal side or network side in the aforementioned method embodiments.

[0360] Optionally, the communication device further includes a storage unit 1630 for storing programs or code for performing the aforementioned methods.

[0361] Figure 16 The transceiver unit in the middle can correspond to Figure 15 The transceiver circuit in the middle, Figure 16 The processing unit in can correspond to Figure 15 The processing circuitry within.

[0362] Figure 15 and Figure 16 The illustrated device embodiment is used to implement Figures 8 to 14The content described. Figure 15 and Figure 16 The specific execution steps and methods of the device shown can be found in the content described in the foregoing method embodiments.

[0363] This application also provides a chip, including a processor, for calling and executing instructions stored in a memory, causing a communication device on which the chip is installed to perform the methods described in the examples above. The memory may be integrated within the chip or located externally.

[0364] This application also provides another chip, including: an input interface, an output interface, and a processing circuit. The input interface, the output interface, and the processor are connected via an internal connection path. The processing circuit is used to execute code in a memory. When the code is executed, the processing circuit is used to execute the methods in the examples described above. Optionally, the chip also includes a memory for storing computer programs or code. The input interface and the output interface can be independent of each other, or they can be integrated into a single input / output interface.

[0365] The processing circuitry can be all or part of the processing circuitry in one or more processors, or one or more processors.

[0366] This application also provides a processor for coupling with a memory for performing methods and functions related to the terminal side or network side in any of the above embodiments.

[0367] In another embodiment of this application, a computer program product containing instructions is provided, which, when run on a computer, enables the implementation of the methods described in the foregoing embodiments.

[0368] This application also provides a computer program that, when run on a computer, enables the implementation of the methods described in the foregoing embodiments.

[0369] In another embodiment of this application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a computer, implements the methods described in the foregoing embodiments.

[0370] It should be understood that the processor mentioned in the embodiments of this application can be one of the following devices or a portion of the circuitry used for processing functions: a central processing unit (CPU), a processor for AI, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0371] For example, the processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0372] For example, one possible implementation of a processor for AI could be... Figure 17 The AI ​​processor 1700 shown can be understood to have many other possible implementations, which are not limited in this application. Figure 17 This is a schematic diagram of the structure of a possible AI processor 1700 provided in an embodiment of this application.

[0373] like Figure 17As shown, the AI ​​processor 1700 may include one or more of the following: an AI core, a digital vision pre-processing (DVPP) module, a task scheduler (TS), an L3 cache, an AI CPU, a control CPU, an L2 cache, a universal serial bus (USB) interface, a network interface card (NIC), a peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), a double data rate (DDR) / high bandwidth memory (HBM) interface, a general purpose input / output (GPIO) / inter-integrated circuit (I2C) bus, etc. It is understood that the specific meanings of these terms are well known to those skilled in the art and will not be elaborated upon here.

[0374] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced synchronous SDRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0375] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0376] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 this application.

[0377] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0378] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the above functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0379] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: Obtain first association information, which indicates that at least one resource configuration is associated with at least one artificial intelligence (AI) function, wherein each resource configuration is associated with at least one AI function, and an AI function is associated with the at least one resource configuration; First channel information is determined based on a reference signal indicating a first resource configuration, wherein the first resource configuration is one of the at least one resource configuration; The first channel information is used to perform AI operations for a first AI function, the first AI function being one or more of at least one AI function associated with the first resource configuration, and the AI ​​operation being the AI ​​operation involved in the first AI function when the first resource configuration is applied to the first AI function.

2. The method according to claim 1, characterized in that, The method further includes: Receive a first instruction message, which instructs the first AI function; The first resource configuration is determined based on the first AI function.

3. The method according to claim 1, characterized in that, The method further includes: Obtain second association information, which indicates the association information between the at least one resource configuration and at least one AI operation.

4. The method according to claim 3, characterized in that, The method further includes: Receive a second instruction message, the second instruction message indicating a first AI operation of the first AI function, the first AI operation being one or more of the at least one AI operation; The first resource configuration is determined based on the first AI operation of the first AI function; The first channel information is used to perform AI operations for the first AI function, including: The first channel information is used to perform the first AI operation of the first AI function.

5. The method according to claim 3 or 4, characterized in that, Each of the at least one AI operation includes at least one of the following: Model inference, model training, model monitoring, model validation, model testing, and model evaluation.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Obtain third association information, which indicates the association between at least one of the at least one AI operation, the at least one AI function, and the at least one resource configuration and at least one channel state information (CSI) reporting configuration, wherein the at least one AI operation includes the AI ​​operation of the first AI function.

7. The method according to claim 6, characterized in that, The method further includes: Determine a first CSI reporting configuration corresponding to the first AI function, wherein the first CSI reporting configuration is one or more of the at least one CSI reporting configuration; A first channel report is sent based on the first CSI reporting configuration. The first channel report is obtained by performing an AI operation of the first AI function, or the first channel report is used to perform an AI operation of the first AI function.

8. The method according to claim 7, characterized in that, The method further includes: The configuration for the first CSI reporting is determined based on the first AI function.

9. The method according to claim 7, characterized in that, The method further includes: The first CSI reporting configuration is determined based on the first AI operation of the first AI function.

10. The method according to any one of claims 1 to 9, characterized in that, The first AI function includes at least one of the following: Channel estimation function, channel prediction function, and channel compression function.

11. The method according to any one of claims 1 to 10, characterized in that, Each resource configuration indicates at least one of the following: The frequency domain density, port density, transmission period, or time domain location where the reference signal is not transmitted.

12. The method according to any one of claims 1 to 10, characterized in that, The resource allocation includes one or more of the following: the first resource allocation, the second resource allocation, the third resource allocation, and the fourth resource allocation. The first resource configuration indicates the complete set of resources used to transmit reference signals, the complete set including the complete set of resource elements REs transmitted on the reference signals by a plurality of first time units and the complete set of air interface resources; The second resource configuration indicates a first subset of the entire set of resources for transmitting reference signals, the first subset including a subset of the entire set of REs transmitting the reference signals on each first time unit and / or a subset of the entire set of air interface resources transmitting the reference signals on each first time unit; The third resource configuration indicates a second subset of the entire set of resources used to transmit reference signals, the second subset including a portion of the first time units among a plurality of first time units; The fourth resource configuration indicates a third subset of the complete set of resources used to transmit reference signals, the third subset including a subset of the complete set of REs on all or part of the first time units in a portion of the first time units and / or a subset of the complete set of air interface resources on all or part of the first time units in a portion of the first time units.

13. The method according to claim 12, characterized in that, If the first AI function includes channel estimation, then the first resource configuration is the second resource configuration; or... If the first AI function includes channel prediction, then the first resource configuration is the third resource configuration; or... If the first AI function includes channel compression, then the first resource configuration is the first type of resource configuration; or... When the first AI function includes the channel estimation function and the channel prediction function, the first resource configuration is the fourth resource configuration.

14. The method according to claim 12 or 13, characterized in that, The second resource configuration is determined by the first resource configuration and the first information, whereby the first information indicates the complement of the first subset, and the resources corresponding to the complement of the first subset are not used to send the reference signal. The third resource configuration is determined by the first resource configuration and the second information. The second information indicates the complement of the second subset, and the resources corresponding to the complement of the second subset are not used to send the reference signal. The fourth resource configuration is determined by the first resource configuration and the third information. The third information indicates the complement of the third subset, and the resources corresponding to the complement of the third subset are not used to send the reference signal.

15. The method according to any one of claims 12 to 14, characterized in that, The first resource configuration is one of the first resource configuration, the second resource configuration, the third resource configuration, and the fourth resource configuration.

16. The method according to claim 7, characterized in that, The CSI reporting configuration includes CSI-RS configuration and CSI reporting configuration. The CSI-RS configuration indicates that the first channel report is associated with one of the following resource densities: A first resource density, wherein the first resource density is greater than or equal to a first value; or... A second resource density, wherein the second resource density is lower than or equal to a second value, and the first value is greater than the second value; The CSI report configuration indicates that the first channel report is associated with one of the following: CSI bit count and / or quantization bit width: First CSI bit count and / or first quantization bit width, the first CSI bit count is greater than or equal to a third value, and the first quantization bit width is greater than or equal to a fourth value; The second CSI bit count and / or the second quantization bit width, wherein the second CSI bit count is less than or equal to the fifth value, and the second quantization bit width is less than or equal to the sixth value; The third value is greater than the fifth value, and the fourth value is greater than the sixth value.

17. The method according to claim 16, characterized in that, When the first AI function includes at least one of the channel estimation function, the channel prediction function, and the channel compression function. The first channel report obtained by performing model inference on the first AI function is associated with the second resource density; or, The first channel report used for model monitoring, model training, model verification, model testing, or model evaluation of the first AI function is associated with the first resource density; or, When the first AI function is a channel estimation function, the first channel report is associated with the second resource density; or... When the first AI function is a channel prediction function, the first channel report is associated with the second resource density; or... When the first AI function is a channel compression function, the first channel report is associated with the first resource density.

18. A communication method, characterized in that, include: First association information is determined, which indicates that at least one resource configuration is associated with at least one AI function, wherein each resource configuration is associated with at least one AI function, and an AI function is associated with the at least one resource configuration; Send the first association information; Wherein, the at least one resource configuration includes a first resource configuration, the first resource configuration being used to determine first channel information based on an indicated reference signal, the first channel information being used to perform AI operations for a first AI function. The first AI function is one or more of at least one AI function associated with the first resource configuration, and the AI ​​operation is the AI ​​operation involved in the first AI function when the first resource configuration is applied to the first AI function.

19. A communication device, characterized in that, It includes modules or units for implementing the method of any one of claims 1 to 17, or modules or units for implementing the method of claim 18.

20. The communication device according to claim 34, characterized in that, Where the communication device includes a module or unit for implementing the method described in any one of 1 to 17, the communication device is a terminal device, or... The communication device is a chip used in terminal equipment, or... The communication device is a server on the terminal device side, or; When the communication device includes a module or unit for implementing the method described in 18, the communication device is a network device, or... The communication device is a chip used in network equipment, or... The communication device is a server on the network equipment side.

Images