Communication method, communication device, communication system, and storage medium

Abstract

The present disclosure relates to a communication method, a communication device, a communication system, and a storage medium. The communication method comprises: a terminal and / or a network device determines at least one of first information, second information, third information, and fourth information, wherein the first information is used for indicating information about a channel state information processing unit (CPU) required for an artificial intelligence (AI) function to predict and / or report channel state information (CSI); the second information is used for indicating information about a CPU required for reporting monitoring information of the AI function; the third information is used for indicating information about a CPU required for generating a dataset, the dataset being used for training the AI function; and the fourth information is used for indicating the number of activated channel measurement resources. In this way, the terminal and the network device can have a consistent understanding of at least one of the various pieces of information described above, thereby enabling the terminal and the network device to determine a CSI processing behavior, allowing the network device to configure appropriate CSI reporting parameters for the terminal, and ensuring the accuracy and effect of AI-function-based CSI prediction.

Description

Communication methods, communication equipment, communication systems and storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, communication system and storage medium. Background Technology

[0002] With the development and application of Artificial Intelligence (AI) technology, AI has been widely applied to the physical layer of wireless communication. Channel state information (CSI) predictions for future moments can be derived through AI model reasoning; this method can be called an "AI prediction algorithm." Summary of the Invention

[0003] This disclosure provides a communication method, communication device, communication system, and storage medium.

[0004] A first aspect of this disclosure provides a communication method executed by a communication device, comprising: determining at least one of first information, second information, third information, and fourth information, wherein the first information is used to instruct an artificial intelligence (AI) function to predict channel state information (CSI) and / or information of a channel state information processing unit (CPU) required for CSI reporting; the second information is used to instruct information of a monitoring information reporting unit (CPU) required for the AI ​​function; the third information is used to instruct information of a CPU required for generating a dataset, the dataset being used to train the AI ​​function; and the fourth information is used to instruct the number of activated channel measurement resources.

[0005] A second aspect of this disclosure provides a communication device, comprising: a processing module configured to determine at least one of first information, second information, third information, and fourth information, wherein the first information is configured to instruct an artificial intelligence (AI) function to predict channel state information (CSI) and / or information of a channel state information processing unit (CPU) required for CSI reporting; the second information is configured to instruct information of a monitoring information reporting unit (CPU) required for the AI ​​function; the third information is configured to instruct information of a CPU required for generating a dataset, the dataset being used to train the AI ​​function; and the fourth information is configured to instruct the number of activated channel measurement resources.

[0006] A third aspect of this disclosure provides a communication device comprising: one or more processors; wherein the processors are configured to perform the method as described in the first aspect above.

[0007] A fourth aspect of this disclosure provides a communication system including a terminal and / or a network device for performing the method as described in the first aspect above.

[0008] A fifth aspect of this disclosure provides a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method described in the first aspect above.

[0009] A sixth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the method as described in the first aspect above.

[0010] In the solution proposed in this disclosure, in the above embodiments, the terminal and / or network device can determine at least one of the following: first information, second information, third information, and fourth information. The first information is used to instruct the AI ​​function to predict Channel State Information (CSI) and / or the information of the Channel State Information Processing Unit (CPU) required for CSI reporting. The second information is used to instruct the information of the CPU required for monitoring information reporting by the AI ​​function. The third information is used to instruct the information of the CPU required to generate a dataset, which is used to train the AI ​​function. The fourth information is used to instruct the number of activated channel measurement resources. Therefore, the terminal and network device can have a consistent understanding of at least one of the above-mentioned information, thereby enabling the terminal and network device to determine the CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on the AI ​​function. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments or background art of this disclosure, the accompanying drawings that can be used in the embodiments or background art of this disclosure will be described below.

[0012] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure;

[0013] Figure 1B is a schematic diagram of an observation window and a prediction window in an embodiment of this disclosure;

[0014] Figure 1C is a schematic diagram of another observation window and prediction window in an embodiment of this disclosure;

[0015] Figure 1D is a schematic diagram of another observation window and prediction window in an embodiment of this disclosure;

[0016] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure;

[0017] Figure 2B is an interactive schematic diagram of a communication method according to another embodiment of the present disclosure;

[0018] Figure 2C is an interactive schematic diagram of a communication method according to another embodiment of the present disclosure;

[0019] Figure 2D is an interactive schematic diagram of a communication method according to yet another embodiment of the present disclosure;

[0020] Figure 2E is an interactive schematic diagram of a communication method according to yet another embodiment of the present disclosure;

[0021] Figure 2F is an interactive schematic diagram of a communication method according to yet another embodiment of the present disclosure;

[0022] Figure 3 is an interactive schematic diagram of a communication method according to another embodiment of the present disclosure;

[0023] Figure 4 is a schematic diagram of a possible CSI prediction in an embodiment of this disclosure;

[0024] Figure 5 is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure;

[0025] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure;

[0026] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0027] This disclosure provides communication methods, communication devices, communication systems, and storage media.

[0028] In a first aspect, embodiments of this disclosure propose a communication method executed by a communication device, comprising: determining at least one of first information, second information, third information, and fourth information, wherein the first information is used to instruct an artificial intelligence (AI) function to predict channel state information (CSI) and / or information of a channel state information processing unit (CPU) required for CSI reporting; the second information is used to instruct information of a monitoring information reporting unit (CPU) required for the AI ​​function; the third information is used to instruct information of a CPU required for generating a dataset, the dataset being used to train the AI ​​function; and the fourth information is used to instruct the number of activated channel measurement resources.

[0029] In the above embodiments, the terminal and / or network device can determine at least one of the first, second, third, and fourth information. The first information is used to instruct the AI ​​function to predict Channel State Information (CSI) and / or the information of the Channel State Information Processing Unit (CPU) required for CSI reporting. The second information is used to instruct the information of the CPU required for monitoring information reporting by the AI ​​function. The third information is used to instruct the information of the CPU required to generate a dataset, which is used to train the AI ​​function. The fourth information is used to instruct the number of activated channel measurement resources. Therefore, the terminal and network device can have a consistent understanding of at least one of the above information, enabling them to determine CSI processing behavior and allowing the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on the AI ​​function.

[0030] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first information includes: determining a first value and / or determining a second value, wherein the first value is related to a first input data dimension of the AI ​​function, and the second value is related to a first output data dimension of the AI ​​function; determining the first information based on the first value and / or the second value, and information of the first CPU, wherein the first CPU is the CPU required for predicting CSI based on the AI ​​function unit, and the first information is used to indicate the information of the CPU required for predicting CSI by the AI ​​function.

[0031] In the above embodiments, the terminal and / or network device determine a first value, and / or a second value, and determine information about the first CPU, and determine first information based on the first value and / or the second value, and the information about the first CPU. Thus, the terminal and network device can have a consistent understanding of the CPU information required for CSI prediction using AI functions, thereby enabling the terminal and network device to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on AI functions.

[0032] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first value includes: determining a first parameter; determining a first input data dimension based on the first parameter; and determining the first value based on the first input data dimension and a second input data dimension, wherein the second input data dimension is the input data dimension of the AI ​​functional unit.

[0033] In the above embodiments, a first value is determined based on the second input data dimension of the AI ​​functional unit as a reference and the first input data dimension of the AI ​​function. The determined first value can be used to determine the CPU information required for the AI ​​function to predict CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0034] In conjunction with some embodiments of the first aspect, in some embodiments, determining the second value includes: determining a first parameter; determining a first output data dimension based on the first parameter; and determining the second value based on the first output data dimension and a second output data dimension, wherein the second output data dimension is the output data dimension of the AI ​​functional unit.

[0035] In the above embodiments, a second value is determined based on the second output data dimension of the AI ​​functional unit as a reference and the first output data dimension of the AI ​​function. The determined second value can be used to determine the CPU information required for the AI ​​function to predict CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0036] In conjunction with some embodiments of the first aspect, in some embodiments, the first parameter includes at least one of the following: the number of antenna ports; the number of frequency domain elements; the number of prediction times, wherein the prediction times are used to predict CSI; and the number of measurement times, wherein the measurement times are used to measure CSI.

[0037] In the above embodiments, since the determined first parameter can be used to determine the first input data dimension and / or the first output data dimension of the AI ​​function, and the first parameter can be at least one of the aforementioned possible parameters, the first input data dimension and / or the first output data dimension of the AI ​​function can be accurately determined by flexibly configuring and / or defining the type of the first parameter.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein determining the first parameter includes at least one of the following: determining a first parameter configured by the network device; predefining the first parameter based on a protocol; and sending the first parameter to the network device.

[0039] In the above embodiments, the terminal can flexibly and effectively determine the first parameter, ensuring the accuracy of the determination of the first parameter, and is also applicable to various communication systems.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein determining the first parameter includes at least one of the following: configuring the first parameter for a terminal; predefining the first parameter based on a protocol; receiving the first parameter sent by the terminal.

[0041] In the above embodiments, the network device can flexibly and effectively determine the first parameter, ensuring the accuracy of the determination of the first parameter, and is also applicable to various communication systems.

[0042] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first value includes: determining a first complexity and / or number of parameters of the AI ​​function based on a first input data dimension; and determining the first value based on the first complexity and / or number of parameters.

[0043] In the above embodiments, a first value is determined based on a first complexity and / or number of parameters under a first input data dimension. The determined first value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, determining the second value includes: determining the second complexity and / or number of parameters of the AI ​​function based on the first output data dimension; and determining the second value based on the second complexity and / or number of parameters.

[0045] In the above embodiments, a second value is determined based on a second complexity and / or number of parameters under a first output data dimension. The determined second value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein the method further includes: sending a first value and / or a second value to a network device.

[0047] In the above embodiments, the first value and / or the second value can be reported to the network device in a timely manner, so that the terminal and the network device can have a consistent understanding of the first value and / or the second value, thereby supporting the improvement of the accuracy of determining the CPU information required for AI function to predict CSI.

[0048] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein the method further includes: receiving a first value and / or a second value sent by a terminal.

[0049] In the above embodiments, the first value and / or the second value reported by the terminal can be obtained in a timely manner, so that the terminal and the network device can have a consistent understanding of the first value and / or the second value, thereby supporting the improvement of the accuracy of determining the CPU information required for AI function to predict CSI.

[0050] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first information includes: determining a third value; determining the first information based on the third value and information from the second CPU, wherein the second CPU is the CPU required for non-AI predicted CSI and / or CSI reporting.

[0051] In the above embodiments, the terminal and / or network device determine a third value and, based on the third value and the information of the second CPU, determine first information, wherein the second CPU is the CPU required for CSI prediction and / or CSI reporting based on non-AI functionality. Therefore, the terminal and network device can have a consistent understanding of the CPU information required for AI-based CSI prediction and / or CSI reporting, thereby enabling the terminal and network device to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on AI functionality.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein determining the third value includes at least one of the following: predefining the third value based on a protocol; or sending the third value to a network device.

[0053] In the above embodiments, the terminal can use various possible methods to determine the third value. The determined third value can be used to determine the CPU information required for AI function prediction CSI and / or CSI reporting, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference (which may include AI function prediction CSI and / or CSI reporting).

[0054] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein determining the third value includes at least one of the following: a third value predefined based on a protocol; or a third value sent by a receiving terminal.

[0055] In the above embodiments, the network device can use various possible methods to determine the third value, which can be used to determine the information of the CPU required for AI function prediction CSI and / or CSI reporting, thereby supporting the rapid and accurate determination of the information of the CPU required for AI function inference.

[0056] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first information includes: determining at least one of a fourth value, a fifth value, and a sixth value; determining the first information based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values, wherein the first information is used to indicate information about the CPU required for AI function prediction of CSI.

[0057] In the above embodiments, the terminal and / or network device determine at least one of a fourth, fifth, and sixth value, and determine first information based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values. Thus, the terminal and network device can have a consistent understanding of the CPU information required for AI-based CSI prediction, enabling them to determine CSI processing behavior and allowing the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0058] In conjunction with some embodiments of the first aspect, in some embodiments, determining first information based on the type of channel measurement resource and at least one of a fourth value, a fifth value, and a sixth value includes: if the type of channel measurement resource is periodic resource and / or semi-persistent resource, determining the first information based on the fourth value and a first duration, wherein the first duration is the duration of the interval between adjacent channel state information reference signals (CSI-RS); if the type of channel measurement resource is periodic resource and / or semi-persistent resource, determining the first information based on the fifth value and the number of prediction times, wherein the prediction times are used to predict CSI; if the type of channel measurement resource is aperiodic resource, determining the first information based on the sixth value and a first number, wherein the first number is the number of aperiodic CSI-RS.

[0059] In the above embodiments, the first information can be determined by at least one of the various possible methods, which can effectively improve the accuracy of the first information. The terminal and / or network device can flexibly select an appropriate method to determine the first information based on the type of channel measurement resources, so that under any possible type of channel measurement resources, the terminal and network device can have a consistent understanding of the CPU information required for AI function prediction CSI.

[0060] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following: predefining at least one of the fourth, fifth, and sixth values ​​based on a protocol; and sending at least one of the fourth, fifth, and sixth values ​​to a network device.

[0061] In the above embodiments, the terminal can use various possible methods to determine at least one of the fourth, fifth, and sixth values. The determined at least one value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0062] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following: predefining at least one of the fourth, fifth, and sixth values ​​based on a protocol; receiving at least one of the fourth, fifth, and sixth values ​​sent by a terminal.

[0063] In the above embodiments, the network device can use various possible methods to determine at least one of the fourth, fifth, and sixth values. The determined at least one value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0064] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein the method further includes: sending first information to a network device.

[0065] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein determining the first information includes: receiving the first information sent by the terminal.

[0066] In the above embodiments, the terminal can send first information to the network device, and the network device can receive the first information sent by the terminal. That is to say, if the terminal determines the first information, the terminal can also report the first information to the network device, and the network device can receive the first information reported by the terminal. Thus, both the terminal and the network device can obtain the first information in a timely manner, improving the efficiency and effectiveness of determining the first information.

[0067] In conjunction with some embodiments of the first aspect, in some embodiments, the type of monitoring information includes at least one of the following: monitoring results of AI functions; performance index values ​​of AI functions; predicted CSI; actual CSI.

[0068] In the above embodiments, for all possible types of monitoring information, it is supported to effectively calculate the CPU information required for AI function monitoring information calculation, which is applicable to various possible communication scenarios.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, determining the second information includes: determining the fifth information, wherein the fifth information is used to indicate the CPU information required for monitoring information calculation of the AI ​​function; determining the second information based on the first information and the fifth information, or determining the fifth information as the second information.

[0070] In the above embodiments, the terminal and / or network device determine the fifth information, and based on the first and fifth information, determine the second information, or determine the fifth information as the second information. The fifth information is used to indicate the CPU information required for the AI ​​function's monitoring information calculation. Therefore, the terminal and network device can have a consistent understanding of the CPU information required for the AI ​​function's monitoring information calculation, thereby enabling the terminal and network device to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on the AI ​​function.

[0071] In conjunction with some embodiments of the first aspect, in some embodiments, determining the fifth information includes: determining the fifth information based on the type of monitoring information and the type of channel measurement resources.

[0072] In the above embodiments, the "CPU information required for AI function monitoring information calculation" that conforms to the type of monitoring information and the type of channel measurement resources can be effectively determined, thereby greatly improving the accuracy of the CPU information required for AI function monitoring information calculation and ensuring system performance.

[0073] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a terminal; wherein the method further includes: determining channel measurement resources configured for the network device; and generating a dataset based on the channel measurement resources.

[0074] In the above embodiments, the terminal can use the channel measurement resources configured by the network device to generate a dataset, thereby ensuring the effectiveness of the dataset generation, improving the training effect of the AI ​​function, and ensuring the inference performance of the AI ​​function.

[0075] In conjunction with some embodiments of the first aspect, in some embodiments, the communication device includes a network device; wherein the method further includes: configuring channel measurement resources for the terminal.

[0076] In the above embodiments, the network device can configure channel measurement resources for the terminal to generate datasets, thereby supporting the improvement of the dataset generation effect on the terminal side.

[0077] In conjunction with some embodiments of the first aspect, in some embodiments, determining the third information includes: determining the third information based on a predefined seventh value.

[0078] In the above embodiments, the network device configures channel measurement resources for the terminal, the terminal generates a dataset based on the channel measurement resources, and the terminal and / or network device determine third information based on a predefined seventh value. Thus, the terminal and network device can have a consistent understanding of the CPU information required to generate the dataset, enabling them to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0079] In conjunction with some embodiments of the first aspect, in some embodiments, determining the fourth information includes: determining an eighth value or a ninth value, wherein the eighth value is used to indicate the number of channel measurement resources activated corresponding to a single CSI report associated with a channel measurement resource, and the ninth value is used to indicate the number of channel measurement resources activated corresponding to multiple different reporting amounts included in a single CSI report associated with a channel measurement resource; and determining the fourth information based on the eighth value or the ninth value.

[0080] In the above embodiments, the terminal and / or network device can determine an eighth or ninth value, and determine the fourth information based on the eighth or ninth value. Thus, the terminal and network device can have a consistent understanding of the number of activated channel measurement resources, thereby enabling them to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0081] Secondly, embodiments of this disclosure provide a communication device, comprising: a processing module, configured to determine at least one of first information, second information, third information, and fourth information, wherein the first information is used to instruct an artificial intelligence (AI) function to predict channel state information (CSI) and / or information of a channel state information processing unit (CPU) required for CSI reporting; the second information is used to instruct information of a monitoring information reporting unit (CPU) required for the AI ​​function; the third information is used to instruct information of a CPU required for generating a dataset, the dataset being used to train the AI ​​function; and the fourth information is used to instruct the number of activated channel measurement resources.

[0082] Thirdly, embodiments of this disclosure provide a communication device, which includes one or more processors; wherein the processors are configured to execute the first aspect and optional implementations thereof.

[0083] Fourthly, embodiments of this disclosure provide a communication system comprising: a terminal and / or a network device; wherein the terminal and / or network device is configured to perform the methods described in the first aspect and optional implementations thereof.

[0084] Fifthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method described in the first aspect and its optional implementations.

[0085] In a sixth aspect, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method as described in the first aspect and its optional implementations.

[0086] In a seventh aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in the first aspect and optional implementations of the first aspect.

[0087] Eighthly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to the first aspect and optional implementations thereof.

[0088] It is understood that the aforementioned communication devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0089] This disclosure provides a communication method, a communication device, a communication system, and a storage medium. In some embodiments, the terms "communication method" and "information processing method," "communication control method," etc., can be used interchangeably; the terms "communication method apparatus" and "information processing apparatus," "communication control apparatus," etc., can be used interchangeably; and the terms "transmission system" and "information processing system," "communication system," etc., can be used interchangeably.

[0090] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0091] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0092] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0093] In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the aforementioned," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.

[0094] In the embodiments disclosed herein, "multiple" refers to two or more.

[0095] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0096] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0097] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0098] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0099] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0100] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0101] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0102] In some embodiments, the apparatus and device may be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they may also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "body", etc.

[0103] In some embodiments, "network" can be interpreted as devices included in the network, such as access network devices, core network devices, etc.

[0104] In some embodiments, "access network device (AN device)" may also be referred to as "radio access network device (RAN device)," "base station (BS)," "radio base station," or "fixed station." In some embodiments, it may also be understood as "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," or "bandwidth part (BWP)."

[0105] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "Narrow Band-Internet of Things (NB-IoT) device," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0106] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0107] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0108] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0109] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0110] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0111] As shown in Figure 1A, the communication system 100 includes a terminal 101 and a network device 102.

[0112] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0113] In some embodiments, network device 102 may include at least one of access network device and core network device.

[0114] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0115] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0116] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0117] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of the aforementioned one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Protocol Core (EPC), a 5G Core Network (5GCN), or a Next Generation Core (NGC).

[0118] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0119] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0120] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), 6th generation mobile communication system (6G), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New Radio Access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0121] Optionally, for medium- and high-speed mobile terminals, due to the rapid changes in channel information in the time domain, in order to improve system performance, the codebook added in Type II of some versions of the communication protocol (such as Rel-18) can be used to feed back Channel State Information (CSI). The Type II codebook is based on downlink channel information estimated by the terminal side based on historical time points. It uses an autoregressive or linear minimum mean square error (LMMSE) algorithm to predict downlink channel information at future time points, and then calculates the corresponding precoding information at future time points based on the predicted downlink channel information.

[0122] Optionally, with the development and application of Artificial Intelligence (AI) technology, AI has been widely applied to the physical layer of wireless communication. CSI prediction for future moments can be predicted using AI models; this method can be called an "AI prediction algorithm." The performance of AI prediction algorithms can outperform that of non-AI algorithms. Both AI and non-AI prediction algorithms require the use of CSI data from multiple historical moments. Downlink channel information is estimated based on Channel State Information Reference Signals (CSI-RS) transmitted at multiple historical moments. The range encompassing "multiple historical moments" can be called the observation window. The range encompassing "multiple prediction moments" can be called the prediction window, where the prediction moments are used to predict future CSI. Figures 1B, 1C, and 1D illustrate this. Figure 1B is a schematic diagram of one observation window and prediction window in this embodiment; Figure 1C is a schematic diagram of another observation window and prediction window in this embodiment; and Figure 1D is a schematic diagram of yet another observation window and prediction window in this embodiment. Under different parameter configurations, future CSI within the prediction window can be predicted based on the CSI of historical moments within the observation window. The definitions of each parameter are as follows:

[0123] N represents the number of times CSI-RS is transmitted within the observation window, where N can be any one of 4, 5, 8, or 10;

[0124] M represents the interval between adjacent CSI-RS, where M can be equal to D, and M can be any one of 2 slots, 2.5 slots, 4 slots, or 5 slots;

[0125] K indicates that the prediction window has K time points to predict CSI, where K can be any one of 1, 3, or 4;

[0126] D represents the CSI interval predicted by the prediction window for adjacent time points, where D can be any one of 1 slot, 2.5 slots, 4 slots, 5 slots, or 8 slots;

[0127] The length w of the prediction window d =K·D.

[0128] Optionally, if the network (NW) is configured with an aperiodic channel state information reference signal (AP CSI-RS), the value of N can be any one of 4 slots, 8 slots, or 12 slots, and M is 2 slots.

[0129] Alternatively, N can also be referred to as the number of measurement times, and K can also be referred to as the number of prediction times.

[0130] Optionally, during the use of the AI ​​model, due to channel variations at the terminal, the AI ​​model's inference results may not achieve the expected results. Therefore, the performance of the AI ​​model can be monitored. Methods for monitoring AI model performance can include: Type 1, Type 2, and Type 3. In Type 1, the terminal can report monitoring results. In Type 2, the terminal can report the measured future time-instance CSI, i.e., the ground truth CSI within the prediction window. In Type 3, the terminal can report monitoring performance metrics.

[0131] Optionally, in CSI prediction research based on AI and / or Machine Learning (ML), Generalized Cosine Similarity (GCS) and / or SGCS, and Normalized Mean Square Error (NMSE) can be used as intermediate evaluation metrics. GCS can be used to calculate the similarity between the predicted feature vector w' and the original input w. SGCS represents the squared GCS. The formula for calculating GCS can be shown below:

[0132] Among them, w k Let w′ represent the eigenvector of the ideal CSI within the k-th resource unit. k Let w' represent the feature vector of the predicted output CSI within the k-th resource unit. NMSE can be used to calculate the error between the predicted feature vector w' and the original input w.

[0133] Optionally, for Type 1 (terminal reporting of monitoring results), performance metrics and threshold values ​​can be defined. The terminal determines the model performance results and the reporting configuration of the monitoring results based on the performance metrics and threshold values. For Type 2 (terminal reporting of measured future-time CSI, i.e., prediction window ground truth CSI), CSI reporting for future times can be defined or configured. For Type 3 (terminal reporting of monitoring performance metrics), performance metrics reported by the terminal can be defined.

[0134] Optionally, the aforementioned CSI prediction model inference, monitoring computational performance, or generating datasets for training the CSI prediction model can be collectively referred to as CSI processing. A set of criteria can be defined for CSI processing to ensure a consistent understanding between the terminal and network (NW) sides, facilitating reasonable parameter configurations from the network side. These criteria may include: the CPU usage for CSI processing, the duration of CPU usage for CSI processing, and the number of channel measurement resources activated during CSI processing, such as CSI-RS resources.

[0135] Optionally, since AI-based CSI prediction algorithms (or AI prediction algorithms) and traditional CSI prediction algorithms (or non-AI-based CSI prediction algorithms, non-AI prediction algorithms, etc.) have different complexities and may require different hardware or software, different Channel State Information Processing Units (CPUs) can be defined. For example, the CPU required for AI-based CSI prediction algorithms can be defined as an Artificial Intelligence Channel State Information Processing Unit (ACPU), while the CPU required for traditional CSI prediction algorithms can be calculated using traditional methods.

[0136] Optionally, if ACPU is introduced, when there are multiple CSI prediction models (or AI models for CSI prediction) or a CSI prediction model that supports different input data dimensions and / or output data dimensions, it is necessary to determine the number of ACPUs occupied by the multiple CSI prediction models or the CSI prediction models that support different data dimensions (or any other possible information about the ACPUs occupied, such as duration).

[0137] Optionally, the results of CSI prediction can still be reported using traditional CSI measurement methods. Traditional CSI measurement reporting still uses a traditional CPU pool to determine the number of CPUs occupied (or any other possible information about the occupied CPUs, such as duration). If another CPU pool (ACPU) is introduced, the total number of CPUs occupied by CSI can be counted to facilitate parameter configuration on the network side.

[0138] Optionally, the terminal may need to report monitoring information (which may include at least one of monitoring results, model performance metric values, ground truth CSI, and predicted CSI) and the dataset required to generate the training CSI prediction model. Therefore, it is necessary to define CSI processing guidelines for monitoring CSI or generating training datasets.

[0139] Optionally, in the embodiments of this disclosure, a method for defining the CPU usage of dataset generation for CSI inference, function monitoring, or training AI functions (or CSI prediction functions) based on AI functions is proposed, and a method for defining the number of activated channel measurement resources is also proposed. The aforementioned definitions can be used as CSI processing criteria when predicting CSI based on AI functions.

[0140] Optionally, in some embodiments, the AI ​​function may include one or more AI models. The AI ​​function can be used to predict CSI. That is, the AI ​​function can be a single AI model used to predict CSI, or the AI ​​function can be multiple AI models, each of which can be used to predict CSI independently, or multiple AI models can be used jointly to predict CSI; there is no limitation on this.

[0141] Optionally, in some embodiments, an AI function can be used to predict CSI, and this AI function may also be referred to as a CSI prediction function. An AI model can be used to predict CSI, and this AI model may also be referred to as a CSI prediction model.

[0142] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0143] In step S2101, the terminal and / or network device determines a first value and / or determines a second value.

[0144] Optionally, in some embodiments, the terminal can be a UE, and the network device can be a base station.

[0145] Optionally, in some embodiments, the first value is related to a first input data dimension of the AI ​​function, and the second value is related to a first output data dimension of the AI ​​function. The AI ​​function is used to predict CSI, and the AI ​​function can be, for example, a CSI prediction function. The input data dimension of the AI ​​function can be referred to as the first input data dimension. The output data dimension of the AI ​​function can be referred to as the first output data dimension. The first value can be a single value, which can be based on the first input data dimension (the first input data dimension can be represented as: N). i The first value, as determined by ), can be represented as w. i The second value can be a single value, which can be based on the first output data dimension (the first output data dimension can be represented as: N). o The second value, as determined by ), can be expressed as w. o .

[0146] Optionally, in some embodiments, a first value may be used to determine the first information, or a second value may be used to determine the first information, or the first and second values ​​may be used in combination to determine the first information. Optionally, in this embodiment, the first information may be used to indicate the CPU required (or occupied) by the AI ​​function to predict CSI. For example, the first information may be used to indicate the number of CPUs occupied by the AI ​​function to predict CSI, or the first information may be used to indicate the duration of CPU usage by the AI ​​function to predict CSI, etc.

[0147] Optionally, in some embodiments, the terminal may determine a first value, or the terminal may determine a second value, or the terminal may determine both a first value and a second value, and the determined first value and / or second value may be used to determine the aforementioned first information.

[0148] Optionally, in some embodiments, the network device may determine a first value, or the network device may determine a second value, or the network device may determine both a first value and a second value, and the determined first value and / or second value may be used to determine the first information mentioned above.

[0149] Optionally, in some embodiments, the terminal or the network device can determine the first value. The terminal and the network device can use the same method to determine the first value. Optionally, in determining the first value, a first parameter can be determined, and based on the first parameter, a first input data dimension can be determined. Furthermore, the first value can be determined based on the first input data dimension and a second input data dimension, wherein the second input data dimension is the input data dimension of the AI ​​functional unit. Thus, the first value is determined based on the second input data dimension of the AI ​​functional unit as a reference and the first input data dimension of the AI ​​function. The determined first value can be used to determine the CPU information required for AI function CSI prediction, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0150] Optionally, in some embodiments, the terminal or the network device can determine the second value. The terminal and the network device can use the same method to determine the second value. Optionally, in determining the second value, a first parameter can be determined, and based on the first parameter, a first output data dimension can be determined, and based on the first output data dimension and a second output data dimension, the second value can be determined, wherein the second output data dimension is the output data dimension of the AI ​​functional unit. Thus, the second value is determined based on the second output data dimension of the AI ​​functional unit as a reference and the first output data dimension of the AI ​​function. The determined second value can be used to determine the CPU information required for the AI ​​function to predict CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0151] Optionally, in some embodiments, the terminal and / or network device can combine the above two methods to determine the first value and the second value, and use the first value and the second value to determine the CPU information required for AI function to predict CSI, thereby improving the flexibility of determining the CPU information required for AI function to predict CSI, and is applicable to various communication systems.

[0152] Optionally, in some embodiments, the AI ​​functional unit is an AI function that serves as a basic unit. The AI ​​functional unit may also be referred to as an AI sub-function, AI model unit, AI sub-model, etc. Optionally, the input data dimension of the AI ​​functional unit may be referred to as the second input data dimension. The second input data dimension may be represented as N. u,i Optionally, the output data dimension of the AI ​​functional unit can be referred to as the second output data dimension. The second output data dimension can be represented as N. u,o .

[0153] Optionally, in some embodiments, the first input data dimension N can be... iSecond input data dimension N u,i Perform calculations to determine the first value w. i It is possible to output data of dimension N. o Second output data dimension N u,o Perform calculations to determine the second value w. o .

[0154] Optionally, in some embodiments, the first parameter includes at least one of the following: the number of antenna ports; the number of frequency domain elements; the number of prediction times, wherein the prediction times are used to predict CSI; and the number of measurement times, wherein the measurement times are used to measure CSI. Since the determined first parameter can be used to determine the first input data dimension and / or the first output data dimension of the AI ​​function, and the first parameter can be at least one of the aforementioned possible parameters, thus, by flexibly configuring and / or defining the type of the first parameter, it is possible to accurately determine the first input data dimension and / or the first output data dimension of the AI ​​function.

[0155] Optionally, in some embodiments, when determining the first parameter, the terminal may use at least one of the following methods to determine the first parameter: determining the first parameter configured by the network device, predefining the first parameter based on a protocol, or sending the first parameter to the network device. This allows the terminal to flexibly and effectively determine the first parameter, ensuring the accuracy of the determination, and is also applicable to various communication systems.

[0156] In other words, the first parameter can be configured by the network device for the terminal, in which case the terminal can determine the first parameter configured by the network device. Alternatively, the first parameter can be predefined by the protocol, in which case the terminal can determine the first parameter based on the protocol predefined parameter. Or, the terminal can determine the first parameter independently and report the first parameter to the network device.

[0157] Optionally, in some embodiments, the network device may determine the first parameter using at least one of the following methods: configuring the first parameter for the terminal, predefining the first parameter based on a protocol, or receiving the first parameter sent by the terminal. This allows the network device to determine the first parameter flexibly and effectively, ensuring the accuracy of the determination, while also being applicable to various communication systems.

[0158] In other words, the first parameter can be reported by the terminal to the network device, in which case the network device can receive the first parameter reported by the terminal. Alternatively, the first parameter can be predefined by the protocol, in which case the network device can predefine the first parameter based on the protocol. Or, the network device can independently determine the first parameter and configure it for the terminal.

[0159] Optionally, in some embodiments, during the process of determining the first value, the terminal or network device can determine the first complexity and / or number of parameters of the AI ​​function based on the first input data dimension, and determine the first value based on the first complexity and / or number of parameters. Thus, the first value is determined based on the first complexity and / or number of parameters under the first input data dimension. The determined first value can be used to determine the CPU information required for the AI ​​function to predict CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0160] In other words, AI functions can support multiple input data dimensions. The complexity of different input data dimensions can be the same or different, or the number of parameters can be the same or different. The complexity and number of parameters of different input data dimensions can be the same or different. Then, the terminal or network device can determine the first value based on the first complexity and / or number of parameters of the first input data dimension of the AI ​​model. For example, it can determine the first value based on the first complexity and / or number of parameters of the first input data dimension of the AI ​​model using any possible operation method.

[0161] Optionally, in some embodiments, during the process of determining the second value, the terminal or network device can determine the second complexity and / or number of parameters of the AI ​​function based on the first output data dimension, and determine the second value based on the second complexity and / or number of parameters. Thus, the second value is determined based on the second complexity and / or number of parameters under the first output data dimension. The determined second value can be used to determine the CPU information required for AI function CSI prediction, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0162] In other words, AI functions can support multiple output data dimensions. The complexity of different output data dimensions can be the same or different, or the number of parameters can be the same or different. The complexity and number of parameters of different output data dimensions can be the same or different. Then, the terminal or network device can determine the second value based on the second complexity and / or number of parameters of the first output data dimension of the AI ​​model. For example, it can determine the second value based on the second complexity and / or number of parameters of the first output data dimension of the AI ​​model based on any possible operation method.

[0163] Optionally, in some embodiments, if the terminal determines the first value and / or the second value, the terminal can also send the first value and / or the second value to the network device, and the network device can receive the first value and / or the second value sent by the terminal. That is, if the terminal determines the first value and / or the second value, the terminal can report the first value and / or the second value to the network device. This allows for timely reporting of the first value and / or the second value to the network device, enabling the terminal and the network device to have a consistent understanding of the first value and / or the second value, thereby supporting improved accuracy in determining the CPU information required for AI function prediction of CSI.

[0164] Optionally, in some embodiments, if the network device determines the first value and / or the second value, the network device may also indicate (or configure) the first value and / or the second value to the terminal, and the terminal may receive the first value and / or the second value indicated (or configured) by the network device.

[0165] In step S2102, the terminal and / or network device determines the information of the first CPU.

[0166] The first CPU is the CPU required for predicting CSI based on the AI ​​functional unit.

[0167] Optionally, in some embodiments, the AI ​​functional unit is an AI function that serves as a basic unit. The AI ​​functional unit may also be referred to as an AI sub-function, an AI model unit, an AI sub-model, etc.

[0168] Optionally, in some embodiments, a first CPU can be defined for the AI ​​functional unit. The first CPU is the CPU required for CSI prediction based on the AI ​​functional unit. The information of the first CPU may be, for example, the number of CPUs required for CSI prediction based on the AI ​​functional unit, and / or the duration of CPU usage required for CSI prediction based on the AI ​​functional unit, etc., and there are no limitations on this.

[0169] Optionally, in some embodiments, the first CPU may also be referred to as the first ACPU, indicating that the first CPU is used for AI functions. Information about the first CPU can be represented as follows:

[0170] Optionally, in some embodiments, the information of the first CPU can be predefined. For example, the information of the first CPU can be defined based on the input data dimensions and / or output data dimensions of the AI ​​model (or AI function), or the complexity / number of parameters of the AI ​​model (or AI function).

[0171] Optionally, the terminal may determine the information of a predefined first CPU; or the network device may determine the information of the first CPU; or the terminal and the network device may determine the information of the first CPU.

[0172] Optionally, the information and first value of the first CPU determined above can be used to determine the first information; or the information and second value of the first CPU can be used to determine the first information; or the information, first value and second value of the first CPU can be used to determine the first information.

[0173] In step S2103, the terminal and / or network device determine the first information based on the first value and / or the second value, and the information of the first CPU.

[0174] Optionally, in some embodiments, the terminal may determine the first information based on the first value and the information of the first CPU; or the terminal may determine the first information based on the second value and the information of the first CPU; or the terminal may determine the first information based on the first value, the second value, and the information of the first CPU.

[0175] Optionally, in some embodiments, the network device may determine the first information based on the first value and the information of the first CPU; or the network device may determine the first information based on the second value and the information of the first CPU; or the network device may determine the first information based on the first value, the second value, and the information of the first CPU.

[0176] Optionally, in some embodiments, the terminal and network device can determine the first information based on the first value and the information of the first CPU; or the terminal and network device can determine the first information based on the second value and the information of the first CPU; or the terminal and network device can determine the first information based on the first value, the second value and the information of the first CPU.

[0177] Optionally, in some embodiments, in the process of determining the first information based on the first value and the information of the first CPU, the first value and the information of the first CPU may be processed by calculation, and the result of the calculation may be determined as the first information; or the second value and the information of the first CPU may be processed by calculation, and the result of the calculation may be determined as the first information; or the first value, the second value and the information of the first CPU may be processed by calculation, and the result of the calculation may be determined as the first information, without limitation.

[0178] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2103. For example, steps S2101, S2102, and S2103 may be implemented as independent embodiments, steps S2101+S2102 may be implemented as independent embodiments, steps S2101+S2103 may be implemented as independent embodiments, steps S2102+S2103 may be implemented as independent embodiments, steps S2101+S2102+S2103 may be implemented as independent embodiments, etc., but not limited thereto.

[0179] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0180] In the embodiments disclosed herein, each step and its optional implementation can also be carried out independently.

[0181] In this embodiment, the terminal and / or network device determine a first value and / or a second value, and determine information about the first CPU, and determine first information based on the first value and / or the second value and the information about the first CPU. Thus, the terminal and network device can have a consistent understanding of the CPU information required for CSI prediction using the AI ​​function, thereby enabling the terminal and network device to determine the CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on the AI ​​function.

[0182] It should be noted that the descriptions of corresponding or identical terms and method steps in the following embodiments can be found in the above embodiments, and will not be repeated here.

[0183] Figure 2B is an interactive schematic diagram of a communication method according to another embodiment of the present disclosure. As shown in Figure 2B, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0184] Step S2201: The terminal and / or network device determines the third value.

[0185] Optionally, in some embodiments, the third value can be a single value used to determine the first information, which is used to instruct the AI ​​function to predict CSI and / or the CPU information required for CSI reporting. If the first information is used to instruct the AI ​​function to predict the CPU information required for CSI, then the third value can be represented as w1. And if the first information is used to instruct the CSI to report the CPU information required, then the third value can be represented as w2.

[0186] Optionally, in this embodiment, the first information can be used to indicate the CPU information required for the AI ​​function to predict the CSI, or the first information can be used to indicate the CPU information required for the CSI (which may refer to the CSI predicted by the AI ​​function), or the first information can be used to indicate the AI ​​function to predict the CSI and the CPU information required for the CSI to report.

[0187] Alternatively, in some embodiments, the terminal may determine a third value.

[0188] Alternatively, in some embodiments, the network device may determine a third value.

[0189] Alternatively, in some embodiments, the terminal and network device may determine a third value.

[0190] Optionally, in some embodiments, the terminal may use at least one of the following methods to determine the third value: pre-defining the third value based on a protocol, or sending the third value to a network device. Thus, the terminal can use various possible methods to determine the third value, which can be used to determine the CPU information required for AI function prediction CSI and / or CSI reporting, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference (which may include AI function prediction CSI and / or CSI reporting).

[0191] In other words, if the third value can be predefined, the terminal can predefine the third value based on the protocol. Alternatively, the terminal can determine the third value independently and report the third value to the network device.

[0192] Optionally, in some embodiments, the network device may use at least one of the following methods to determine the third value: based on a protocol-predefined third value, or by receiving a third value sent by a terminal. Thus, the network device can use various possible methods to determine the third value, which can be used to determine the CPU information required for AI function prediction CSI and / or CSI reporting, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0193] In other words, if a third value can be predefined, then the network device can predefine the third value based on the protocol. Alternatively, the terminal can independently determine the third value and report it to the network device, in which case the network device can receive the third value reported by the terminal.

[0194] In step S2202, the terminal and / or network device determine the first information based on the third value and the information from the second CPU.

[0195] The second CPU is the CPU required for CSI prediction and / or CSI reporting based on non-AI.

[0196] Optionally, in some embodiments, the terminal and / or network device may determine information about the second CPU. The second CPU is the CPU required for CSI prediction based on non-AI and / or CSI reporting. For example, the second CPU is the CPU required based on a conventional CSI prediction algorithm, or the second CPU is the CPU required for reporting CSI calculated based on a conventional CSI prediction algorithm. The information about the second CPU may include, for example, the number of CPUs occupied by CSIs calculated based on a conventional CSI prediction algorithm, and / or the duration of CPUs occupied by CSIs calculated based on a conventional CSI prediction algorithm, and / or the number of CPUs occupied by CSI reporting calculated based on a conventional CSI prediction algorithm, and / or the duration of CPUs occupied by CSI reporting calculated based on a conventional CSI prediction algorithm, etc.

[0197] Optionally, in some embodiments, the information of the second CPU may be predefined based on a protocol. The terminal and / or network device may predefine the information of the second CPU based on a protocol, or the terminal and network device may use any other possible methods to determine the information of the second CPU.

[0198] Optionally, in some embodiments, after determining the third value, the terminal can determine the first information based on the third value and the information of the second CPU.

[0199] Optionally, in some embodiments, after determining the third value, the network device can determine the first information based on the third value and the information of the second CPU.

[0200] Optionally, in some embodiments, after determining the third value, the terminal and network device can determine the first information based on the third value and the information of the second CPU.

[0201] Optionally, in some embodiments, in the process of determining the first information based on the third value and the information of the second CPU, the third value and the information of the second CPU may be processed by calculation, and the result of the calculation may be determined as the first information.

[0202] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2202. For example, steps S2201 and S2202 may be implemented as independent embodiments, steps S2201+S2202 may be implemented as independent embodiments, etc., but are not limited thereto.

[0203] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0204] In this embodiment, the terminal and / or network device determine a third value and, based on the third value and the information of the second CPU, determine first information, wherein the second CPU is the CPU required for CSI prediction and / or CSI reporting based on non-AI functionality. Thus, the terminal and network device can have a consistent understanding of the CPU information required for AI-based CSI prediction and / or CSI reporting, enabling them to determine CSI processing behavior and allowing the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0205] Figure 2C is an interactive schematic diagram of a communication method according to another embodiment of the present disclosure. As shown in Figure 2C, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0206] Step S2301: The terminal and / or network device determines at least one of the fourth, fifth, and sixth values.

[0207] Optionally, in some embodiments, the fourth value can be a single value, which can be used to determine the first information. Optionally, in this embodiment, the first information can be used to indicate the CPU information required for the AI ​​function to predict CSI. The fourth value can be represented as X1.

[0208] Optionally, in some embodiments, the fifth value can be a single value, which can be used to determine the first information, which indicates the CPU information required for the AI ​​function to predict CSI. The fifth value can be represented as X2.

[0209] Optionally, in some embodiments, the sixth value can be a single value, which can be used to determine the first information, which indicates the CPU information required for the AI ​​function to predict CSI. The sixth value can be represented as X3.

[0210] Optionally, in some embodiments, the terminal may determine at least one of a fourth value, a fifth value, and a sixth value.

[0211] Optionally, in some embodiments, the network device may determine at least one of a fourth value, a fifth value, and a sixth value.

[0212] Optionally, in some embodiments, the terminal and network device may determine at least one of a fourth value, a fifth value, and a sixth value.

[0213] Optionally, in some embodiments, the terminal may use at least one of the following methods to determine at least one of the fourth, fifth, and sixth values: predefining at least one of the fourth, fifth, and sixth values ​​based on a protocol; or sending at least one of the fourth, fifth, and sixth values ​​to a network device. Thus, the terminal can use various possible methods to determine at least one of the fourth, fifth, and sixth values, and the determined at least one value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0214] In other words, if at least one of the fourth, fifth, and sixth values ​​can be predefined, then the terminal can predefine at least one of the fourth, fifth, and sixth values ​​based on the protocol. Alternatively, the terminal can independently determine at least one of the fourth, fifth, and sixth values, and can also report at least one of the fourth, fifth, and sixth values ​​to the network device.

[0215] Optionally, in some embodiments, the network device may use at least one of the following methods to determine at least one of the fourth, fifth, and sixth values: predefining at least one of the fourth, fifth, and sixth values ​​based on a protocol; or receiving at least one of the fourth, fifth, and sixth values ​​sent by a terminal. Thus, the network device can use various possible methods to determine at least one of the fourth, fifth, and sixth values, and the determined at least one value can be used to determine the CPU information required for AI function prediction CSI, thereby supporting the rapid and accurate determination of the CPU information required for AI function inference.

[0216] In other words, if at least one of the fourth, fifth, and sixth values ​​can be predefined, then the network device can predefine at least one of the fourth, fifth, and sixth values ​​based on the protocol. Alternatively, the network device can receive at least one of the fourth, fifth, and sixth values ​​reported by the terminal.

[0217] Optionally, in some embodiments, determining at least one of the fourth, fifth, and sixth values ​​may include the following various cases: determining the fourth value; determining the fifth value; determining the sixth value; determining the fourth and fifth values; determining the fourth and sixth values; determining the fourth and sixth values; determining the fourth, fifth, and sixth values, without limitation.

[0218] In step S2302, the terminal and / or network device determine the first information based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values.

[0219] Optionally, in some embodiments, the type of channel measurement resource may be, for example, periodic resource, semi-persistent resource, or aperiodic resource.

[0220] Optionally, in some embodiments, the terminal may determine the first information by combining the type of channel measurement resources and at least one of the fourth, fifth, and sixth values.

[0221] Optionally, in some embodiments, the network device may determine the first information by combining the type of channel measurement resources and at least one of the fourth, fifth, and sixth values.

[0222] Optionally, in some embodiments, the terminal and network device may determine the first information by combining the type of channel measurement resources and at least one of the fourth, fifth, and sixth values.

[0223] Optionally, in some embodiments, in the process of determining the first information based on the type of channel measurement resource and at least one of the fourth, fifth, and sixth values, the first information may be determined based on the fourth value and a first duration when the type of channel measurement resource is a periodic resource and / or a semi-persistent resource. The first duration is the duration of the interval between adjacent Channel State Information Reference Signals (CSI-RS). That is, if the type of channel measurement resource is a periodic resource, the first information can be determined based on the fourth value and the duration of the interval between adjacent CSI-RS; or if the type of channel measurement resource is a semi-persistent resource, the first information can also be determined based on the fourth value and the duration of the interval between adjacent CSI-RS.

[0224] Optionally, in some embodiments, the first duration is, for example, the observation window (or viewing window) parameter M.

[0225] Optionally, in some embodiments, in the process of determining the first information based on the fourth value and the duration of the interval between adjacent CSI-RS, the duration of the interval between the fourth value and adjacent CSI-RS may be calculated and the result of the calculation may be determined as the first information.

[0226] Optionally, in some embodiments, in the process of determining the first information based on the type of channel measurement resource and at least one of the fourth, fifth, and sixth values, the first information may be determined based on the fifth value and the number of prediction times when the type of channel measurement resource is a periodic resource and / or a semi-persistent resource, wherein the prediction times are used to predict CSI. That is, if the type of channel measurement resource is a periodic resource, the first information can be determined based on the fifth value and the number of prediction times; or if the type of channel measurement resource is a semi-persistent resource, the first information can also be determined based on the fifth value and the number of prediction times.

[0227] Optionally, in some embodiments, the number of prediction times is, for example, the prediction window parameter K.

[0228] Optionally, in some embodiments, in the process of determining the first information based on the fifth value and the number of predicted times, the fifth value and the number of predicted times may be processed, and the result of the processing may be determined as the first information.

[0229] Optionally, in some embodiments, in the process of determining the first information based on the type of channel measurement resource and at least one of the fourth, fifth, and sixth values, the first information may be determined based on the sixth value and a first number when the type of channel measurement resource is an aperiodic resource, wherein the first number is the number of aperiodic CSI-RS. That is, if the type of channel measurement resource is an aperiodic resource, the first information can be determined based on the sixth value and the number of aperiodic CSI-RS.

[0230] Optionally, in some embodiments, the first number is the number of aperiodic CSI-RS. The first number can be represented as K. s .

[0231] Optionally, in some embodiments, in the process of determining the first information based on the sixth value and the number of aperiodic CSI-RS, the sixth value and the number of aperiodic CSI-RS may be calculated, and the result of the calculation may be determined as the first information.

[0232] Therefore, the first information can be determined through at least one of the above possible methods, which can effectively improve the accuracy of the first information. The terminal and / or network device can flexibly select the appropriate method to determine the first information based on the type of channel measurement resources, so that under any possible type of channel measurement resources, the terminal and network device can have a consistent understanding of the CPU information required for AI function prediction CSI.

[0233] The communication method involved in the embodiments of this disclosure may include at least one of steps S2301 to S2302. For example, steps S2301 and S2302 may be implemented as independent embodiments, steps S2301+S2302 may be implemented as independent embodiments, etc., but are not limited thereto.

[0234] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0235] In this embodiment, the terminal and / or network device determine at least one of a fourth, fifth, and sixth value, and determine first information based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values. Thus, the terminal and network device can have a consistent understanding of the CPU information required for AI-based CSI prediction, enabling them to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0236] Optionally, in some embodiments of this disclosure, after determining the first information, the terminal can send the first information to the network device, and the network device can receive the first information sent by the terminal. That is, if the terminal determines the first information, it can also report the first information to the network device, and the network device can receive the first information reported by the terminal. Therefore, both the terminal and the network device can obtain the first information in a timely manner, improving the efficiency and effectiveness of determining the first information.

[0237] Figure 2D is an interactive schematic diagram illustrating a communication method according to another embodiment of the present disclosure. As shown in Figure 2D, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0238] Step S2401: The terminal and / or network device determines the fifth information.

[0239] The fifth piece of information is used to indicate the CPU information required for the AI ​​function's monitoring information calculation. Optionally, in some embodiments, the CPU information required for the AI ​​function's monitoring information calculation may be, for example, the number of CPUs required for the AI ​​function's monitoring information calculation, or the duration of CPU usage required for the AI ​​function's monitoring information calculation, etc.

[0240] Optionally, in some embodiments, the terminal may determine the fifth piece of information.

[0241] Alternatively, in some embodiments, the network device may determine the fifth piece of information.

[0242] Optionally, in some embodiments, the terminal and network device may determine the fifth information.

[0243] Optionally, in determining the fifth information, the terminal and / or network device can determine the fifth information based on the type of monitoring information and the type of channel measurement resources. This effectively determines the "CPU information required for AI function monitoring information calculation" that matches the type of monitoring information and the type of channel measurement resources, thereby significantly improving the accuracy of the CPU information required for AI function monitoring information calculation and ensuring system performance.

[0244] Optionally, in some embodiments, the type of monitoring information includes at least one of the following: monitoring results of AI functions, performance index values ​​of AI functions, predicted CSI, and actual CSI. Therefore, for all possible types of monitoring information, it supports efficient calculation of the CPU information required for calculating the monitoring information of AI functions, applicable to various possible communication scenarios.

[0245] Optionally, in some embodiments, the fifth piece of information can be represented as Y.

[0246] Optionally, in some embodiments, at least one candidate information may be predefined, each candidate information being associated with a combination of a type of monitoring information and a type of channel measurement resource. Then, candidate information associated with the type of monitoring information and the type of channel measurement resource is determined from the at least one candidate information, and the selected candidate information is used as the fifth information.

[0247] In step S2402, the terminal and / or network device determine the second information based on the first information and the fifth information, or determine the fifth information as the second information.

[0248] Optionally, in some embodiments, monitoring information reporting may include both model inference and monitoring information calculation. Alternatively, monitoring information reporting may only include monitoring information calculation. Optionally, in some embodiments, if monitoring information reporting includes both model inference and monitoring information calculation, the terminal and / or network device can determine the second information based on the first information and the fifth information. Optionally, the terminal can accumulate the first information and the fifth information and determine the accumulated result as the second information. Optionally, the network device can accumulate the first information and the fifth information and determine the accumulated result as the second information. Optionally, the terminal and the network device can accumulate the first information and the fifth information and determine the accumulated result as the second information.

[0249] Optionally, in some embodiments, if the monitoring information reporting includes monitoring information calculation, the terminal and / or network device can determine the fifth information as the second information. Optionally, the terminal can determine the fifth information as the second information. Optionally, the network device can determine the fifth information as the second information. Optionally, both the terminal and the network device can determine the fifth information as the second information.

[0250] Optionally, in some embodiments, the second information is determined based on the first information and the fifth information. For example, it may be by accumulating the information on the CPU required for predicting CSI by the AI ​​function and the information on the monitoring information of the AI ​​function, and then determining the accumulated result as the information on the CPU required for reporting the monitoring information of the AI ​​function.

[0251] Optionally, in some embodiments, the fifth information is determined as the second information. For example, the information required to calculate the CPU based on the monitoring information of the AI ​​function can be directly determined as the information required to report the monitoring information of the AI ​​function to the CPU.

[0252] The communication method involved in the embodiments of this disclosure may include at least one of steps S2401 to S2402. For example, steps S2401 and S2402 may be implemented as independent embodiments, steps S2401+S2402 may be implemented as independent embodiments, etc., but are not limited thereto.

[0253] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0254] In this embodiment, the terminal and / or network device determine the fifth information, and based on the first and fifth information, determine the second information, or determine the fifth information as the second information. The fifth information is used to indicate the CPU information required for the AI ​​function's monitoring information calculation. Therefore, the terminal and network device can have a consistent understanding of the CPU information required for the AI ​​function's monitoring information calculation, thereby enabling the terminal and network device to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of CSI prediction based on the AI ​​function.

[0255] Figure 2E is an interactive schematic diagram illustrating a communication method according to yet another embodiment of the present disclosure. As shown in Figure 2E, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0256] Step S2501: The network device configures channel measurement resources for the terminal.

[0257] Optionally, in some embodiments, the network device can configure channel measurement resources for the terminal, which can be used to measure CSI. Channel measurement resources can be time-domain resources and / or frequency-domain resources.

[0258] Optionally, in some embodiments, the channel measurement resources configured by the network device for the terminal can be used by the terminal to generate a dataset. The dataset can then be used to train AI functions (or AI models).

[0259] Step S2502: The terminal generates a dataset based on channel measurement resources.

[0260] Optionally, in some embodiments, the terminal may determine the channel measurement resources configured by the network device and use the channel measurement resources to generate a dataset.

[0261] In step S2503, the terminal and / or network device determine the third information based on a predefined seventh value.

[0262] The third information indicates the CPU required to generate the dataset, which is used to train the AI ​​function. Optionally, in some embodiments, the third information may be represented as Y′.

[0263] In other words, if the channel measurement resources configured by the network device for the terminal are used to generate a dataset, then the terminal and / or the network device can determine the third information based on a predefined seventh value.

[0264] Optionally, in some embodiments, if the channel measurement resources configured by the network device for the terminal are used to generate a dataset, the terminal can determine the third information based on a predefined seventh value.

[0265] Optionally, in some embodiments, if the channel measurement resources configured by the network device for the terminal are used to generate a dataset, the network device can determine the third information based on a predefined seventh value.

[0266] Optionally, in some embodiments, if the channel measurement resources configured by the network device for the terminal are used to generate a dataset, the terminal and the network device can determine the third information based on a predefined seventh value.

[0267] Optionally, in some embodiments, if the channel measurement resources configured by the network device for the terminal are used to generate a dataset, the seventh value can be directly determined as the CPU information required to generate the dataset.

[0268] The communication method involved in the embodiments of this disclosure may include at least one of steps S2501 to S2503. For example, steps S2501, S2502, and S2503 may be implemented as independent embodiments, steps S2501+S2502 may be implemented as independent embodiments, steps S2501+S2503 may be implemented as independent embodiments, steps S2502+S2503 may be implemented as independent embodiments, steps S2501+S2502+S2503 may be implemented as independent embodiments, and so on, but are not limited thereto.

[0269] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0270] In the embodiments disclosed herein, each step and its optional implementation can also be carried out independently.

[0271] In this embodiment, the network device configures channel measurement resources for the terminal. The terminal generates a dataset based on these resources. The terminal and / or the network device determine third information based on a predefined seventh value. This allows the terminal and network device to have a consistent understanding of the CPU information required to generate the dataset, enabling them to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI predictions.

[0272] Figure 2F is an interactive schematic diagram illustrating a communication method according to yet another embodiment of the present disclosure. As shown in Figure 2F, the embodiments of the present disclosure relate to a communication method that can be used in a communication system 100, and are not limited thereto. The above method includes:

[0273] Step S2601: The terminal and / or network device determines the eighth or ninth value.

[0274] The eighth value indicates the number of active channel measurement resources corresponding to a single CSI report associated with a channel measurement resource. Optionally, in some embodiments, a channel measurement resource may be associated with at least one CSI report, such as two CSI reports. The terminal and / or network device can determine the number of active channel measurement resources corresponding to a single CSI report associated with a channel measurement resource, that is, determine the eighth value. The determined eighth value can be used to determine the fourth information, which indicates the number of active channel measurement resources.

[0275] The ninth value indicates the number of channel measurement resources activated corresponding to multiple different reporting quantities in a single CSI report associated with a channel measurement resource. Optionally, in some embodiments, a single CSI report may contain one or more reporting quantities, which may be the same or different. The number of channel measurement resources activated corresponding to the "multiple different reporting quantities" in a single CSI report can be represented by the ninth value. For example, if a single CSI report is associated with two different reporting quantities, and one reporting quantity corresponds to K1 = {1,2,4}, while the other reporting quantity corresponds to K2 = {1,2,...,K}, then the "number of channel measurement resources activated corresponding to the "multiple different reporting quantities" in a single CSI report" is K1 + K2.

[0276] Optionally, in some embodiments, the terminal and / or network device can determine the number of active channel measurement resources corresponding to multiple different reporting quantities included in a single CSI report associated with a channel measurement resource, that is, determine the ninth value. The determined ninth value can be used to determine the fourth information, which is used to indicate the number of active channel measurement resources.

[0277] In step S2602, the terminal and / or network device determine the fourth information based on the eighth or ninth value.

[0278] The fourth piece of information is used to indicate the number of active channel measurement resources.

[0279] Optionally, in some embodiments, the terminal may determine the fourth information based on the eighth or ninth value.

[0280] Optionally, in some embodiments, the network device may determine the fourth information based on an eighth or ninth value.

[0281] Optionally, in some embodiments, the terminal and network device may determine the fourth information based on the eighth or ninth value.

[0282] Optionally, in some embodiments, in the process of determining the fourth information based on the eighth value, the fourth information can be determined based on the number of active channel measurement resources corresponding to a single CSI report associated with the channel measurement resource indicated by the eighth value, and the number of CSI reports.

[0283] Optionally, in some embodiments, during the process of determining the fourth information based on the ninth value, the number of channel measurement resources activated corresponding to multiple different reporting quantities in a single CSI report associated with the channel measurement resource indicated by the ninth value can be determined as the fourth information.

[0284] The communication method involved in the embodiments of this disclosure may include at least one of steps S2601 to S2602. For example, steps S2601 and S2602 may be implemented as independent embodiments, steps S2601+S2602 may be implemented as independent embodiments, etc., but are not limited thereto.

[0285] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0286] In this embodiment, the terminal and / or network device can determine an eighth or ninth value, and determine the fourth information based on the eighth or ninth value. Thus, the terminal and network device can have a consistent understanding of the number of activated channel measurement resources, enabling them to determine CSI processing behavior. This allows the network device to configure more reasonable CSI reporting parameters for the terminal, ensuring the accuracy and effectiveness of AI-based CSI prediction.

[0287] Figure 3 is an interactive schematic diagram illustrating a communication method according to another embodiment of the present disclosure. As shown in Figure 3, the embodiments of the present disclosure relate to a communication method that can be used in a communication device, which can be a terminal and / or a network device. The above method includes:

[0288] Step S3101: Determine at least one of the first information, second information, third information, and fourth information, wherein the first information is used to instruct the artificial intelligence (AI) function to predict channel state information (CSI) and / or the information of the channel state information processing unit (CPU) required for CSI reporting; the second information is used to instruct the information of the monitoring information reporting required by the AI ​​function; the third information is used to instruct the information of the CPU required to generate the dataset, which is used to train the AI ​​function; and the fourth information is used to instruct the number of activated channel measurement resources.

[0289] The communication method involved in the embodiments of this disclosure may include step S3101. For example, step S3101, etc., may be implemented as a standalone embodiment, etc., but is not limited thereto.

[0290] In the embodiments disclosed herein, some or all of the steps and their optional implementations may be arbitrarily combined with some or all of the steps in other embodiments, or may be arbitrarily combined with the optional implementations in other embodiments.

[0291] Optionally, in some embodiments of this disclosure, determining the first information includes:

[0292] Determine a first value, and / or determine a second value, wherein the first value is related to a first input data dimension of the AI ​​function, and the second value is related to a first output data dimension of the AI ​​function;

[0293] Based on the first value and / or the second value, and the information of the first CPU, the first information is determined, wherein the first CPU is the CPU required for predicting CSI based on the AI ​​functional unit, and the first information is used to indicate the information of the CPU required for predicting CSI by the AI ​​function.

[0294] Optionally, in some embodiments of this disclosure, determining the first value includes:

[0295] Determine the first parameter;

[0296] The first input data dimension is determined based on the first parameter;

[0297] A first value is determined based on the first input data dimension and the second input data dimension, wherein the second input data dimension is the input data dimension of the AI ​​functional unit.

[0298] Optionally, in some embodiments of this disclosure, determining the second value includes:

[0299] Determine the first parameter;

[0300] The first output data dimension is determined based on the first parameter;

[0301] The second value is determined based on the first output data dimension and the second output data dimension, wherein the second output data dimension is the output data dimension of the AI ​​functional unit.

[0302] Optionally, in some embodiments of this disclosure, the first parameter includes at least one of the following:

[0303] Number of antenna ports;

[0304] Number of frequency domain units;

[0305] Number of prediction times, where the prediction times are used to predict CSI;

[0306] Number of measurement times, where the measurement times are used to measure CSI.

[0307] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein determining the first parameter includes at least one of the following:

[0308] Determine the first parameter for configuring network devices;

[0309] Based on the first parameter predefined in the protocol;

[0310] Send the first parameter to the network device.

[0311] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein determining the first parameter includes at least one of the following:

[0312] Configure the first parameter for the terminal;

[0313] Based on the first parameter predefined in the protocol;

[0314] The first parameter sent by the receiving terminal.

[0315] Optionally, in some embodiments of this disclosure, determining the first value includes:

[0316] Based on the first input data dimension, determine the first complexity and / or number of parameters of the AI ​​function;

[0317] Determine the first value based on the first complexity and / or the number of parameters.

[0318] Optionally, in some embodiments of this disclosure, determining the second value includes:

[0319] Based on the first output data dimension, determine the second complexity and / or number of parameters of the AI ​​function;

[0320] Determine the second value based on the second complexity and / or the number of parameters.

[0321] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein the method further includes:

[0322] Send the first value and / or the second value to the network device.

[0323] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the method further includes:

[0324] The receiving terminal sends the first and / or second numerical values.

[0325] Optionally, in some embodiments of this disclosure, determining the first information includes:

[0326] Determine the third value;

[0327] Based on the third value and the information of the second CPU, the first information is determined, wherein the second CPU is the CPU required for non-AI predicted CSI and / or CSI reporting.

[0328] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein determining the third value includes at least one of the following:

[0329] Based on a predefined third value in the protocol;

[0330] Send a third value to the network device.

[0331] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein determining the third value includes at least one of the following:

[0332] Based on a predefined third value in the protocol;

[0333] The third value sent by the receiving terminal.

[0334] Optionally, in some embodiments of this disclosure, determining the first information includes:

[0335] Determine at least one of the fourth, fifth, and sixth values;

[0336] First information is determined based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values, wherein the first information is used to indicate the CPU information required for AI function prediction of CSI.

[0337] Optionally, in some embodiments of this disclosure, the first information is determined based on the type of channel measurement resources and at least one of a fourth, fifth, and sixth value, including:

[0338] The channel measurement resource is of the type of periodic resource and / or semi-persistent resource. The first information is determined according to the fourth value and the first duration, wherein the first duration is the duration of the interval between adjacent channel state information reference signals (CSI-RS).

[0339] The channel measurement resources are of periodic and / or semi-persistent types. The first information is determined based on the fifth value and the number of prediction times, wherein the prediction times are used to predict CSI.

[0340] The channel measurement resource type is aperiodic resource. The first information is determined based on the sixth value and the first number, where the first number is the number of aperiodic CSI-RS.

[0341] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following:

[0342] Based on at least one of the fourth, fifth, and sixth predefined values ​​in the protocol;

[0343] Send at least one of the fourth, fifth, and sixth values ​​to the network device.

[0344] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following:

[0345] Based on at least one of the fourth, fifth, and sixth predefined values ​​in the protocol;

[0346] At least one of the fourth, fifth, and sixth values ​​sent by the receiving terminal.

[0347] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein the method further includes:

[0348] Send the first message to the network device.

[0349] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein determining the first information includes:

[0350] The first message sent by the receiving terminal.

[0351] Optionally, in some embodiments of this disclosure, the types of monitoring information include at least one of the following:

[0352] Monitoring results of AI functions;

[0353] Performance metrics for AI functionality;

[0354] Predicted CSI;

[0355] The real CSI.

[0356] Optionally, in some embodiments of this disclosure, determining the second information includes:

[0357] The fifth piece of information is determined, which is used to indicate the CPU information required for the monitoring information calculation of the AI ​​function;

[0358] Based on the first and fifth pieces of information, determine the second piece of information, or determine the fifth piece of information as the second piece of information.

[0359] Optionally, in some embodiments of this disclosure, determining the fifth piece of information includes:

[0360] The fifth piece of information is determined based on the type of monitoring information and the type of channel measurement resources.

[0361] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein the method further includes:

[0362] Determine the channel measurement resources configured for network devices;

[0363] Generate a dataset based on channel measurement resources.

[0364] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the method further includes:

[0365] Configure channel measurement resources for the terminal.

[0366] Optionally, in some embodiments of this disclosure, determining the third information includes:

[0367] The third piece of information is determined based on the predefined seventh value.

[0368] Optionally, in some embodiments of this disclosure, determining the fourth piece of information includes:

[0369] Determine the eighth or ninth value, wherein the eighth value is used to indicate the number of channel measurement resources activated corresponding to a single CSI report associated with a channel measurement resource, and the ninth value is used to indicate the number of channel measurement resources activated corresponding to multiple different reporting quantities included in a single CSI report associated with a channel measurement resource.

[0370] The fourth piece of information is determined based on the eighth or ninth value.

[0371] Examples of the above embodiments are illustrated below:

[0372] Optionally, an AI function may be used as an example, including an AI model. The CPU required for the AI ​​function may be referred to as an ACPU. CPU information may include, for example, the number of CPUs, the terminal may be a UE, and the network device may be a base station; there are no restrictions on this.

[0373] Optionally, embodiments of this disclosure may introduce an ACPU pool occupied by an AI model, or may define the ACPU of an AI model as a basic unit, or convert the CPU occupied by the AI ​​model into a traditional CPU pool and statistically define the ACPU occupied by the AI ​​model for inference; or may determine the CPU occupied by the monitoring AI model based on a traditional CPU pool; or may determine the CPU occupied by the generated dataset, wherein the dataset is used to train a CSI prediction model (an optional example of the AI ​​model mentioned above); or may determine the number of activated channel measurement resources based on the reporting content associated with the channel measurement resources.

[0374] Optionally, in some embodiments, a method for defining the CPU usage of CSI prediction model inference is proposed, including the following:

[0375] Method 1: Define a first CSI prediction model and / or function of a basic unit based on the input data dimension and / or output data dimension of the model, or the complexity of the model and / or the number of model parameters (an optional example of the AI ​​functional unit mentioned above). The ACPU required for the inference of the first CSI prediction model and / or function can be used as the first ACPU.

[0376] Optionally, the CPU required for the CSI prediction model to predict CSI can be determined based on the predefined first ACPU and the input data dimensions and / or output data dimensions of the model (i.e., the first CSI prediction model and / or function of the basic unit).

[0377] The method for determining this can be: the CPU required for the CSI prediction model to predict CSI is... or in, This indicates the first CPU (ACPU).

[0378] w i and / or w o It can be obtained through the following methods:

[0379] Method 1-1: and / or N i and N o N represents the input and output data dimensions of the CSI prediction model, respectively. u,i and N u,oThese represent the input and output data dimensions of the predefined model (i.e., the first CSI prediction model and / or function of the basic unit), respectively. The input or output data dimensions of the CSI prediction model can be determined based on parameters configured by the network (NW), parameters reported by the UE, or predefined parameters. These parameters can be, for example, the number of antenna ports, the number of frequency domain elements, the number of predicted CSI moments, and the number of measured CSI moments within the observation window.

[0380] Method 1-2: w i and / or w o The value of w can be determined by the UE based on the model complexity / number of model parameters under different input data dimensions and / or output data dimensions, and then reported by the UE to the NW. For example, the UE can indicate w to the NW when reporting capabilities. i and / or w o The value of .

[0381] Method 2: The number of CPUs required for model inference (e.g., CSI prediction model predicting CSI) can be determined using traditional CPUs, such as N. ACPU =w1N 0,CPU Where N ACPU and N 0,CPU These represent the ACPU used for model inference and the CPU used for traditional algorithms, respectively. The value of w1 can be predefined, or the UE can indicate the value of w1 in the capability report.

[0382] Method 2a: The CPU usage of CSI reporting for model inference can be determined using traditional CPUs, such as N. 1,ACPU =w2N 1,CPU Among them, N 1,ACPU and N 1,CPU These represent the ACPU used for CSI reporting by the AI ​​model inference and the CPU used for CSI reporting calculated by the traditional algorithm (i.e., the traditional CSI prediction algorithm), respectively. The value of w2 can be predefined, or the UE can indicate the value of w2 in its capability reporting.

[0383] The aforementioned CSI reporting can be based on the Rel-18 Type II Doppler codebook. This "CSI" is the CSI of a future moment predicted by an AI model or traditional algorithm. The predicted CSI can be reported to the NW via the Rel-18 Type II Doppler codebook.

[0384] Method 3: The number of CPUs required for the CSI prediction model can be determined based on different measurement resource types. For periodic and / or semi-persistent channel measurement resources, the number of CPUs for the CSI prediction model can be determined based on the observation window parameter M and / or the prediction window parameter K, such as N.ACPU =X1M or X2K, where X1 or X2 is the UE capability reporting indicator or a predefined value. For aperiodic channel measurement resources, the number of CPUs for the CSI prediction model can be determined by the number of aperiodic CSI-RS, such as N. ACPU =X3K s X3 can be predefined, or the UE can indicate X3 to the NW in the capability report. s Indicates the number of aperiodic CSI-RS.

[0385] Method 4: If the terminal deploys multiple CSI prediction AI models, the CPU occupied by each model can be determined independently through the methods described in Method 1, Method 2 or Method 3 above, or the UE can indicate the CPU of each model and / or function when reporting capabilities.

[0386] Optionally, in some embodiments, the method for defining the CPU usage for monitoring information reporting includes the following:

[0387] Optionally, the number of CPUs required to calculate the monitoring information can be Y, where the value of Y can be determined based on the type of monitoring information being calculated and the time-domain type of the channel measurement resources used within the prediction window.

[0388] Optionally, the monitoring information includes the final monitoring results, performance index values, ground truth CSI, and predicted future time CSI. The time domain type of the channel measurement resources includes periodic, semi-persistent, and aperiodic measurement resources.

[0389] Optionally, the value of Y can be determined by any combination of monitoring information and configured channel measurement resource types. The value of Y can be predefined through negotiation between the UE and NW, or it can be determined based on the number of future monitoring moments K' within the prediction window, such as Y = K', where K' ≤ K.

[0390] Optionally, monitoring information reporting may include model inference and monitoring information computation. Therefore, the CPU usage for monitoring information reporting includes the sum of the CPU usage for model inference and the CPU usage for computing monitoring information.

[0391] Optionally, in some embodiments, the CPU definition method for generating the CSI model training dataset includes the following:

[0392] When the configured reporting amount is 'None', meaning no reporting content is included, the configured channel measurement resources can be used to generate the training dataset. In this case, the number of CPUs required to generate the AI ​​model training dataset can be Y′, where Y′ is a predefined integer value.

[0393] Optionally, in some embodiments, the method for defining the number of activated channel measurement resources includes the following:

[0394] If a channel measurement resource is associated with two CSI reports, or if a channel measurement resource is associated with a single report containing two different reporting quantities, the number of activated channel measurement resources is K1+K2. The values ​​of K1 and K2 can be indicated by the UE through capability reporting. Here, K1 and K2 represent the number of activated channel measurement resources when associated with one CSI report, or the number of activated channel measurements corresponding to two different reporting quantities in a single report.

[0395] Optionally, in some embodiments, Embodiment 1 (Model Reasoning):

[0396] Suppose a user interface (UE) has trained a scalable CSI prediction AI model, meaning the AI ​​model can support different input and / or output data dimensions. The processing complexity varies depending on the different input and / or output data dimensions supported by the AI ​​model, and consequently, the CPU usage also differs. Let's take the model's output data dimension as an example, defining the prediction window as containing the CSI at one time point. This means the AI ​​model infers the CSI at a future time point from the historical CSI of multiple inputs. In this case, its CPU usage is... Define this model as the first CSI prediction model, which is the basic unit. The ACPU used by the first CSI prediction model is defined as the first ACPU. If the AI ​​model predicts the CSI at four future time points, the CPU usage for the corresponding model inference is: UE can report w i The value of w can also be predefined. i =N, where N represents the number of future moments in the predicted CSI.

[0397] Optionally, in some embodiments, in order to retain the traditional CPU definition, the above-mentioned ACPU can be converted to CPU, such as N. 0,CPU =w1N ACPU The value of w1 can be determined based on the complexity of the AI ​​model used and the complexity of the traditional algorithm, and then the value of w1 is reported through the UE capability.

[0398] Optionally, in some embodiments, the historical CSI can be obtained through periodic, semi-persistent, or aperiodic Channel Measurement Resources (CSI-RS). The CPU usage for AI model inference can also differ depending on the time-domain type. For periodic or semi-persistent CSI-RS, the CPU usage is N. ACPU=X1M or X2K, where X1 or X2 is the value of the UE capability reporting indication, or a predefined value. For aperiodic channel measurement resources, N ACPU =X3K s X3 is the value of the UE capability reporting indication, or a predefined value, K s Indicates the number of aperiodic CSI-RS.

[0399] Optionally, in some embodiments, Embodiment 2 (CPU usage for monitoring information reporting):

[0400] As mentioned above, the model's monitoring information includes monitoring results, predicted CSI, measured ground truth CSI, and performance index values. Different monitoring information requires different amounts of CPU for CSI processing. If the monitoring information is a monitoring result or a performance index value, CSI processing involves channel estimation, calculating SGCS or NMSE, and the NW can configure K' = 2 aperiodic CSI-RS resources. These two aperiodic CSI-RS resources are used to calculate the monitoring information for two future time points. Figure 4 below shows a CSI prediction model that predicts the CSI for K = 4 future time points based on CSI measured at N = 4 historical time points within the observation window. However, during model performance monitoring, the two configured aperiodic CSI-RS resources are only transmitted at the first and fourth time points within the prediction window. The UE estimates channel information and calculates performance index values ​​based on the received CSI-RS signals. In this case, the CPU usage for the UE to calculate the monitoring information is K' = 2. Optionally, the CPU usage does not depend on the number of monitoring times within the prediction window, but is predefined to occupy Y CPUs, which are used to calculate monitoring information. As shown in Figure 4, which is a possible CSI prediction diagram in an embodiment of this disclosure, the CSI for the next K=4 times can be predicted based on CSI measured at 4 historical times. If a monitoring information session includes model inference and monitoring information reporting, the CPU usage should include the sum of the CPU used for model inference and the CPU used for monitoring information. According to Embodiment 1, the number of CPUs occupied by the AI ​​model is... If the CPU usage for calculating monitoring information is K' = 2, then the total CPU usage for monitoring information is...

[0401] Optionally, in some embodiments, Embodiment 3 (number of activated channel measurement resources):

[0402] Assuming the NW is configured with periodic or semi-persistent CSI-RS resources, the UE, based on these resources, can not only measure historical CSI for model inference but also report the measured CSI to the NW via a codebook. It can also measure future CSI (which can be used to calculate monitoring information). Therefore, this CSI-RS resource can be associated with two different reporting quantities. If the reporting quantity is codebook-based CSI reporting, then the number of activated CSI-RS resources is K1 = {1, 2, 4}. If the reporting quantity is monitoring information, then the number of activated CSI-RS resources is K2 = {1, 2, ..., K}. Therefore, the total number of activated CSI-RS resources for this period is K1 + K2.

[0403] According to the definition method of CPU usage for CSI inference, model monitoring, or training CSI prediction model dataset generation of the AI ​​model provided in this disclosure embodiment, as well as the definition method of the number of activated channel measurement resources, the UE and NW have a consistent understanding of CSI processing behavior, thereby configuring more reasonable CSI reporting parameters, such as configuring a reasonable number of CSI reports and CSI reporting volume.

[0404] This disclosure also provides embodiments of an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., a RAN) in any of the above methods.

[0405] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a central processing unit or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0406] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit, microprocessor, graphics processing unit (GPU) (which can be understood as a microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc.

[0407] Figure 5 is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure. As shown in Figure 5, the communication device 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc.

[0408] In some embodiments, wherein

[0409] The processing module 5102 is used to determine at least one of the first information, the second information, the third information, and the fourth information, wherein the first information is used to instruct the artificial intelligence (AI) function to predict channel state information (CSI) and / or the information of the channel state information processing unit (CPU) required for CSI reporting; the second information is used to instruct the information of the monitoring information reporting required by the AI ​​function; the third information is used to instruct the information of the CPU required to generate a dataset, the dataset being used to train the AI ​​function; and the fourth information is used to instruct the number of activated channel measurement resources.

[0410] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0411] Determine a first value, and / or determine a second value, wherein the first value is related to a first input data dimension of the AI ​​function, and the second value is related to a first output data dimension of the AI ​​function;

[0412] Based on the first value and / or the second value, and the information of the first CPU, the first information is determined, wherein the first CPU is the CPU required for predicting CSI based on the AI ​​functional unit, and the first information is used to indicate the information of the CPU required for predicting CSI by the AI ​​function.

[0413] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0414] Determine the first parameter;

[0415] The first input data dimension is determined based on the first parameter;

[0416] A first value is determined based on the first input data dimension and the second input data dimension, wherein the second input data dimension is the input data dimension of the AI ​​functional unit.

[0417] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0418] Determine the first parameter;

[0419] The first output data dimension is determined based on the first parameter;

[0420] The second value is determined based on the first output data dimension and the second output data dimension, wherein the second output data dimension is the output data dimension of the AI ​​functional unit.

[0421] Optionally, in some embodiments of this disclosure, the first parameter includes at least one of the following:

[0422] Number of antenna ports;

[0423] Number of frequency domain units;

[0424] Number of prediction times, where the prediction times are used to predict CSI;

[0425] Number of measurement times, where the measurement times are used to measure CSI.

[0426] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein the processing module 5102 is configured to perform at least one of the following:

[0427] Determine the first parameter for configuring network devices;

[0428] Based on the first parameter predefined in the protocol;

[0429] The transceiver module 5101 is used to send the first parameter to the network device.

[0430] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein the processing module 5102 is configured to perform at least one of the following:

[0431] Configure the first parameter for the terminal;

[0432] Based on the first parameter predefined in the protocol;

[0433] The transceiver module 5101 is used to receive the first parameter sent by the terminal.

[0434] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0435] Based on the first input data dimension, determine the first complexity and / or number of parameters of the AI ​​function;

[0436] Determine the first value based on the first complexity and / or the number of parameters.

[0437] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0438] Based on the first output data dimension, determine the second complexity and / or number of parameters of the AI ​​function;

[0439] Determine the second value based on the second complexity and / or the number of parameters.

[0440] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein, the transceiver module 5101 is used to send a first value and / or a second value to the network device.

[0441] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the transceiver module 5101 is used to receive a first value and / or a second value sent by the terminal.

[0442] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0443] Determine the third value;

[0444] Based on the third value and the information of the second CPU, the first information is determined, wherein the second CPU is the CPU required for non-AI predicted CSI and / or CSI reporting.

[0445] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein the processing module 5102 is configured to perform at least one of the following:

[0446] Based on a predefined third value in the protocol;

[0447] The transceiver module 5101 is used to send third values ​​to network devices.

[0448] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein the processing module 5102 is configured to perform at least one of the following:

[0449] Based on a predefined third value in the protocol;

[0450] The transceiver module 5101 is used to receive the third value sent by the terminal.

[0451] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0452] Determine at least one of the fourth, fifth, and sixth values;

[0453] First information is determined based on the type of channel measurement resources and at least one of the fourth, fifth, and sixth values, wherein the first information is used to indicate the CPU information required for AI function prediction of CSI.

[0454] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0455] The channel measurement resource is of the type of periodic resource and / or semi-persistent resource. The first information is determined according to the fourth value and the first duration, wherein the first duration is the duration of the interval between adjacent channel state information reference signals (CSI-RS).

[0456] The channel measurement resources are of periodic and / or semi-persistent types. The first information is determined based on the fifth value and the number of prediction times, wherein the prediction times are used to predict CSI.

[0457] The channel measurement resource type is aperiodic resource. The first information is determined based on the sixth value and the first number, where the first number is the number of aperiodic CSI-RS.

[0458] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein, the processing module 5102 is configured to:

[0459] Based on at least one of the fourth, fifth, and sixth predefined values ​​in the protocol;

[0460] The transceiver module 5101 is used to send at least one of the fourth, fifth, and sixth values ​​to the network device.

[0461] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the processing module 5102 is configured to:

[0462] Based on at least one of the fourth, fifth, and sixth predefined values ​​in the protocol;

[0463] The transceiver module 5101 is used to receive at least one of the fourth, fifth, and sixth values ​​sent by the terminal.

[0464] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein, the transceiver module 5101 is used to send first information to the network device.

[0465] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the transceiver module 5101 is used to receive first information sent by the terminal.

[0466] Optionally, in some embodiments of this disclosure, the types of monitoring information include at least one of the following:

[0467] Monitoring results of AI functions;

[0468] Performance metrics for AI functionality;

[0469] Predicted CSI;

[0470] The real CSI.

[0471] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0472] The fifth piece of information is determined, which is used to indicate the CPU information required for the monitoring information calculation of the AI ​​function;

[0473] Based on the first and fifth pieces of information, determine the second piece of information, or determine the fifth piece of information as the second piece of information.

[0474] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0475] The fifth piece of information is determined based on the type of monitoring information and the type of channel measurement resources.

[0476] Optionally, in some embodiments of this disclosure, the communication device includes a terminal; wherein, the processing module 5102 is configured to:

[0477] Determine the channel measurement resources configured for network devices;

[0478] Generate a dataset based on channel measurement resources.

[0479] Optionally, in some embodiments of this disclosure, the communication device includes a network device; wherein, the processing module 5102 is configured to:

[0480] Configure channel measurement resources for the terminal.

[0481] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0482] The third piece of information is determined based on the predefined seventh value.

[0483] Optionally, in some embodiments of this disclosure, the processing module 5102 is configured to:

[0484] Determine the eighth or ninth value, wherein the eighth value is used to indicate the number of channel measurement resources activated corresponding to a single CSI report associated with a channel measurement resource, and the ninth value is used to indicate the number of channel measurement resources activated corresponding to multiple different reporting quantities included in a single CSI report associated with a channel measurement resource.

[0485] The fourth piece of information is determined based on the eighth or ninth value.

[0486] Optionally, the transceiver module described above is used to perform at least one of the communication steps such as sending and / or receiving performed by the communication device in any of the above methods, which will not be elaborated here.

[0487] Optionally, the above processing module is used to perform at least one of the other steps performed by the communication device in any of the above methods, which will not be elaborated here.

[0488] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure. The communication device 6100 can be the terminal described above, or it can be the network device described above. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0489] As shown in Figure 6A, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. The communication device 6100 is used to execute any of the above methods.

[0490] In some embodiments, the communication device 6100 further includes one or more memories 6102 for storing instructions. Optionally, all or part of the memories 6102 may also be located outside the communication device 6100.

[0491] In some embodiments, the communication device 6100 further includes one or more transceivers 6103. When the communication device 6100 includes one or more transceivers 6103, the transceivers 6103 perform at least one of the communication steps such as sending and / or receiving in the above method, and the processor 6101 performs other steps.

[0492] In some embodiments, a transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0493] In some embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6102, and the interface circuit 6104 can be used to receive signals from the memory 6102 or other devices, and can be used to send signals to the memory 6102 or other devices. For example, the interface circuit 6104 can read instructions stored in the memory 6102 and send the instructions to the processor 6101.

[0494] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0495] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of the chip 6200 shown in Figure 6B, but it is not limited thereto.

[0496] Chip 6200 includes one or more processors 6201, which are used to perform any of the above methods.

[0497] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, the interface circuit 6202 is connected to memory 6203, and the interface circuit 6202 can be used to receive signals from memory 6203 or other devices, and the interface circuit 6202 can be used to send signals to memory 6203 or other devices. For example, the interface circuit 6202 can read instructions stored in memory 6203 and send the instructions to processor 6201.

[0498] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processor 6201 performs at least one of the other steps.

[0499] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0500] In some embodiments, chip 6200 further includes one or more memories 6203 for storing instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200.

[0501] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0502] This disclosure also provides a program product that, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0503] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0504] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0505] 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 disclosure.

[0506] 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.

[0507] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure 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 disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The method is performed by a communication device, and the method includes: Determine at least one of the following: first information, second information, third information, and fourth information, wherein... The first information is used to instruct the artificial intelligence (AI) function to predict the channel state information (CSI) and / or the information of the channel state information processing unit (CPU) required to report the CSI. The second information is used to instruct the monitoring information of the AI ​​function to be reported to the required CPU information; The third information is used to indicate the CPU information required to generate the dataset, which is used to train the AI ​​function. The fourth piece of information is used to indicate the number of active channel measurement resources.

2. The method as described in claim 1, characterized in that, The determination of the first information includes: Determine a first value, and / or determine a second value, wherein the first value is related to a first input data dimension of the AI ​​function, and the second value is related to a first output data dimension of the AI ​​function; The first information is determined based on the first value and / or the second value, and the information of the first CPU, wherein the first CPU is the CPU required for predicting CSI based on the AI ​​functional unit, and the first information is used to indicate the information of the CPU required for predicting CSI by the AI ​​function.

3. The method as described in claim 2, characterized in that, Determining the first value includes: Determine the first parameter; The first input data dimension is determined based on the first parameter; The first value is determined based on the first input data dimension and the second input data dimension, wherein the second input data dimension is the input data dimension of the AI ​​functional unit.

4. The method according to any one of claims 2-3, characterized in that, Determining the second value includes: Determine the first parameter; The first output data dimension is determined based on the first parameter; The second value is determined based on the first output data dimension and the second output data dimension, wherein the second output data dimension is the output data dimension of the AI ​​functional unit.

5. The method according to any one of claims 3-4, characterized in that, The first parameter includes at least one of the following: Number of antenna ports; Number of frequency domain units; Number of prediction times, wherein the prediction times are used to predict CSI; Number of measurement times, wherein the measurement times are used to measure CSI.

6. The method according to any one of claims 3-5, characterized in that, The communication device includes a terminal; wherein determining the first parameter includes at least one of the following: Determine the first parameter configured for the network device; The first parameter is predefined based on the protocol; Send the first parameter to the network device.

7. The method according to any one of claims 3-5, characterized in that, The communication device includes a network device; wherein determining the first parameter includes at least one of the following: Configure the first parameter for the terminal; The first parameter is predefined based on the protocol; Receive the first parameter sent by the terminal.

8. The method as described in claim 2, characterized in that, Determining the first value includes: Based on the first input data dimension, determine the first complexity and / or number of parameters of the AI ​​function; The first value is determined based on the first complexity and / or the number of parameters.

9. The method as described in claim 2 or 8, characterized in that, Determining the second value includes: Based on the first output data dimension, determine the second complexity and / or number of parameters of the AI ​​function; The second value is determined based on the second complexity and / or the number of parameters.

10. The method according to any one of claims 2-9, characterized in that, The communication device includes a terminal; wherein the method further includes: Send the first value and / or the second value to the network device.

11. The method according to any one of claims 2-9, characterized in that, The communication device includes a network device; wherein, the method further includes: The receiving terminal sends the first value and / or the second value.

12. The method as described in claim 1, characterized in that, The determination of the first information includes: Determine the third value; The first information is determined based on the third value and the information of the second CPU, wherein the second CPU is the CPU required for non-AI prediction of CSI and / or CSI reporting.

13. The method as described in claim 12, characterized in that, The communication device includes a terminal; wherein determining the third value includes at least one of the following: Based on the third value predefined in the protocol; Send the third value to the network device.

14. The method as described in claim 12, characterized in that, The communication device includes a network device; wherein determining the third value includes at least one of the following: Based on the third value predefined in the protocol; The third value sent by the receiving terminal.

15. The method as described in claim 1, characterized in that, The determination of the first information includes: Determine at least one of the fourth, fifth, and sixth values; The first information is determined based on the type of the channel measurement resource and at least one of the fourth, fifth, and sixth values, wherein the first information is used to indicate the CPU information required for AI function prediction of CSI.

16. The method as described in claim 15, characterized in that, Determining the first information based on the type of the channel measurement resource and at least one of the fourth, fifth, and sixth values ​​includes: The type of channel measurement resource is periodic resource and / or semi-persistent resource. The first information is determined according to the fourth value and the first duration, wherein the first duration is the duration of the interval between adjacent channel state information reference signals (CSI-RS). The channel measurement resource is of the type of periodic resource and / or semi-persistent resource. The first information is determined based on the fifth value and the number of prediction times, wherein the prediction times are used to predict CSI. The channel measurement resource is of the aperiodic resource type. The first information is determined based on the sixth value and the first number, wherein the first number is the number of aperiodic CSI-RS.

17. The method according to any one of claims 15-16, characterized in that, The communication device includes a terminal; wherein determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following: Based on at least one of the fourth, fifth, and sixth values ​​predefined in the protocol; Send at least one of the fourth, fifth, and sixth values ​​to the network device.

18. The method according to any one of claims 15-16, characterized in that, The communication device includes a network device; wherein, determining at least one of the fourth, fifth, and sixth values ​​includes at least one of the following: Based on at least one of the fourth, fifth, and sixth values ​​predefined in the protocol; At least one of the fourth, fifth, and sixth values ​​sent by the receiving terminal.

19. The method according to any one of claims 1-18, characterized in that, The communication device includes a terminal; wherein the method further includes: Send the first information to the network device.

20. The method according to any one of claims 1-18, characterized in that, The communication device includes a network device; wherein, determining the first information includes: The first information sent by the receiving terminal.

21. The method according to any one of claims 1-20, characterized in that, The types of monitoring information include at least one of the following: The monitoring results of the AI ​​function; The performance metrics of the AI ​​function; Predicted CSI; The real CSI.

22. The method according to any one of claims 1-21, characterized in that, The determination of the second information includes: The fifth piece of information is determined, wherein the fifth piece of information is used to indicate the CPU information required for the monitoring information calculation of the AI ​​function; The second information is determined based on the first information and the fifth information, or the fifth information is determined as the second information.

23. The method according to any one of claims 1-22, characterized in that, The determination of the fifth piece of information includes: The fifth piece of information is determined based on the type of the monitoring information and the type of the channel measurement resource.

24. The method according to any one of claims 1-23, characterized in that, The communication device includes a terminal; wherein the method further includes: Determine the channel measurement resources configured for network devices; The dataset is generated based on the channel measurement resources.

25. The method according to any one of claims 1-23, characterized in that, The communication device includes a network device; wherein, the method further includes: Configure the channel measurement resources for the terminal.

26. The method according to any one of claims 24-25, characterized in that, The determination of the third information includes: The third information is determined based on a predefined seventh value.

27. The method according to any one of claims 1-26, characterized in that, The determination of the fourth piece of information includes: Determine an eighth value or a ninth value, wherein the eighth value is used to indicate the number of active channel measurement resources corresponding to a single CSI report associated with the channel measurement resource, and the ninth value is used to indicate the number of active channel measurement resources corresponding to multiple different reporting amounts included in a single CSI report associated with the channel measurement resource. The fourth information is determined based on the eighth or ninth value.

28. A communication device, characterized in that, The communication device includes: The processing module is configured to determine at least one of the following: first information, second information, third information, and fourth information. The first information is used to instruct the artificial intelligence (AI) function to predict channel state information (CSI) and / or the information of the channel state information processing unit (CPU) required for CSI reporting. The second information is used to instruct the information of the CPU required for monitoring information reporting by the AI ​​function. The third information is used to instruct the information of the CPU required to generate a dataset, which is used to train the AI ​​function. The fourth information is used to instruct the number of activated channel measurement resources.

29. A communication device, characterized in that, include: One or more processors; wherein the processors are configured to perform the method as described in any one of claims 1-27.

30. A communication system, characterized in that, Includes a terminal and / or network device, wherein the terminal and / or network device is used to perform the method as described in any one of claims 1-27.

31. A storage medium storing instructions, characterized in that, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1-27.

32. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-27.

Images