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

Abstract

A communication method, a communication device, a communication system, a storage medium and a program product. The method comprises: a terminal determining a first value according to at least one of a transmission layer, a frequency granularity and a time unit, the first value being used to determine a performance of a first model; and the terminal sending a first report to a network device, the first report comprising quantized information of the first value. Thus, quantized indication and reporting of model performance monitoring information are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods, communication devices, communication systems, storage media, and program products. Background Technology

[0002] In wireless communication systems, when using artificial intelligence (AI) or machine learning (ML) models, the inference results of the model may not achieve the expected results due to changes in the terminal's channel. Therefore, the terminal needs to monitor and report the model's performance. Summary of the Invention

[0003] This disclosure provides communication methods, communication devices, communication systems, storage media, and program products.

[0004] According to a first aspect of the embodiments of this disclosure, a communication method is provided, executed by a terminal, the method comprising:

[0005] A first value is determined according to at least one of transport layer, frequency granularity, and time unit, and the first value is used to determine the performance of the first model.

[0006] A first report is sent to the network device, the first report including quantification information of the first value.

[0007] According to a second aspect of the embodiments of this disclosure, a communication method is provided, performed by a network device, the method comprising:

[0008] The receiving terminal sends a first report, the first report including quantization information of a first value, the first value being determined by the terminal according to at least one of transmission layer, frequency granularity, and time unit, the first value being used to determine the performance of the first model.

[0009] According to a third aspect of the present disclosure, an embodiment of the present disclosure provides a communication device that may include at least one of a transceiver module and a processing module; wherein the communication device may be used to perform an optional implementation of the first aspect or the second aspect.

[0010] According to a fourth aspect of the embodiments of this disclosure, a communication device is provided that can be used to perform the methods described in an optional implementation of the first or second aspect.

[0011] According to a fifth aspect of the embodiments of this disclosure, a communication device is provided, comprising:

[0012] One or more processors;

[0013] The communication device can be used to execute the method described in the optional implementation of the first or second aspect.

[0014] According to a sixth aspect of the present disclosure, a communication system is provided, including a terminal and a network device, wherein the terminal is configured to perform the method described in the optional implementation of the first aspect, and the network device is configured to perform the method described in the optional implementation of the second aspect.

[0015] According to a seventh aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform the method as described in an optional implementation of the first or second aspect.

[0016] According to an eighth aspect of the present disclosure, a program product is provided, including at least one of a program and instructions, wherein the program and instructions, when executed by a communication device, implement the method described in an optional implementation of the first or second aspect.

[0017] The technical solution provided in this disclosure can produce the following beneficial effects: the terminal can quantize and report model performance monitoring information according to at least one of the transmission layer, frequency granularity, and time unit, thereby realizing the terminal's quantitative indication and reporting of model performance monitoring information. Reliable model monitoring performance information can be obtained while reducing terminal feedback overhead, ensuring the quantification accuracy of performance detection information.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0020] Figure 1A This is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0021] Figure 1B This is a schematic diagram illustrating the prediction of future CSI within a prediction window based on historical moments within an observation window, according to an embodiment of this disclosure.

[0022] Figure 2A This is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0023] Figure 2BThis is a schematic diagram of the CSI reference resource corresponding to the quantization information of the first value shown in an embodiment of this disclosure.

[0024] Figure 2C This is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0025] Figure 2D This is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure.

[0026] Figure 3A This is a schematic diagram of the terminal structure proposed in the embodiments of this disclosure.

[0027] Figure 3B This is a schematic diagram of the structure of the network device proposed in the embodiments of this disclosure.

[0028] Figure 4A This is a schematic diagram of the structure of the communication device proposed in the embodiments of this disclosure.

[0029] Figure 4B This is a schematic diagram of the chip structure proposed in the embodiments of this disclosure. Detailed Implementation

[0030] This disclosure provides communication methods, communication devices, communication systems, storage media, and program products.

[0031] In a first aspect, embodiments of this disclosure provide a communication method executed by a terminal, the method comprising:

[0032] A first value is determined according to at least one of transport layer, frequency granularity, and time unit, and the first value is used to determine the performance of the first model.

[0033] A first report is sent to the network device, the first report including quantification information of the first value.

[0034] In the above embodiments, the terminal can quantize and report model performance monitoring information according to at least one of the transmission layer, frequency granularity, and time unit, thereby realizing the terminal's quantitative indication and reporting of model performance monitoring information. This can obtain reliable model monitoring performance information while reducing terminal feedback overhead and ensuring the quantification accuracy of performance detection information.

[0035] In conjunction with some embodiments of the first aspect, in some embodiments, the first value is obtained according to at least one of the following:

[0036] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model;

[0037] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model.

[0038] The statistical value of the first value within the first window.

[0039] In the above embodiments, multiple implementation methods of the first value are defined, enriching the types of the first value.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, the first value is a first performance index value, which includes at least a portion of the first value corresponding to the transport layer.

[0041] In the above embodiments, the first performance index value can be quantized and reported according to the transport layer.

[0042] In conjunction with some embodiments of the first aspect, in some embodiments, the first performance index value includes at least one of the following:

[0043] The first value corresponding to each transport layer;

[0044] The first value corresponding to the i-th transport layer, where i is a positive integer;

[0045] The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal.

[0046] In the above embodiments, a variety of feasible implementation methods are provided for the first performance index value, enriching the types of the first performance index.

[0047] In conjunction with some embodiments of the first aspect, in some embodiments, the first performance index value includes a first reference value and one or more first difference values, wherein the first reference value is a first value corresponding to a first transmission layer among a plurality of transmission layers, and the first difference value is the difference between the first value corresponding to the other transmission layers among the plurality of transmission layers besides the first transmission layer and the first reference value.

[0048] In the above embodiments, a reference value and a difference value are defined in the first performance index.

[0049] In conjunction with some embodiments of the first aspect, in some embodiments, the first transport layer includes at least one of the following:

[0050] The network device indicates the transport layer;

[0051] The terminal and the network device negotiate a predefined transport layer;

[0052] The terminal via The value of U, which is a bit-indicating transport layer value, is either predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal.

[0053] In the above embodiments, the first transport layer provides multiple possible implementation methods, enriching the reference values ​​in the corresponding first performance indicators.

[0054] In conjunction with some embodiments of the first aspect, in some embodiments, the first value is a second performance index value, the second performance index value including at least a portion of the first performance index values ​​corresponding to the sub-bands.

[0055] In the above embodiments, the second performance index value can be quantified and reported according to frequency granularity.

[0056] In conjunction with some embodiments of the first aspect, in some embodiments, the second performance index value includes at least one of the following:

[0057] The first performance index value corresponding to the entire broadband;

[0058] The first performance index value corresponding to each sub-band;

[0059] The average value of the first performance index corresponding to a portion of the sub-band;

[0060] The average of the first performance index value corresponding to all subbands.

[0061] In the above embodiments, a variety of feasible implementation methods are provided for the second performance index value, enriching the types of the second performance index.

[0062] In conjunction with some embodiments of the first aspect, in some embodiments, the second performance index value includes a second reference value and one or more second difference values, wherein the second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands, and the second difference value is the difference between the first value corresponding to other sub-bands among the plurality of sub-bands besides the first sub-band and the second reference value.

[0063] In the above embodiments, reference values ​​and differential values ​​are defined in the second performance index.

[0064] In conjunction with some embodiments of the first aspect, in some embodiments, the first sub-band includes at least one of the following:

[0065] The subband indicated by the network device;

[0066] The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device;

[0067] The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device.

[0068] In the above embodiments, the first sub-band provides multiple possible implementation methods, enriching the reference values ​​in the corresponding second performance indicators.

[0069] In conjunction with some embodiments of the first aspect, in some embodiments, the first value is a third performance index value, which includes at least a portion of the second performance index values ​​corresponding to the time units.

[0070] In the above embodiments, the third performance index value can be quantified and reported according to time units.

[0071] In conjunction with some embodiments of the first aspect, in some embodiments, the third performance index value includes at least one of the following:

[0072] The second performance index value corresponding to each time unit;

[0073] The second performance index values ​​corresponding to each of the time units;

[0074] The average value of the second performance index corresponding to all time units.

[0075] In the above embodiments, a variety of feasible implementation methods are provided for the third performance index value, enriching the types of the third performance index.

[0076] In conjunction with some embodiments of the first aspect, in some embodiments, the third performance index value includes a third reference value and one or more third difference values, wherein the third reference value is a first value corresponding to a first time unit among a plurality of time units, and the third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

[0077] In the above embodiments, reference values ​​and differential values ​​are defined in the third performance index.

[0078] In conjunction with some embodiments of the first aspect, in some embodiments, the first time unit includes at least one of the following:

[0079] The time unit indicated by the network device;

[0080] The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device;

[0081] The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

[0082] In the above embodiments, the first time unit provides multiple possible implementation methods, enriching the reference values ​​in the corresponding third performance index.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the quantization information of the first value is obtained using at least one of the following:

[0084] The first value is a performance index value, which is quantized by x bits, where x is a positive integer;

[0085] The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

[0086] In the above embodiments, a quantitative indication of the first performance index or reference value and the difference value is realized.

[0087] In conjunction with some embodiments of the first aspect, in some embodiments, at least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

[0088] In the above embodiments, a method for reporting relevant information of the first value is provided.

[0089] In conjunction with some embodiments of the first aspect, in some embodiments, the relevant information of the first value is at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value;

[0090] The relevant information for the first value is a performance index value, and the indication information is used to indicate the performance index value;

[0091] The relevant information for the first value includes a reference value and a difference value, and the indication information is used to indicate the reference value and the difference value.

[0092] In the above embodiments, reporting methods for the transmission layer, frequency granularity, time unit, performance index value, reference value, and differential value are provided respectively.

[0093] In conjunction with some embodiments of the first aspect, in some embodiments, the first reporting unit includes indication information of a reference value and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the second reporting unit includes indication information of a differential value;

[0094] Alternatively, the second reporting unit may include indication information of a reference value, indication information of at least one of the following: the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information of a differential value.

[0095] In the above embodiments, multiple reporting methods are provided, including transmission layer, frequency granularity, time unit, performance index value, reference value, and differential value.

[0096] In conjunction with some embodiments of the first aspect, in some embodiments, the indication information is carried on physical uplink control channel resources or physical uplink shared channel resources.

[0097] In the above embodiments, various resource transmission methods can be used, which enriches the implementation.

[0098] In conjunction with some embodiments of the first aspect, in some embodiments, determining the first value includes:

[0099] The channel state information based on the first model inference is determined according to the second configuration information. The second configuration information is associated with the first configuration information. The first configuration information is used to send a second report corresponding to the channel state information based on the first model inference. The second configuration information is used to send the first report.

[0100] The first value is determined based on the channel state information inferred from the first model.

[0101] In the above embodiments, the terminal can determine channel state information based on the correlation between the first report and the second report, using the channel state information inferred from the first model. The terminal can then determine a first value based on the channel state information inferred from the first model.

[0102] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0103] Receive the second configuration information sent by the network device.

[0104] In the above embodiments, the network device will pre-configure the second configuration information of the first report, and the second configuration information is related to the first configuration information.

[0105] In conjunction with some embodiments of the first aspect, in some embodiments, the first configuration information is associated with the second configuration information, including:

[0106] The first configuration information includes indication information for identifying the second report;

[0107] The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

[0108] In the above embodiments, a possible implementation method for associating the first configuration information with the second configuration information is provided.

[0109] In conjunction with some embodiments of the first aspect, in some embodiments, the channel state information based on the first model inference associated with the quantization information of the first value is not updated;

[0110] Sending the first report to the network device includes: sending the first report to the network device, wherein the first report is used to indicate quantization information of the first value that has not been updated.

[0111] In the above embodiments, when the channel state information based on model inference is not updated, the performance monitoring information of the model may not be reported, which can reduce the feedback overhead of performance monitoring information.

[0112] In conjunction with some embodiments of the first aspect, in some embodiments, the channel state information reference resource corresponding to the quantization information of the first value is determined according to at least one of the following:

[0113] The time when channel state information based on the inference from the first model is transmitted;

[0114] A second time unit is used to send the first report, the second time unit being predefined or indicated by the network device configuration.

[0115] In the above embodiments, a variety of possible implementation methods are provided for determining the channel state information reference resource corresponding to the quantization information of the first value.

[0116] Secondly, embodiments of this disclosure provide a communication method executed by a network device, the method comprising:

[0117] The receiving terminal sends a first report, the first report including quantization information of a first value, the first value being determined by the terminal according to at least one of transmission layer, frequency granularity, and time unit, the first value being used to determine the performance of the first model.

[0118] In conjunction with some embodiments of the second aspect, in some embodiments, the first value is obtained according to at least one of the following:

[0119] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model;

[0120] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model.

[0121] The statistical value of the first value within the first window.

[0122] In conjunction with some embodiments of the second aspect, in some embodiments, the first value is a first performance index value, which includes at least a portion of the first value corresponding to the transport layer.

[0123] In conjunction with some embodiments of the second aspect, in some embodiments, the first performance index value includes at least one of the following:

[0124] The first value corresponding to each transport layer;

[0125] The first value corresponding to the i-th transport layer, where i is a positive integer;

[0126] The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal.

[0127] In the above embodiments, a variety of feasible implementation methods are provided for the first performance index value, enriching the types of the first performance index.

[0128] In conjunction with some embodiments of the first aspect, in some embodiments, the first performance index value includes a first reference value and one or more first difference values, wherein the first reference value is a first value corresponding to a first transmission layer among a plurality of transmission layers, and the first difference value is the difference between the first value corresponding to the other transmission layers among the plurality of transmission layers besides the first transmission layer and the first reference value.

[0129] In conjunction with some embodiments of the second aspect, in some embodiments, the first transport layer includes at least one of the following:

[0130] The network device indicates the transport layer;

[0131] The terminal and the network device negotiate a predefined transport layer;

[0132] The terminal via The value of U, which is a bit-indicating transport layer value, is either predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal.

[0133] In conjunction with some embodiments of the second aspect, in some embodiments, the first value is a second performance index value, the second performance index value including at least a portion of the first performance index values ​​corresponding to the sub-bands.

[0134] In conjunction with some embodiments of the second aspect, in some embodiments, the second performance index value includes at least one of the following:

[0135] The first performance index value corresponding to the entire broadband;

[0136] The first performance index value corresponding to each sub-band;

[0137] The average value of the first performance index corresponding to a portion of the sub-band;

[0138] The average of the first performance index value corresponding to all subbands.

[0139] In conjunction with some embodiments of the second aspect, in some embodiments, the second performance index value includes a second reference value and one or more second difference values, wherein the second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands, and the second difference value is the difference between the first value corresponding to other sub-bands among the plurality of sub-bands besides the first sub-band and the second reference value.

[0140] In conjunction with some embodiments of the second aspect, in some embodiments, the first sub-band includes at least one of the following:

[0141] The subband indicated by the network device;

[0142] The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device;

[0143] The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device.

[0144] In conjunction with some embodiments of the second aspect, in some embodiments, the first value is a third performance index value, which includes at least a portion of the second performance index values ​​corresponding to the time units.

[0145] In conjunction with some embodiments of the second aspect, in some embodiments, the third performance index value includes at least one of the following:

[0146] The second performance index value corresponding to each time unit;

[0147] The second performance index values ​​corresponding to each of the time units;

[0148] The average value of the second performance index corresponding to all time units.

[0149] In conjunction with some embodiments of the second aspect, in some embodiments, the third performance index value includes a third reference value and one or more third difference values, wherein the third reference value is a first value corresponding to a first time unit among a plurality of time units, and the third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

[0150] In conjunction with some embodiments of the second aspect, in some embodiments, the first time unit includes at least one of the following:

[0151] The time unit indicated by the network device;

[0152] The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device;

[0153] The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

[0154] In conjunction with some embodiments of the second aspect, in some embodiments, the quantization information of the first value is obtained using at least one of the following:

[0155] The first value is a performance index value, which is quantized by x bits, where x is a positive integer;

[0156] The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

[0157] In conjunction with some embodiments of the second aspect, in some embodiments, at least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

[0158] In conjunction with some embodiments of the second aspect, in some embodiments, the relevant information of the first value is at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value;

[0159] The relevant information for the first value is a performance index value, and the indication information is used to indicate the performance index value;

[0160] The relevant information for the first value includes a reference value and a difference value, and the indication information is used to indicate the reference value and the difference value.

[0161] In conjunction with some embodiments of the second aspect, in some embodiments, the first reporting unit includes indication information of a reference value and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the second reporting unit includes indication information of a differential value;

[0162] Alternatively, the second reporting unit may include indication information of a reference value, indication information of at least one of the following: the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information of a differential value.

[0163] In conjunction with some embodiments of the second aspect, in some embodiments, the indication information is carried on physical uplink control channel resources or physical uplink shared channel resources.

[0164] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0165] Send second configuration information to the terminal, the second configuration information being used to send the first report;

[0166] The second configuration information is associated with the first configuration information, and the first configuration information is used to send a second report corresponding to the channel state information inferred based on the first model.

[0167] In conjunction with some embodiments of the second aspect, in some embodiments, the first configuration information is associated with the second configuration information, including:

[0168] The first configuration information includes indication information for identifying the second report;

[0169] The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

[0170] In conjunction with some embodiments of the second aspect, in some embodiments, the channel state information based on the first model inference associated with the quantization information of the first value is not updated;

[0171] The first report sent by the receiving terminal includes: receiving the first report sent by the terminal, wherein the first report includes quantization information of the first value associated with the channel state information based on the first model inference that has not been updated.

[0172] Thirdly, embodiments of this disclosure propose a terminal that may include at least one of a transceiver module and a processing module; wherein the terminal may be used to execute an optional implementation of the first aspect.

[0173] Fourthly, embodiments of this disclosure provide a network device that may include at least one of a transceiver module and a processing module; wherein the network device may be used to perform an optional implementation of the second aspect.

[0174] Fifthly, embodiments of this disclosure provide a terminal that may include one or more processors; wherein the terminal may be used to execute an optional implementation of the first aspect.

[0175] In a sixth aspect, embodiments of this disclosure provide a network device that may include one or more processors; wherein the network device may be used to perform an optional implementation of the second aspect.

[0176] In a seventh aspect, embodiments of this disclosure provide a communication system that may include: a terminal and a network device; wherein the terminal is configured to perform the method described in the optional implementation of the first aspect, and the network device is configured to perform the method described in the optional implementation of the second aspect.

[0177] Eighthly, 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 as described in an optional implementation of the first or second aspect.

[0178] In a ninth 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 an optional implementation of the first or second aspect.

[0179] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in an optional implementation of the first or second aspect.

[0180] Eleventhly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described in optional implementations of the first or second aspect.

[0181] It is understood that the aforementioned communication equipment, communication system, storage medium, program product, etc., 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.

[0182] This disclosure provides communication methods, communication devices, communication systems, storage media, and program products. In some embodiments, the terms communication method, information processing method, and information transmission method may be used interchangeably.

[0183] 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. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0184] 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.

[0185] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "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 expression or a plural expression.

[0186] In the embodiments disclosed herein, "multiple" refers to two or more.

[0187] In some embodiments, the terms "at least one of A or B, at least one of A and B", "one or more", "a plurality of", "multiple" and the like can be used interchangeably.

[0188] 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 whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch 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.

[0189] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); 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, and C.

[0190] 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.

[0191] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0192] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.

[0193] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0194] 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”.

[0195] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0196] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0197] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "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," and "bandwidth part (BWP)" can be used interchangeably.

[0198] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "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 subscriberstation, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, and client can be used interchangeably.

[0199] 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.

[0200] 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.

[0201] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0202] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0203] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0204] Figure 1A This is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0205] like Figure 1A As shown, the communication system 100 includes a terminal 101 and a network device 102.

[0206] In some embodiments, terminal 101 includes, for example, 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, but is not limited thereto.

[0207] In some embodiments, network device 102 may include at least one of access network device and core network device.

[0208] 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 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, but is not limited thereto.

[0209] 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.

[0210] 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.

[0211] In some embodiments, a core network device may be a single device, including one or more network elements, or it may be multiple devices or a group of devices, each including all or part of the multiple network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of the evolved packet core (EPC), 5G core network (5GCN), and next-generation core (NGC).

[0212] 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.

[0213] The following embodiments of this disclosure can be applied to Figure 1A The communication system 100 shown, or a part thereof, but not limited to it. Figure 1A The entities shown are illustrative; a communication system may include... Figure 1A All or part of the main body, or may include Figure 1A Other entities besides the main body, the number and form of each entity are arbitrary, each entity can be physical or virtual, the connection relationship between the entities is illustrative, the entities can be unconnected or connected, and 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.

[0214] 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), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Futuregeneration 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, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0215] In some embodiments of this disclosure, for medium- to high-speed mobile terminals, due to the rapid changes in channel information in the time domain, using the traditional Rel-15 / 16 / 17 Type II codebook to feed back channel status information (CSI) will lead to a degraded system performance. To address this issue, the Rel-18 Type II Doppler codebook was introduced in the 3GPP Rel-18 standardization.

[0216] The Rel-18 Type II Doppler codebook is based on downlink channel information estimated by the terminal side from historical moments. It uses traditional autoregressive or linear minimum mean square error (LMMSE) algorithms to predict downlink channel information for future moments, and then calculates the corresponding precoding information based on the predicted downlink channel information. Studies show that in medium-to-high-speed mobile scenarios, the Rel-18 Type II codebook significantly improves system performance compared to the Rel-16 / 17 Type II codebook.

[0217] With the development and application of artificial intelligence (AI) technology, AI has been widely applied to the physical layer of wireless communication. The traditional CSI prediction algorithm mentioned above can also use AI models to predict channel information at future moments. Current simulation evaluations show that the prediction performance based on AI models is superior to that of traditional non-AI model algorithms.

[0218] Regardless of whether the prediction algorithm uses an AI model or a non-AI model, it needs to utilize CSI data from multiple historical moments. The range within which downlink channel information is estimated based on CSI-RS transmitted from multiple historical moments is called the observation window. The range within which CSI data is predicted for multiple future moments is called the prediction window, such as... Figure 1B As shown.

[0219] Figure 1B This paper describes the prediction of future CSI within an observation window based on historical CSI values ​​within that window, under different parameter configurations. Here, N represents the channel status information-reference signal (CSI-RS) transmitted at N times within the observation window. M represents the interval between adjacent CSI-RS, for example, M equals 4 slots. K represents the number of CSI predictions for K times within the prediction window, for example, K equals 4 slots. D represents the interval between CSI predictions for adjacent times. The length of the prediction window, w_d = K·D.

[0220] During the process of using AI models, the inference results may not meet expectations due to channel variations within the UE. Therefore, it is necessary to monitor the performance of the AI ​​model. The following methods are currently supported for monitoring AI model performance.

[0221] This performance monitoring method

[0222] Step 1: UE calculates performance metric(s).

[0223] Step 2: The UE reports performance metric(s) to the network (network, NW).

[0224] The performance metric(s) in step one above is the square generalized cosine similarity (SGCS), which is defined according to the following conference conclusions.

[0225] Regarding the definition of SGCS:

[0226] For a given layer l∈{1,…,ν}, subband n3∈{1,…,N3}, and prediction instance n4∈{1,…,N4}, SGCS is defined as follows:

[0227] -For a given layer l∈{1,…,v},subband n3∈{1,…,N3},and prediction instance n4∈{1,…,N4},SGCS is defined as

[0228]

[0229] where is the predicted precoder represented by PMI used forinference for l-th layer,n3-th subband and n4-th prediction instance,and isthe precoder represented by PMI used for ground-truth CSI for l-th layer,n3-th subband and n4-th prediction instance

[0230] in, It is a predictive precoder, represented by the precoding matrix indication (PMI) used for inference at layer l, the n3rd subband, and the n4th time step.

[0231] It is a pre-encoder for ground truth CSI, represented by PMI for layer l, subband n3, and time n4.

[0232] Note: How to handle layer mapping mismatch depends on the UE implementation.

[0233] As shown in the above formula, the SGCS value is calculated based on the PMI calculated from the predicted CSI and the actual CSI. Specifically, the PMI is calculated based on the predicted CSI and the actual measured CSI.

[0234] The performance metrics reported by the UE in step two above include the following three candidate options:

[0235] For CSI prediction using a UE-side model, and for reporting contents of UE assisted performance monitoring, one candidate option will be selected through RAN1#121 meetings.

[0236] Option 1: Calculate an SGCS value based on the PMI corresponding to the predicted CSI and the PMI corresponding to the ground truth CSI for one inference report.

[0237] Option 2: Calculate an SGCS value based on the predicted CSI for one inference reporting and the ground truth CSI; simultaneously, calculate another SGCS value based on the ground truth CSI and the non-predicted CSI corresponding to the latest CSI-RS transmission occasion not later than the CSI reference resource of the inference reporting instance.

[0238] Option 3: Within the configured monitoring window, perform statistics on the reporting contents (e.g., mean of SGCS values, x% quantile CDF) of inference reporting instances at each reporting time of the inference report.

[0239] CDF stands for Cumulative Distribution Function. The x% quantile CDF is the value of the cumulative distribution function at the specific point x% quantile.

[0240] The monitoring window can be configured via the network.

[0241] The signaling details are yet to be determined (FFS on signaling details).

[0242] Whether to report per prediction instance, selected prediction instance(s), or averaged prediction instances is yet to be determined (FFS on whether to report per prediction instance, selected prediction instance(s), averaged over prediction instances).

[0243] The reporting frequency granularity (e.g., per wideband, per subband, averaged over subband, or selected subband) is yet to be determined.

[0244] Whether to report per layer, the first layer, or averaged over layers is yet to be determined (FFS on whether to report per layer, the first layer, or averaged over layers).

[0245] The implementation method of the quantification and reporting mechanism is yet to be determined (FFS on how to quantize and report mechanism).

[0246] Therefore, the performance metric SGCS that the UE may calculate may refer to at least one of the following:

[0247] (1) SGCS value corresponding to each transport layer. The SGCS value corresponding to the k-th transport layer is the same as the SGCS value corresponding to the 1st transport layer. The rank indicated by the UE is equal to the average of the SGCS values ​​corresponding to the v transport layers.

[0248] (2) The first performance index value corresponding to the entire broadband, the first performance index value corresponding to each sub-band, and the average value of the first performance index values ​​of the selected sub-bands or all sub-bands.

[0249] (3) The second performance index value corresponding to each time point, the second performance index value corresponding to the selected time point respectively, and the average of the second performance index values ​​corresponding to all time points.

[0250] Therefore, there is currently no corresponding quantification method for reporting the SGCS value calculated by the UE to the NW. Furthermore, there is no solution for reporting monitoring results when the CSI based on AI model inference is not updated.

[0251] Figure 2A This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 2A As shown, the embodiments of this disclosure relate to a communication method, which includes:

[0252] In step S2101, terminal 101 determines a first value according to at least one of the following: transmission layer, frequency granularity, and time unit.

[0253] In some embodiments, the terminal may determine the first value according to the transport layer.

[0254] In some embodiments, the terminal may determine the first value according to frequency granularity.

[0255] In some embodiments, the terminal may determine the first value according to a time unit.

[0256] In some embodiments, the terminal may determine the first value according to any combination of transport layer, frequency granularity, and time unit.

[0257] In some embodiments, frequency granularity can be bandwidth or subband.

[0258] In some embodiments, the time unit may be the predicted moment, the predicted period of time, or the predicted duration.

[0259] In some embodiments, the first value is used to determine the performance of the first model.

[0260] In some embodiments, the first value is used to indicate the performance of the first model.

[0261] In some embodiments, the first value is used to characterize the performance of the first model.

[0262] In other words, network devices determine the performance of the first model based on the first value.

[0263] In some embodiments, the first model may include an AI model or a machine learning (ML) model.

[0264] In some embodiments, the name of the first value is not limited, and it may be, for example, an SGCS value, a performance index value, etc.

[0265] In some embodiments, the types of the first value may include a first SGCS value, a second SGCS value, and a third SGCS value.

[0266] (1) The first SGCS value is obtained based on the precoding matrix indication corresponding to the real channel state information and the precoding matrix indication corresponding to the channel state information based on the first model inference.

[0267] In some embodiments, channel state information (CSI) may include channel information, or a feature vector corresponding to the channel information, or PMI.

[0268] In some embodiments, the first SGCS value may be calculated based on the PMI corresponding to the real CSI and the PMI corresponding to the CSI inferred from the first model.

[0269] (2) The second SGCS value is obtained based on the precoding matrix indication corresponding to the real channel state information and the precoding matrix indication corresponding to the first channel state information.

[0270] The precoding matrix indicator corresponding to the first channel state information is the precoding matrix indicator corresponding to the channel state information that is closest to the reference time of the channel state information reference resource corresponding to the channel state information based on the first model inference.

[0271] In some embodiments, channel state information (CSI) may include channel information, or a feature vector corresponding to the channel information, or PMI.

[0272] In some embodiments, the second SGCS value may be calculated based on the PMI corresponding to the real CSI and the PMI corresponding to the first CSI.

[0273] Wherein, the PMI corresponding to the first CSI is the PMI corresponding to the CSI that is closest to the reference time of the channel state information reference resource before the reference time of the CSI based on the first model inference.

[0274] (3) The third SGCS value is obtained based on the statistical value of the first value in the first window.

[0275] In some embodiments, the name of the first window is not limited, and it may be, for example, a monitoring window or an observation window.

[0276] In some embodiments, the monitoring window is configured for the network.

[0277] In some embodiments, the third SGCS value may be a statistical value based on the SGCS values ​​within the monitoring window, such as the mean of the SGCS values ​​or the x% quantile CDF.

[0278] In some embodiments, the first value is a first performance metric value, which includes at least a portion of the first value corresponding to the transport layer. Thus, the terminal can report quantized information of the first value according to the transport layer.

[0279] In some embodiments, the first performance metric value includes at least one of the following:

[0280] (1) The first value corresponding to each transport layer, that is, the SGCS value corresponding to each transport layer.

[0281] (2) The first value corresponding to the i-th transport layer, where i is a positive integer. Where i equals 1, and the first performance index value is the SGCS value corresponding to the 1st transport layer.

[0282] (3) The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal.

[0283] In some embodiments, the first performance metric value includes a first reference value and one or more first difference values.

[0284] Wherein, the first reference value is the first value corresponding to the first transmission layer among multiple transmission layers, and the first difference value is the difference between the first value corresponding to the other transmission layers (excluding the first transmission layer) and the first reference value.

[0285] In some embodiments, the first reference value may include one or more reference values. For example, each transport layer may correspond to one reference value.

[0286] In some embodiments, the number of first difference values ​​is related to the number of other transport layers L and the number of first reference values ​​R1, where L and R1 are positive integers.

[0287] In some embodiments, if the number of first reference values ​​R1 is equal to 1, then the number of first difference values ​​is equal to the number of other transport layers L.

[0288] In some embodiments, if the number of first reference values ​​R1 is equal to 1 and the number of other transport layers L is equal to 1, then the number of first difference values ​​is equal to 1.

[0289] In some embodiments, if the number of first reference values ​​R1 is equal to 1 and the number of other transport layers L is greater than 1, then the number of first difference values ​​is greater than 1 and equal to L.

[0290] In some embodiments, if the number of other transport layers L is equal to 1, then the number of first differential values ​​is equal to the number of first reference values ​​R1.

[0291] In some embodiments, if the number of other transport layers L is equal to 1 and the number of first reference values ​​R1 is equal to 1, then the number of first difference values ​​is equal to 1.

[0292] In some embodiments, if the number of other transport layers L is equal to 1 and the number of first reference values ​​R1 is greater than 1, then the number of first difference values ​​is greater than 1 and equal to R1.

[0293] In some embodiments, if the terminal reports a first performance index value that is an SGCS value corresponding to multiple transport layers, the SGCS value corresponding to the first transport layer is defined as the first reference value, and the difference between the SGCS values ​​corresponding to other transport layers and the first reference value is defined as the first difference value. That is, the first difference value is obtained by performing a difference operation between the SGCS values ​​corresponding to other transport layers and the first reference value.

[0294] In some embodiments, the first transport layer can be any one of a plurality of transport layers.

[0295] In some embodiments, the first transport layer includes at least one of the following:

[0296] (1) Transport layer indicated by network devices.

[0297] (2) The terminal and network equipment negotiate a predefined transport layer, such as the first predefined transport layer.

[0298] (3) The terminal passes The value of U, indicated by the bit, is either predefined or configured by the network device, or equal to the rank indicated by the terminal, i.e., the value of v reported by the UE. Here, the value of U represents the number of transport layers.

[0299] In some embodiments, the first value is a second performance index value, which includes at least a portion of the first performance index values ​​corresponding to the sub-bands. Thus, the terminal can report the quantization information of the first value at the frequency granularity.

[0300] In some embodiments, the second performance metric value includes at least one of the following:

[0301] (1) The first performance index value corresponding to the entire broadband.

[0302] (2) The first performance index value corresponding to each sub-band.

[0303] (3) The average value of the first performance index corresponding to a sub-band.

[0304] (4) The average value of the first performance index value corresponding to all sub-bands.

[0305] In some embodiments, the second performance metric value includes a second reference value and one or more second difference values.

[0306] The second reference value is the first value corresponding to the first sub-band among the multiple sub-bands, and the second difference value is the difference between the first value corresponding to the other sub-bands (excluding the first sub-band) and the second reference value.

[0307] In some embodiments, the second reference value may include one or more reference values. For example, each sub-band corresponds to one reference value.

[0308] In some embodiments, the number of second difference values ​​is related to the number of other subbands B and the number of second reference values ​​R2, where B and R2 are positive integers.

[0309] In some embodiments, if the number of second reference values ​​R1 is equal to 1, then the number of first difference values ​​is equal to the number of other subbands B.

[0310] In some embodiments, if the number of second reference values ​​R1 is equal to 1 and the number of other subbands B is equal to 1, then the number of second difference values ​​is equal to 1.

[0311] In some embodiments, if the number of second reference values ​​R1 is equal to 1 and the number of other subbands B is greater than 1, then the number of second difference values ​​is greater than 1 and equal to B.

[0312] In some embodiments, if the number of other subbands B is equal to 1, then the number of second difference values ​​is equal to the number of second reference values ​​R2.

[0313] In some embodiments, if the number of other subbands B is equal to 1 and the number of second reference values ​​R2 is equal to 1, then the number of second difference values ​​is equal to 1.

[0314] In some embodiments, if the number of other subbands B is equal to 1 and the number of second reference values ​​R2 is greater than 1, then the number of second difference values ​​is greater than 1 and equal to R2.

[0315] In some embodiments, if the terminal reports a second performance index value that is an SGCS value corresponding to multiple sub-bands, the SGCS value corresponding to the first sub-band is defined as the second reference value, and the difference between the SGCS values ​​corresponding to other sub-bands and the second reference value is defined as the second difference value. That is, the second difference value is obtained by performing a difference operation between the SGCS values ​​corresponding to other sub-bands and the second reference value.

[0316] In some embodiments, the first subband can be any one of a plurality of subbands.

[0317] In some embodiments, the first subband includes at least one of the following:

[0318] (1) Subband indicated by network device.

[0319] (2) The terminal and the network device negotiate N predefined subbands, where the value of N is equal to the total number of subbands configured by the network device. For example, the predefined subbands are those with the smallest or largest subband index.

[0320] (3) The terminal passes The subband indicated by the bit, where the value of S is predefined or configured by the network device. The value of S represents the number of subbands.

[0321] In some embodiments, the value of S can be equal to the value of N.

[0322] In some embodiments, the value of S is equal to the value of N, and the network device does not need to configure the first subband.

[0323] In some embodiments, the first value is a third performance index value, which includes at least a portion of the second performance index values ​​corresponding to time units. Thus, the terminal can report the quantization information of the first value according to time units.

[0324] In some embodiments, the third performance metric value includes at least one of the following:

[0325] (1) The second performance index value corresponding to each time unit.

[0326] (2) The second performance index values ​​corresponding to each of the time units.

[0327] (3) The average value of the second performance index corresponding to all time units.

[0328] In some embodiments, the time unit can be a moment, a time period, a duration, etc.

[0329] In some embodiments, each or all of the time units described above may be as agreed upon in the protocol.

[0330] In some embodiments, the aforementioned time units may be indicated by network devices or reported by terminals.

[0331] In some embodiments, the third performance metric value includes a third reference value and one or more third difference values.

[0332] The third reference value is the first value corresponding to the first time unit among multiple time units, and the third difference value is the difference between the first value corresponding to other times besides the first time unit among multiple time units and the third reference value.

[0333] In some embodiments, the third reference value may include one or more reference values. For example, one reference value may correspond to each time unit.

[0334] In some embodiments, the number of third difference values ​​is related to the number of other time units T and the number of third reference values ​​R3, where T and R3 are positive integers.

[0335] In some embodiments, if the number of third reference values ​​R3 is equal to 1, then the number of third difference values ​​is equal to the number of other time units L3.

[0336] In some embodiments, the number of third reference values ​​R3 is equal to 1, the number of other time units L3 is equal to 1, and the number of third difference values ​​is equal to 1.

[0337] In some embodiments, if the number of third reference values ​​R3 is equal to 1 and the number of other time units L3 is greater than 1, then the number of third difference values ​​is greater than 1 and equal to L3.

[0338] In some embodiments, if the number of other time units T is equal to 1, then the number of third difference values ​​is equal to the number of third reference values ​​R3.

[0339] In some embodiments, if the number of other time units T is equal to 1 and the number of third reference values ​​R3 is equal to 1, then the number of third difference values ​​is equal to 1.

[0340] In some embodiments, if the number of other time units T is equal to 1 and the number of third reference values ​​R3 is greater than 1, then the number of third difference values ​​is greater than 1 and equal to R3.

[0341] In some embodiments, if the terminal reports a third performance index value that is an SGCS value corresponding to multiple time units, the SGCS value corresponding to the first time unit is defined as the third reference value, and the difference between the SGCS value corresponding to other time units and the third reference value is defined as the third difference value. That is, the third difference value is obtained by performing a difference operation between the SGCS value corresponding to other time units and the third reference value.

[0342] In some embodiments, the first time unit can be any one of a plurality of sub-bands.

[0343] In some embodiments, the first time unit includes at least one of the following:

[0344] (1) Time unit indicated by network device.

[0345] (2) The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured in the network device. For example, all time units or the first time unit in a selected subset of time units.

[0346] (3) The terminal passes The time unit indicated by the bit, where the value of K is predefined or configured by the network device. The value of K represents the number of time units.

[0347] In some embodiments, the value of K is equal to N4, where N4 is a parameter configured in the network device.

[0348] In some embodiments, if the value of K is equal to N4, then no network device configuration instruction is required.

[0349] In some embodiments, the first value is at least one of a first performance index value, a second performance index value, and a third performance index value.

[0350] In some embodiments, the first SGCS value may be a first performance metric value, a second performance metric value, or a third performance metric value.

[0351] In some embodiments, the first SGCS value can be any combination of the first performance index value, the second performance index value, and the third performance index value.

[0352] In some embodiments, the second SGCS value may be a first performance metric value, a second performance metric value, or a third performance metric value.

[0353] In some embodiments, the second SGCS value can be any combination of the first performance index value, the second performance index value, and the third performance index value.

[0354] In some embodiments, the third SGCS value may be a first performance metric value, a second performance metric value, or a third performance metric value.

[0355] In some embodiments, the third SGCS value can be any combination of the first performance index value, the second performance index value, and the third performance index value.

[0356] In step S2102, terminal 101 determines the quantization information of the first value.

[0357] In some embodiments, the terminal can quantize the first value to obtain quantized information of the first value.

[0358] In some embodiments, the quantization information of the first value is obtained using at least one of the following:

[0359] (1) The first value is the performance index value, which is quantized by x bits, where x is a positive integer.

[0360] In some embodiments, the first performance metric value is quantized using x bits.

[0361] In some embodiments, the second performance metric value is quantized using x bits.

[0362] In some embodiments, the third performance metric value is quantized using x bits.

[0363] (2) The first value includes a reference value and a difference value. The reference value is quantized by a bits and the difference value is quantized by b bits. a and b are positive integers.

[0364] In some embodiments, for the first reference value and the first difference value in the first performance index value, the first reference value is quantized by a bits and the first difference value is quantized by b bits.

[0365] In some embodiments, for the second reference value and the second difference value in the second performance index value, the second reference value is quantized by a bits and the second difference value is quantized by b bits.

[0366] In some embodiments, for the third reference value and the third difference value in the third performance index value, the third reference value is quantized by a bits and the third difference value is quantized by b bits.

[0367] Based on the above method, the terminal can determine the quantization information of the first value, thereby enabling the reporting of the quantization information of the first value.

[0368] In step S2103, terminal 101 sends a first report to network device 102, the first report including quantization information of the first value.

[0369] In some embodiments, network device 102 receives a first report sent by terminal 101, but is not limited thereto. Network device 102 may also receive a first report sent by other communication devices, in which case step S2103 may be omitted.

[0370] In some embodiments, network device 102 obtains a first report as defined by the protocol, in which case step S2103 may be omitted.

[0371] In some embodiments, network device 102 obtains a first report from upper layer(s), in which case step S2103 can be omitted.

[0372] In some embodiments, the network device 102 processes the data to obtain a first report, in which case step S2103 may be omitted.

[0373] In some embodiments, the network device 102 autonomously implements the function indicated by the first report, or the above function is a default or default value, in which case step S2103 can be omitted.

[0374] In some embodiments, terminal 101 sends a first report, which includes quantification information of a first value. Optionally, network device 102 receives the first report. The first report may be, for example, a performance monitoring information report, but is not limited thereto; it may also be a performance monitoring information upload, etc.

[0375] In some embodiments, the network device can determine the performance of the first model based on the quantification information of the first value. Thus, by combining the device type and the model's purpose, the network device can execute related strategies such as model tuning and optimization, resource scheduling and load balancing, anomaly detection and contextualization, and model information sharing, thereby improving network reliability, efficiency, and quality of service.

[0376] In some embodiments, the name of the first report is not limited, and it may be, for example, performance monitoring information reporting or performance monitoring information report.

[0377] In some embodiments, the first report may be carried on a medium access control-control element (MAC-CE) or radio resource control (RRC) signaling.

[0378] In some embodiments, the name of the quantification information of the first value is not limited, and it may be, for example, performance monitoring information, monitoring information, or model performance monitoring information.

[0379] In some embodiments, at least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

[0380] In some embodiments, the first reporting unit is, for example, one CSI part, which includes a part. That is, the indication information is reported by one CSI part.

[0381] In some embodiments, the second reporting unit is, for example, reported by two CSI parts, which include two parts, part 1 and part 2. That is, the indication information is reported by the two CSI parts. The indication information can be placed in part 1 and part 2.

[0382] In some embodiments, the relevant information of the first value may be at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, such as the first transmission layer, the first sub-band, and the first time unit. Based on this, the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value.

[0383] In some embodiments, the relevant information for the first value may be a performance metric value, such as a first performance metric value, a second performance metric value, and a third performance metric value. Based on this, the indication information is used to indicate the performance metric value.

[0384] In some embodiments, the relevant information for the first value may include a reference value and a difference value, such as a first reference value and a first difference value, a second reference value and a second difference value, and a third reference value and a third difference value. Based on this, indication information is used to indicate the reference value and the difference value.

[0385] In some embodiments, the indication information related to the first value is reported by at least one of the first reporting unit and the second reporting unit.

[0386] In some embodiments, the first reporting unit includes indication information of a reference value, and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value. The second reporting unit includes indication information of a differential value;

[0387] In some embodiments, indication information for the first reference value, the second reference value, and the third reference value, and / or indication information for the first transmission layer, the first sub-band, and the first time unit, are reported in part 1. Indication information for the first differential value, the second differential value, and the third differential value are reported in part 2.

[0388] In some embodiments, the second reporting unit includes indication information for a reference value, indication information for indicating at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information for a differential value.

[0389] In some embodiments, the indication information of the first reference value, the second reference value, and the third reference value, the indication information of the first transmission layer, the first sub-band, and the first time unit, and the indication information of the first differential value, the second differential value, and the third differential value are reported in part 2.

[0390] In some embodiments, the terminal may periodically report indication information to the network device.

[0391] In some embodiments, the terminal may send semi-persistent reporting indication information to the network device.

[0392] In some embodiments, the terminal may periodically report indication information to the network device.

[0393] In some embodiments, the indication information is carried on physical uplink control channel (PUCCH) resources or physical uplink shared channel (PUSCH) resources.

[0394] In some embodiments, the terminal reports the indication information to the network device on the PUCCH or PUSCH resource.

[0395] In some embodiments, the channel state information reference resource corresponding to the quantization information of the first value is determined based on at least one of the following:

[0396] (1) The time when the channel state information based on the first model inference is sent, that is, the time when the channel state information based on the first model inference is reported, such as the time when the CSI based on the first model inference is reported.

[0397] (2) A second time unit for sending the first report, wherein the second time unit is predefined or indicated by the network device configuration. For example, the second time unit is the reporting time of the first report.

[0398] In some embodiments, if the second time unit is predefined, then the channel state information reference resource corresponding to the quantization information of the first value can be determined according to the time of transmitting the channel state information based on the first model inference.

[0399] For example, the channel state information reference resource corresponding to the quantization information of the first value is transmitted before the time when the channel state information based on the first model inference is transmitted. Alternatively, the channel state information reference resource corresponding to the quantization information of the first value is transmitted after the time when the channel state information based on the first model inference is transmitted.

[0400] In some embodiments, the channel state information reference resource corresponding to the quantization information of the first value can be determined according to the second time unit.

[0401] For example, the channel state information reference resource corresponding to the quantization information of the first value is located in the time unit of the prediction window.

[0402] In some embodiments, the channel state information reference resource corresponding to the quantization information of the first value can be determined based on the time of transmission of the channel state information based on the first model inference and the second time unit.

[0403] The channel state information reference resource corresponding to the quantization information of the first value is transmitted after the time when the channel state information based on the inference of the first model is sent.

[0404] like Figure 2B As shown, assume n I n represents the reporting time of CSI based on the first model inference. M This indicates the reporting time of the first report. Therefore, the CSI reference resource (CSI reference resource for performance monitoring reporting) corresponding to the quantitative information of the first value is... Figure 2B The moment indicated by the middle arrow.

[0405] Using the above method, the terminal can quantize and report model performance monitoring information according to at least one of the transmission layer, frequency granularity, and time unit, thereby realizing the terminal's quantitative indication and reporting of model performance monitoring information. This can obtain reliable model monitoring performance information while reducing terminal feedback overhead and ensuring the quantification accuracy of performance detection information.

[0406] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0407] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" can be used interchangeably. For example, a codebook can be a collection of one or more codewords / precoding matrices.

[0408] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".

[0409] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”

[0410] In some embodiments, the terms "precoding", "precoder", "weight", "precoding weight", "quasi-co-location (QCL)", "transmission configuration indication (TCI) status", "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "the number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angular degree", "antenna", "antenna element", and "panel" can be used interchangeably.

[0411] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0412] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transmit,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0413] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0414] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0415] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data and / or instructions received; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the receiver to respond to the sent content.

[0416] In some embodiments, if an arrow in the interaction diagram representing the sending of information, signaling, etc. from one subject to another passes through other subjects, it can be interpreted as the information being forwarded from one subject to another via other subjects, or it can be interpreted as the information being sent from one subject to another without passing through other subjects.

[0417] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2103. For example, steps S2101+S2103 may be implemented as independent embodiments, and steps S2101+S2102+S2103 may be implemented as independent embodiments, but are not limited thereto.

[0418] In some embodiments, step S2102 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0419] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0420] Figure 2C This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 2CAs shown, the embodiments of this disclosure relate to a communication method, which includes:

[0421] In step S2201, terminal 101 determines a first value according to at least one of the transmission layer, frequency granularity, and time unit.

[0422] The optional implementation of step S2201 can be found in [reference]. Figure 2A Optional implementation methods of step S2101, and Figure 2A Other related parts in the embodiments involved will not be described in detail here.

[0423] In step S2202, terminal 101 determines the quantization information of the first value.

[0424] The optional implementation of step S2202 can be found in [reference]. Figure 2A Optional implementation methods of step S2102, and Figure 2A Other related parts in the embodiments involved will not be described in detail here.

[0425] In some embodiments, if the channel state information associated with the quantization information of the first value and the inference based on the first model is not updated, the terminal may determine that the first model is not working properly or the first model cannot use inference, for example, because the terminal's central processing unit (CPU) and / or accelerated processing unit (APU) is fully occupied, causing the first model to not work properly or the first model to be unable to use inference.

[0426] In some embodiments, the first report may be submitted without being submitted, i.e., the terminal may execute step S2203. This reduces feedback overhead.

[0427] In some embodiments, the first report can be submitted as a historical first report, i.e., the terminal can submit the report in step S2204. This ensures continuous feedback.

[0428] In some embodiments, the channel state information based on the first model inference can be CSI based on the first model inference, such as PMI, channel quality indication (CQI), rank indication (RI), and other parameters.

[0429] In some embodiments, the terminal may determine whether the channel state information based on the first model inference associated with the quantization information of the first value has not been updated.

[0430] In some embodiments, the terminal may determine whether the indication information has not been updated, wherein the channel state information based on the first model inference associated with the quantization information of the first value is associated with the indication information.

[0431] In some embodiments, the name of the instruction information is not limited, and it may be, for example, a first instruction or identification information or a first identification, etc.

[0432] In some embodiments, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, the indication information is the first value. If the channel state information based on the first model inference associated with the quantization information of the first value is updated, the indication information is the second value. Thus, the terminal can determine the change in the indication information to ascertain whether the channel state information based on the first model inference associated with the quantization information of the first value has not been updated.

[0433] The first and second values ​​can be Boolean values, or they can be binary values.

[0434] In some embodiments, the terminal may be based on the terminal implementation and may choose to execute either step S2203 or step S2204.

[0435] In some embodiments, the terminal may choose to execute either step S2203 or step S2204 based on the protocol agreement.

[0436] In some embodiments, the terminal may perform either step S2203 or step S2204 based on the instructions of the network device.

[0437] In step S2203, the channel state information based on the first model inference associated with the quantization information of the first value has not been updated, and terminal 101 does not expect to send the first report to the network device.

[0438] In some embodiments, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, the terminal 101 does not expect to send the first report to the network device. That is, the terminal 101 does not send the first report to the network device because the channel state information based on the first model inference associated with the quantization information of the first value has not been updated, the quantization information of the first value has not changed, and the terminal does not need to repeatedly report the quantization information of the first value. Thus, feedback overhead is saved.

[0439] In some embodiments, the channel state information based on the first model inference associated with the quantization information of the first value is not updated. The network device 102 does not expect to receive the first report sent by the terminal; that is, the network device 102 does not receive the first report sent by the terminal because the terminal does not repeatedly report the quantization information of the first value. The network device does not need to determine the performance of the first model again based on the quantization information of the first value, and does not need to execute related strategies such as model adjustment and optimization, resource scheduling and load balancing, anomaly detection and context, and model information sharing. Therefore, feedback overhead is saved, processing frequency is reduced, and the ability to handle other services is improved.

[0440] In some embodiments, the terminal performs the following operations:

[0441] The channel state information based on the first model inference associated with the quantization information of the first value has not been updated, and terminal 101 does not expect to send the first report to the network device.

[0442] Alternatively, the terminal 101 sends a first report to the network device based on the channel state information update associated with the quantization information of the first value and the reasoning of the first model.

[0443] In some embodiments, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, the terminal 101 does not expect to send the first report to the network device.

[0444] Optionally, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, terminal 101 does not expect to send a first report to the network device. Optionally, in response to the channel state information based on the first model inference associated with the quantization information of the first value not being updated, terminal 101 does not expect to send a first report to the network device. Optionally, when the channel state information based on the first model inference associated with the quantization information of the first value is not updated, terminal 101 does not expect to send a first report to the network device. Thus, there is no need to repeatedly feed back model performance monitoring information, saving feedback instructions.

[0445] In some embodiments, the terminal 101 sends a first report to the network device when the channel state information based on the first model inference, associated with the quantization information of the first value, is updated.

[0446] Optionally, upon an update of the channel state information based on the first model inference associated with the quantization information of the first value, terminal 101 sends a first report to the network device. Optionally, in response to an update of the channel state information based on the first model inference associated with the quantization information of the first value, terminal 101 sends a first report to the network device. Optionally, when the channel state information based on the first model inference associated with the quantization information of the first value is updated, terminal 101 sends a first report to the network device. This avoids redundant feedback of model performance monitoring information and ensures timely feedback of the latest performance monitoring information.

[0447] In an optional embodiment, a determination step is further included, in which the terminal determines whether the channel state information based on the first model inference associated with the quantization information of the first value has not been updated or the channel state information based on the first model inference associated with the quantization information of the first value has been updated.

[0448] In step S2204, the channel state information associated with the quantization information of the first value based on the first model inference has not been updated. The terminal 101 sends a first report to the network device. The first report includes the quantization information of the first value associated with the unupdated channel state information based on the first model inference.

[0449] In some embodiments, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, the terminal 101 sends a first report to the network device, that is, the first report is a historical first report.

[0450] In some embodiments, the terminal may perform the following operations:

[0451] The channel state information based on the first model inference associated with the quantization information of the first value has not been updated, and the terminal 101 sends the historical first report to the network device.

[0452] Alternatively, the terminal 101 sends the latest first report to the network device, which is associated with the quantization information of the first value and the channel state information based on the first model inference.

[0453] In some embodiments, the channel state information based on the first model inference associated with the quantization information of the first value is not updated, and the network device 102 receives the first report sent by the terminal, that is, the first report is a historical first report.

[0454] In some embodiments, the first historical report includes quantized information of a first value associated with unupdated channel state information based on the first model inference.

[0455] In some embodiments, the first historical report may be the first report submitted previously.

[0456] Optionally, if the channel state information based on the first model inference associated with the quantization information of the first value is not updated, terminal 101 sends a historical first report to the network device. Optionally, in response to the channel state information based on the first model inference associated with the quantization information of the first value not being updated, terminal 101 sends a historical first report to the network device. Optionally, when the channel state information based on the first model inference associated with the quantization information of the first value is not updated, terminal 101 sends a historical first report to the network device. This ensures real-time feedback of model performance monitoring information.

[0457] In some embodiments, the channel state information associated with the quantization information of the first value, based on the reasoning of the first model, is updated, and the terminal 101 sends the latest first report to the network device.

[0458] In some embodiments, the latest first report is obtained based on updated channel state information inferred from the first model.

[0459] Optionally, if the channel state information based on the first model inference associated with the quantization information of the first value is updated, the execution terminal 101 sends the latest first report to the network device. Optionally, in response to an update of the channel state information based on the first model inference associated with the quantization information of the first value, the terminal 101 sends the latest first report to the network device. Optionally, when the channel state information based on the first model inference associated with the quantization information of the first value is updated, the execution terminal 101 sends the latest first report to the network device. This avoids redundant feedback of model performance monitoring information and ensures timely feedback of the latest performance monitoring information.

[0460] In an optional embodiment, a determination step is further included, in which the terminal determines whether the channel state information based on the first model inference associated with the quantization information of the first value has not been updated or the channel state information based on the first model inference associated with the quantization information of the first value has been updated.

[0461] Using the above method, when the channel state information based on model inference is not updated, the model's performance monitoring information does not need to be reported, which can reduce the feedback overhead of performance monitoring information.

[0462] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2204. For example, step S2203 may be implemented as a standalone embodiment, step S2201+S2203 may be implemented as a standalone embodiment, step S2201+S2202+S2203 may be implemented as a standalone embodiment, step S2201+S2204 may be implemented as a standalone embodiment, and step S2201+S2202+S2204 may be implemented as a standalone embodiment, but is not limited thereto.

[0463] In some embodiments, step S2202 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0464] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0465] Based on the above description, determining the first value, such as the first performance indicator value, the second performance indicator value, and the third performance indicator value, requires knowledge of the channel state information inferred from the first model. Therefore, a performance monitoring information report needs to be associated with a corresponding channel state information report inferred from the first model. In other words, the configuration information of a first report needs to be associated with the configuration information of a second report corresponding to the channel state information inferred from the first model.

[0466] Below, in conjunction with Figure 2D The process of determining the first value by combining the first report and the second report is described in detail.

[0467] Figure 2D This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 2D As shown, the embodiments of this disclosure relate to a communication method, which includes:

[0468] In step S2301, network device 102 sends first configuration information to terminal 101. The first configuration information is used to send a second report corresponding to the channel state information based on the first model inference.

[0469] In some embodiments, terminal 101 receives first configuration information sent by network device 102, but is not limited thereto. Terminal 101 may also receive first configuration information sent by other communication devices, in which case step S2301 can be omitted.

[0470] In some embodiments, terminal 101 obtains the first configuration information specified by the protocol, in which case step S2301 can be omitted.

[0471] In some embodiments, the terminal 101 obtains the first configuration information from the upper layer(s), in which case step S2301 can be omitted.

[0472] In some embodiments, the terminal 101 processes the information to obtain the first configuration information, and step S2301 can be omitted.

[0473] In some embodiments, the terminal 101 autonomously implements the function indicated by the first configuration information, or the above function is a default or default value, in which case step S2301 can be omitted.

[0474] In some embodiments, network device 102 sends a report configuration, which includes first configuration information. Optionally, terminal 101 receives the first configuration information.

[0475] In some embodiments, the first configuration information may be carried in a medium access control-control element (MAC-CE) or radio resource control (RRC) signaling.

[0476] In some embodiments, the first configuration information is the configuration information for the second report, enabling the terminal to send the second report to the network device based on the first configuration information.

[0477] In step S2302, network device 102 sends second configuration information to terminal 101. The second configuration information is used to send the first report, and the first configuration information is associated with the second configuration information.

[0478] In some embodiments, terminal 101 receives second configuration information sent by network device 102, but is not limited thereto. Terminal 101 may also receive second configuration information sent by other communication devices, in which case step S2302 may be omitted.

[0479] In some embodiments, terminal 101 obtains the second configuration information specified by the protocol, in which case step S2302 can be omitted.

[0480] In some embodiments, the terminal 101 obtains the second configuration information from the upper layer(s), in which case step S2302 can be omitted.

[0481] In some embodiments, the terminal 101 processes the information to obtain the second configuration information, in which case step S2302 can be omitted.

[0482] In some embodiments, the terminal 101 autonomously implements the function indicated by the second configuration information, or the above function is a default or default value, in which case step S2302 can be omitted.

[0483] In some embodiments, network device 102 sends a report configuration, which includes second configuration information. Optionally, terminal 101 receives the second configuration information.

[0484] In some embodiments, the second configuration information may be carried in a medium access control-control element (MAC-CE) or radio resource control (RRC) signaling.

[0485] In some embodiments, the second configuration information is the configuration information of the first report, enabling the terminal to send the first report to the network device based on the second configuration information.

[0486] In some embodiments, the first configuration information is associated with the second configuration information.

[0487] In some embodiments, the first configuration information is associated with the second configuration information, including:

[0488] The first configuration information includes indication information used to identify the second report;

[0489] The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

[0490] In some embodiments, it is assumed that the indication information used to identify the second report is ID2, and the indication information used to identify the first report is ID1. Then, the first configuration information includes ID2. The second configuration information includes both ID1 and ID2.

[0491] For example, NW is configured with CSI reporting for model inference and CSI reporting for performance monitoring information. Both of these CSI reporting systems have corresponding reporting IDs. The CSI reporting ID for model inference is also configured in the CSI reporting for performance monitoring.

[0492] In step S2303, terminal 101 determines the channel state information based on the first model inference according to the second configuration information.

[0493] In some embodiments, the terminal can determine channel state information based on the first model inference according to the association between the first configuration information and the second configuration information.

[0494] In step S2304, terminal 101 determines the first value based on the channel state information inferred from the first model.

[0495] For optional implementations of step S2304, please refer to [link / reference]. Figure 2A Step S2101, Figure 2C Optional implementation methods of step S2201, and Figure 2A , Figure 2COther related parts in the embodiments involved will not be described in detail here.

[0496] Using the above method, the terminal can determine the channel state information based on the first model inference according to the association relationship configured in the network device, thereby obtaining the first value.

[0497] The communication method involved in the embodiments of this disclosure may include at least one of steps S2301 to S2304. For example, steps S2302+S2303+S2304 may be implemented as independent embodiments, but are not limited thereto.

[0498] In some embodiments, steps S2301 and S2302 may be performed in an alternate order or simultaneously.

[0499] In some embodiments, step S2301 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0500] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0501] This disclosure relates to a communication method, which includes:

[0502] In step S3101, the terminal determines the first value according to at least one of the following: transmission layer, frequency granularity, and time unit.

[0503] The optional implementation of step S3101 can be found in [reference]. Figure 2A Step S2101, Figure 2C Optional implementation methods of step S2201, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0504] In step S3102, the terminal sends a first report to the network device, the first report including quantification information of the first value.

[0505] The optional implementation of step S3102 can be found in [reference]. Figure 2A Step S2103, Figure 2C Optional implementation methods of step S2201, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0506] In some embodiments, the first value is obtained based on at least one of the following:

[0507] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model;

[0508] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model.

[0509] The statistical value of the first value within the first window.

[0510] In some embodiments, the first value is at least one of a first performance index value, a second performance index value, and a third performance index value;

[0511] The first performance index value includes at least a portion of the first value corresponding to the transport layer, the second performance index value includes at least a portion of the first performance index value corresponding to the sub-band, and the third performance index value includes at least a portion of the second performance index value corresponding to the time unit.

[0512] In some embodiments, the first performance metric value includes at least one of the following:

[0513] The first value corresponding to each transport layer;

[0514] The first value corresponding to the i-th transport layer, where i is a positive integer;

[0515] The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal; and / or

[0516] The second performance index value includes at least one of the following:

[0517] The first performance index value corresponding to the entire broadband;

[0518] The first performance index value corresponding to each sub-band;

[0519] The average value of the first performance index corresponding to a portion of the sub-band;

[0520] The average of the first performance index values ​​corresponding to all sub-bands; and / or

[0521] The third performance index value includes at least one of the following:

[0522] The second performance index value corresponding to each time unit;

[0523] The second performance index values ​​corresponding to each of the time units;

[0524] The average value of the second performance index corresponding to all time units.

[0525] In some embodiments, the first performance index value includes a first reference value and one or more first difference values, wherein the first reference value is a first value corresponding to a first transport layer among a plurality of transport layers, and the first difference value is the difference between the first value corresponding to the other transport layers (excluding the first transport layer) and the first reference value; and / or

[0526] The second performance index value includes a second reference value and one or more second difference values. The second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands. The second difference value is the difference between the first value corresponding to other sub-bands (excluding the first sub-band) and the second reference value; and / or

[0527] The third performance index value includes a third reference value and one or more third difference values. The third reference value is a first value corresponding to a first time unit among a plurality of time units. The third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

[0528] In some embodiments, the first transport layer includes at least one of the following:

[0529] The network device indicates the transport layer;

[0530] The terminal and the network device negotiate a predefined transport layer;

[0531] The terminal via The transport layer indicated by the bit, where the value of U is predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal; and / or

[0532] The first sub-band includes at least one of the following:

[0533] The subband indicated by the network device;

[0534] The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device;

[0535] The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device; and / or

[0536] The first time unit includes at least one of the following:

[0537] The time unit indicated by the network device;

[0538] The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device;

[0539] The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

[0540] In some embodiments, the quantization information of the first value is obtained using at least one of the following:

[0541] The first value is a performance index value, which is quantized by x bits, where x is a positive integer;

[0542] The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

[0543] In some embodiments, at least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

[0544] In some embodiments, the relevant information of the first value is at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value.

[0545] The relevant information for the first value is a performance index value, and the indication information is used to indicate the performance index value;

[0546] The relevant information for the first value includes a reference value and a difference value, and the indication information is used to indicate the reference value and the difference value.

[0547] In some embodiments, the first reporting unit includes indication information of a reference value and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the second reporting unit includes indication information of a differential value.

[0548] Alternatively, the second reporting unit may include indication information of a reference value, indication information of at least one of the following: the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information of a differential value.

[0549] In some embodiments, the indication information is carried on physical uplink control channel resources or physical uplink shared channel resources.

[0550] In some embodiments, determining the first value includes:

[0551] The channel state information based on the first model inference is determined according to the second configuration information. The second configuration information is associated with the first configuration information. The first configuration information is used to send a second report corresponding to the channel state information based on the first model inference. The second configuration information is used to send the first report.

[0552] The first value is determined based on the channel state information inferred from the first model.

[0553] In some embodiments, the terminal further includes:

[0554] Receive the second configuration information sent by the network device.

[0555] In some embodiments, the first configuration information is associated with the second configuration information, including:

[0556] The first configuration information includes indication information for identifying the second report;

[0557] The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

[0558] In some embodiments, the channel state information based on the first model inference associated with the quantization information of the first value is not updated;

[0559] Sending the first report to the network device includes: sending the first report to the network device, wherein the first report is used to indicate quantization information of the first value that has not been updated.

[0560] In some embodiments, the channel state information reference resource corresponding to the quantization information of the first value is determined based on at least one of the following:

[0561] The time when channel state information based on the inference from the first model is transmitted;

[0562] A second time unit is used to send the first report, the second time unit being predefined or indicated by the network device configuration.

[0563] For alternative implementation methods of the above content, please refer to Figure 2A , Figure 2B , Figure 2C , Figure 2D Other related parts in the embodiments involved will not be described in detail here.

[0564] The communication method involved in the embodiments of this disclosure may include at least one of steps S3101 to S3102. For example, steps S3101 and S3102 may be implemented as independent embodiments.

[0565] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0566] This disclosure relates to a communication method, which includes:

[0567] In step S3201, the channel state information based on the first model inference associated with the quantization information of the first value has not been updated, and the terminal 101 does not expect to send the first report to the network device.

[0568] The optional implementation of step S3201 can be found in [reference]. Figure 2C Optional implementation methods of step S2203, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0569] In some embodiments, the terminal may further include:

[0570] A first value is determined based on at least one of the following: transport layer, frequency granularity, and time unit. This first value is used to determine the performance of the first model.

[0571] For alternative implementation methods of the above content, please refer to Figure 2A Step S2101, Figure 2C Optional implementation methods of step S2201, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0572] In some embodiments, the terminal may further include:

[0573] Determine the quantification information for the first value.

[0574] For alternative implementation methods of the above content, please refer to Figure 2A Step S2102, Figure 2C Optional implementation methods of step S2202, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0575] In some embodiments, the terminal may further include:

[0576] The channel state information based on the first model inference, which is associated with the quantization information that determines the first value, has not been updated.

[0577] For alternative implementation methods of the above content, please refer to Figure 2COptional implementation methods of step S2203, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0578] In some embodiments, the terminal may further include:

[0579] It is determined that the indication information has not been updated, and the indication information is associated with the channel state information based on the first model inference, which is related to the quantization information of the first value.

[0580] For alternative implementation methods of the above content, please refer to Figure 2C Optional implementation methods of step S2203, and Figure 2A , Figure 2B , Figure 2C Other related parts in the embodiments involved will not be described in detail here.

[0581] In some embodiments, the first value is obtained based on at least one of the following:

[0582] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model;

[0583] The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model.

[0584] The statistical value of the first value within the first window.

[0585] In some embodiments, the first value is at least one of a first performance index value, a second performance index value, and a third performance index value;

[0586] The first performance index value includes at least a portion of the first value corresponding to the transport layer, the second performance index value includes at least a portion of the first performance index value corresponding to the sub-band, and the third performance index value includes at least a portion of the second performance index value corresponding to the time unit.

[0587] In some embodiments, the first performance metric value includes at least one of the following:

[0588] The first value corresponding to each transport layer;

[0589] The first value corresponding to the i-th transport layer, where i is a positive integer;

[0590] The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal; and / or

[0591] The second performance index value includes at least one of the following:

[0592] The first performance index value corresponding to the entire broadband;

[0593] The first performance index value corresponding to each sub-band;

[0594] The average value of the first performance index corresponding to a portion of the sub-band;

[0595] The average of the first performance index values ​​corresponding to all sub-bands; and / or

[0596] The third performance index value includes at least one of the following:

[0597] The second performance index value corresponding to each time unit;

[0598] The second performance index values ​​corresponding to each of the time units;

[0599] The average value of the second performance index corresponding to all time units.

[0600] In some embodiments, the first performance index value includes a first reference value and one or more first difference values, wherein the first reference value is a first value corresponding to a first transport layer among a plurality of transport layers, and the first difference value is the difference between the first value corresponding to the other transport layers (excluding the first transport layer) and the first reference value; and / or

[0601] The second performance index value includes a second reference value and one or more second difference values. The second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands. The second difference value is the difference between the first value corresponding to other sub-bands (excluding the first sub-band) and the second reference value; and / or

[0602] The third performance index value includes a third reference value and one or more third difference values. The third reference value is a first value corresponding to a first time unit among a plurality of time units. The third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

[0603] In some embodiments, the first transport layer includes at least one of the following:

[0604] The network device indicates the transport layer;

[0605] The terminal and the network device negotiate a predefined transport layer;

[0606] The terminal via The transport layer indicated by the bit, where the value of U is predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal; and / or

[0607] The first sub-band includes at least one of the following:

[0608] The subband indicated by the network device;

[0609] The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device;

[0610] The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device; and / or

[0611] The first time unit includes at least one of the following:

[0612] The time unit indicated by the network device;

[0613] The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device;

[0614] The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

[0615] In some embodiments, the quantization information of the first value is obtained using at least one of the following:

[0616] The first value is a performance index value, which is quantized by x bits, where x is a positive integer;

[0617] The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

[0618] In some embodiments, at least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

[0619] In some embodiments, the relevant information of the first value is at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value.

[0620] The relevant information for the first value is a performance index value, and the indication information is used to indicate the performance index value;

[0621] The relevant information for the first value includes a reference value and a difference value, and the indication information is used to indicate the reference value and the difference value.

[0622] In some embodiments, the first reporting unit includes indication information of a reference value and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the second reporting unit includes indication information of a differential value.

[0623] Alternatively, the second reporting unit may include indication information of a reference value, indication information of at least one of the following: the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information of a differential value.

[0624] In some embodiments, the indication information is carried on physical uplink control channel resources or physical uplink shared channel resources.

[0625] In some embodiments, determining the first value includes:

[0626] The channel state information based on the first model inference is determined according to the second configuration information. The second configuration information is associated with the first configuration information. The first configuration information is used to send a second report corresponding to the channel state information based on the first model inference. The second configuration information is used to send the first report.

[0627] The first value is determined based on the channel state information inferred from the first model.

[0628] In some embodiments, the terminal further includes:

[0629] Receive the second configuration information sent by the network device.

[0630] In some embodiments, the first configuration information is associated with the second configuration information, including:

[0631] The first configuration information includes indication information for identifying the second report;

[0632] The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

[0633] In some embodiments, the channel state information reference resource corresponding to the quantization information of the first value is determined based on at least one of the following:

[0634] The time when channel state information based on the inference from the first model is transmitted;

[0635] A second time unit is used to send the first report, the second time unit being predefined or indicated by the network device configuration.

[0636] For alternative implementation methods of the above content, please refer to Figure 2A , Figure 2B , Figure 2C , Figure 2D Other related parts in the embodiments involved will not be described in detail here.

[0637] The communication method involved in the embodiments of this disclosure may include step S3201. For example, step S3201 may be implemented as a standalone embodiment.

[0638] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0639] Below, examples of quantization indication for the SGCS value calculated by the terminal and quantization indication for the reporting method are provided below, with reference to Examples 1 and 2. Example 1 illustrates the quantization indication, and Example 2 illustrates the reporting method.

[0640] Example 1

[0641] Assume that NW is configured with N=4 aperiodic channel measurement resources (CSI-RS) to measure channel information at historical times, and the transmission interval between two adjacent CSI-RS is M=4 slots. The UE infers the CSI at the next K=2 times based on the AI ​​model, and the interval between two adjacent CSI at the next time is D=4 slots.

[0642] To monitor the performance of the AI ​​model, the NW also configured two aperiodic CSI-RS resources to measure the ground truth CSI at two time points. The UE calculates the corresponding PMI based on the CSI obtained from AI model inference. The UE calculates the corresponding PMI based on the measured ground truth CSI.

[0643] Assuming the rank calculated by the UE is 2, then the PMI corresponding to the CSI calculated by the UE based on the AI ​​model inference is expressed as follows: and The PMI calculated based on the measured Ground Truth CSI is expressed as follows: and Then, according to the following formula:

[0644]

[0645] We can obtain the corresponding values ​​of these two layers. and and This is the first performance index value mentioned above.

[0646] Where n3 and n4 represent the n3rd sub-band and the predicted n4th time, respectively.

[0647] In the first quantification method and Each can be quantized using x = 4 bits, so the overhead for indicating the performance index value of a certain subband at a certain moment is 8 bits.

[0648] If differential quantization is used, i.e. The value is used as the first reference value, which is quantized by a = 4 bits, and then let... The first difference value can be obtained, and the first difference value is quantized by b = 2 bits. Therefore, the overhead for indicating the performance index value of a certain subband at a certain moment is 6 bits.

[0649] As can be seen, differential quantization can reduce the indication overhead by 2 bits compared with the first quantization method.

[0650] The second performance index value can be obtained by averaging the performance index values ​​of all sub-bands at a certain moment. and

[0651] The second performance index value can also be quantified using the two methods described above.

[0652] If the second reference value using differential quantization is SGCS 1，1 The second difference includes and

[0653] The performance index values ​​corresponding to time points K are reported separately. Using the first quantization method, a total of 4*4=16 bits are required. Using the differential quantization method, the total overhead is 4+2+2+2=10 bits.

[0654] As can be seen, differential quantization can save 6 bits of overhead compared to the first quantization method.

[0655] Where the second reference value corresponds to the performance index value at the first moment, it can be achieved through... The bit indicates the first moment.

[0656] Similarly, the third performance metric value can also be quantized using the two quantization methods described above and reported to the NW. Thus, the NW determines the performance of the AI ​​model based on the quantization information of the received first value.

[0657] Optionally, for the second or third SGCS value calculated above, their corresponding performance index values ​​can also be quantified in the above manner and reported to NW.

[0658] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0659] Example 2

[0660] The performance index values ​​calculated in Example 1 can be reported in the following two ways.

[0661] Method 1: Report it in one CSI part, i.e., report it in one CSI part.

[0662] The name of "one CSI part" is not limited; for example, it can be "one part CSI".

[0663] This method requires determining the Rank value. The Rank value can be determined either through a predefined parameter or through a high-level parameter of the configured Rank constraint in NW. With the Rank determined, the overhead of indicating the performance metric value is fixed, therefore the performance metric value can be reported in oneCSI part.

[0664] In addition, the performance index value is the average of the SGCS values ​​of all transport layers, so the overhead of indicating the performance index value is fixed and can also be reported in one CSI part.

[0665] It should be noted that for Method 1, the calculated performance index value does not depend on the number of sub-bands. That is, the average of the performance index values ​​corresponding to all sub-bands or some sub-bands is taken. The number of prediction times is fixed, or the average of the performance index values ​​corresponding to each time or some time times is taken.

[0666] Method 2: Report it in the two CSI parts.

[0667] The name of the two CSI part is not limited; for example, it can be called two part CSI.

[0668] In this approach, the length of information in part 2 depends on the indications in part 1. The indications in part 1 may include Rank values, the number of sub-bands, or the number of SGCS values ​​calculated for each time step. Part 2 includes indications of the transport layer, sub-bands, or SGCS values ​​for each time step. If the number of sub-bands or time steps is predefined, their indications may not be included in part 1.

[0669] The content reported using either Method 1 or Method 2 is carried in PUCCH or PUSCH and sent to NW.

[0670] Optionally, since the terminal's CPU and / or APU are fully utilized and cannot process CSI based on AI model inference, the associated CSI-based inference content will not be updated. That is, the PMI calculated by the AI ​​model-based inference CSI is the PMI corresponding to the previously reported inference CSI. In this case, the UE may not report the quantization information of the first value. Alternatively, the UE may still report the quantization information of the first value, and the first, second, and third performance index values ​​are calculated based on the unupdated predicted CSI.

[0671] In some embodiments, performance monitoring reports are associated with CSI reports based on AI model inference. The CSI report ID based on AI model inference is configured in the performance monitoring report.

[0672] In some embodiments, the CSI reference resource reported by performance monitoring is determined by the PMI at the second moment of the prediction window. Alternatively, the CSI reference resource reported by performance monitoring is predefined as the first moment within the prediction window.

[0673] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0674] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0675] 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 (CPU) 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.

[0676] 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 (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a 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), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0677] Figure 3A This is a schematic diagram of the structure of a terminal according to an embodiment of this disclosure. Terminal 101 is used to execute any of the above methods. In some embodiments, such as... Figure 3AAs shown, terminal 101 may include at least one of a transceiver module 3101, a processing module 3102, etc. In some embodiments, the processing module 3102 is used to determine a first value according to at least one of transport layer, frequency granularity, and time unit, the first value being used to determine the performance of a first model, and the transceiver module 3101 is used to send a first report to a network device, the first report including quantization information of the first value. Optionally, the transceiver module is used to perform at least one of the communication steps (e.g., steps S2103, S2203, S2204, S2301, S2302, but not limited thereto) performed by terminal 101 in any of the above methods, which will not be elaborated here. Optionally, the processing module is used to perform at least one of the other steps (e.g., steps S2101, S2102, S2201, S2202, S2303, S2304, but not limited thereto) performed by terminal 101 in any of the above methods, which will not be elaborated here.

[0678] Figure 3B This is a schematic diagram of the structure of a network device according to an embodiment of this disclosure. Network device 102 is used to perform any of the above methods. In some embodiments, such as... Figure 3B As shown, network device 102 may include at least one of a transceiver module 3201, a processing module 3202, etc. In some embodiments, the transceiver module 3201 is used to receive a first report sent by a terminal. The first report includes quantization information of a first value, which is determined by the terminal according to at least one of a transport layer, frequency granularity, and time unit. The first value is used to determine the performance of a first model. Optionally, the transceiver module is used to perform at least one of the communication steps (e.g., steps S2103, S2203, S2204, S2301, S2302, but not limited thereto) performed by network device 102 in any of the above methods. Optionally, the processing module is used to perform at least one of other steps (but not limited thereto) performed by network device 102 in any of the above methods.

[0679] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0680] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module.

[0681] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.

[0682] Figure 4A This is a schematic diagram of the structure of a communication device proposed in an embodiment of this disclosure. The communication device 4100 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 4100 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.

[0683] like Figure 4A As shown, the communication device 4100 is used to execute any of the above methods. In some embodiments, the communication device 4100 includes one or more processors 4101. The processor 4101 may be a general-purpose processor or a special-purpose processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may 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. Optionally, the communication device 4100 is used to execute any of the above methods. Optionally, one or more processors 4101 are used to invoke instructions to cause the communication device 4100 to execute any of the above methods.

[0684] In some embodiments, the communication device 4100 further includes one or more transceivers 4102. When the communication device 4100 includes one or more transceivers 4102, the transceiver 4102 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps S2103, S2203, S2204, S2301, S2302, but not limited thereto), and the processor 4101 performs at least one of other steps (e.g., steps S2101, S2102, S2201, S2202, S2303, S2304, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated together. Optionally, terms such as transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface can be used interchangeably; terms such as transmitter, transmitter unit, transmitter, and transmitter circuit can be used interchangeably; and terms such as receiver, receiver unit, receiver, and receiver circuit can be used interchangeably.

[0685] In some embodiments, the communication device 4100 further includes one or more memories 4103 for storing data and / or instructions. Optionally, one or more processors 4101 are used to invoke instructions stored in the memory 4103 to cause the communication device 4100 to perform any of the above methods. Optionally, all or part of the memory 4103 may also be located outside the communication device 4100. In an optional embodiment, the communication device 4100 may include one or more interface circuits 4104. Optionally, the interface circuit 4104 is connected to the memory 4103 and can be used to receive data and / or instructions from the memory 4103 or other devices, and can be used to send data and / or instructions to the memory 4103 or other devices. For example, the interface circuit 4104 can read data and / or instructions stored in the memory 4103 and send the data and / or instructions to the processor 4101.

[0686] The communication device 4100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 4100 described in this disclosure is not limited thereto, and the structure of the communication device 4100 may vary. Figure 4A The limitations. The communication device may be a standalone device or 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 including storage components for storing data, programs and / or instructions; (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.

[0687] Figure 4B This is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. For cases where the communication device 4100 can be a chip or a chip system, please refer to... Figure 4B The diagram shown is a schematic representation of the structure of chip 4200, but it is not limited to this.

[0688] Chip 4200 includes one or more processors 4201. Chip 4200 is used to perform any of the above methods.

[0689] In some embodiments, chip 4200 further includes one or more interface circuits 4202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 4200 further includes one or more memories 4203 for storing data and / or instructions. Optionally, all or part of the memories 4203 may be located outside of chip 4200. Optionally, the interface circuits 4202 are connected to the memories 4203, and the interface circuits 4202 can be used to receive data and / or instructions from the memories 4203 or other devices, and can be used to send data and / or instructions to the memories 4203 or other devices. For example, the interface circuits 4202 can read data and / or instructions stored in the memories 4203 and send the data and / or instructions to the processor 4201.

[0690] In some embodiments, the interface circuit 4202 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps S2103, S2203, S2204, S2301, S2302, but not limited thereto). The interface circuit 4202 performing the communication steps such as sending and / or receiving in the above-described method refers, for example, to the interface circuit 4202 performing data and / or instruction interaction between the processor 4201, the chip 4200, the memory 4203, or the transceiver device. In some embodiments, the processor 4201 performs at least one of other steps (e.g., steps S2101, S2102, S2201, S2202, S2303, S2304, but not limited thereto).

[0691] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0692] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device 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.

[0693] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0694] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

Claims

1. A communication method, characterized in that, The method, executed by a terminal, includes: A first value is determined according to at least one of transport layer, frequency granularity, and time unit, and the first value is used to determine the performance of the first model. A first report is sent to the network device, the first report including quantification information of the first value.

2. The method according to claim 1, characterized in that, The first value is obtained based on at least one of the following: The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model; The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model. The statistical value of the first value within the first window.

3. The method according to claim 1 or 2, characterized in that, The first value is at least one of the first performance index value, the second performance index value, and the third performance index value; The first performance index value includes at least a portion of the first value corresponding to the transport layer, the second performance index value includes at least a portion of the first performance index value corresponding to the sub-band, and the third performance index value includes at least a portion of the second performance index value corresponding to the time unit.

4. The method according to claim 3, characterized in that, The first performance metric value includes at least one of the following: The first value corresponding to each transport layer; The first value corresponding to the i-th transport layer, where i is a positive integer; The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal; and / or The second performance index value includes at least one of the following: The first performance index value corresponding to the entire broadband; The first performance index value corresponding to each sub-band; The average value of the first performance index corresponding to a portion of the sub-band; The average of the first performance index values ​​corresponding to all sub-bands; and / or The third performance index value includes at least one of the following: The second performance index value corresponding to each time unit; The second performance index values ​​corresponding to each of the time units; The average value of the second performance index corresponding to all time units.

5. The method according to claim 3 or 4, characterized in that, The first performance index value includes a first reference value and one or more first difference values. The first reference value is a first value corresponding to a first transport layer among a plurality of transport layers. The first difference value is the difference between the first value corresponding to the other transport layers (excluding the first transport layer) and the first reference value; and / or The second performance index value includes a second reference value and one or more second difference values. The second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands. The second difference value is the difference between the first value corresponding to other sub-bands (excluding the first sub-band) and the second reference value; and / or The third performance index value includes a third reference value and one or more third difference values. The third reference value is a first value corresponding to a first time unit among a plurality of time units. The third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

6. The method according to claim 5, characterized in that, The first transport layer includes at least one of the following: The network device indicates the transport layer; The terminal and the network device negotiate a predefined transport layer; The terminal via The transport layer indicated by the bit, where the value of U is predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal; and / or The first sub-band includes at least one of the following: The subband indicated by the network device; The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device; The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device; and / or The first time unit includes at least one of the following: The time unit indicated by the network device; The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device; The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

7. The method according to any one of claims 1-6, characterized in that, The quantization information of the first value is obtained using at least one of the following: The first value is a performance index value, which is quantized by x bits, where x is a positive integer; The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

8. The method according to any one of claims 1-7, characterized in that, At least one of the first reporting unit and the second reporting unit in the first report includes indication information related to the first value.

9. The method according to claim 8, characterized in that, The relevant information of the first value is at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value, and the indication information is used to indicate at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value; The relevant information for the first value is a performance index value, and the indication information is used to indicate the performance index value; The relevant information for the first value includes a reference value and a difference value, and the indication information is used to indicate the reference value and the difference value.

10. The method according to claim 8 or 9, characterized in that, The first reporting unit includes indication information of the reference value and / or indication information of at least one of the transmission layer, frequency granularity, and time unit corresponding to the reference value; the second reporting unit includes indication information of the differential value. Alternatively, the second reporting unit may include indication information of a reference value, indication information of at least one of the following: the transmission layer, frequency granularity, and time unit corresponding to the reference value, and indication information of a differential value.

11. The method according to any one of claims 8-10, characterized in that, The indication information is carried on physical uplink control channel resources or physical uplink shared channel resources.

12. The method according to any one of claims 1-11, characterized in that, Determine the first value, including: The channel state information based on the first model inference is determined according to the second configuration information. The second configuration information is associated with the first configuration information. The first configuration information is used to send a second report corresponding to the channel state information based on the first model inference. The second configuration information is used to send the first report. The first value is determined based on the channel state information inferred from the first model.

13. The method according to claim 12, characterized in that, The method further includes: Receive the second configuration information sent by the network device.

14. The method according to claim 12 or 13, characterized in that, The first configuration information is associated with the second configuration information, including: The first configuration information includes indication information for identifying the second report; The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

15. The method according to any one of claims 1-14, characterized in that, The channel state information based on the first model inference, which is associated with the quantization information of the first value, has not been updated; Sending the first report to the network device includes: sending the first report to the network device, wherein the first report is used to indicate quantization information of the first value that has not been updated.

16. The method according to any one of claims 1-15, characterized in that, The channel state information reference resource corresponding to the quantization information of the first value is determined based on at least one of the following: The time when channel state information based on the inference from the first model is transmitted; A second time unit is used to send the first report, the second time unit being predefined or indicated by the network device configuration.

17. A communication method, characterized in that, Performed by a network device, the method includes: The receiving terminal sends a first report, which includes quantization information of a first value. The first value is determined by the terminal according to at least one of the transmission layer, frequency granularity, and time unit. The first value is used to determine the performance of the first model.

18. The method according to claim 17, characterized in that, The first value is obtained based on at least one of the following: The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the channel state information inferred based on the first model; The precoding matrix indication corresponding to the actual channel state information and the precoding matrix indication corresponding to the first channel state information; wherein, the precoding matrix indication corresponding to the first channel state information is the precoding matrix indication corresponding to the channel state information reference resource that is closest to the reference time of the channel state information reference resource before the reference time of the channel state information reference resource based on the channel state information inferred from the first model. The statistical value of the first value within the first window.

19. The method according to claim 17 or 18, characterized in that, The first value is at least one of the first performance index value, the second performance index value, and the third performance index value; The first performance index value includes at least a portion of the first value corresponding to the transport layer, the second performance index value includes at least a portion of the first performance index value corresponding to the sub-band, and the third performance index value includes at least a portion of the second performance index value corresponding to the time unit.

20. The method according to claim 19, characterized in that, The first performance metric value includes at least one of the following: The first value corresponding to each transport layer; The first value corresponding to the i-th transport layer, where i is a positive integer; The average of the first values ​​corresponding to v transport layers, where the value of v is equal to the rank indicated by the terminal; and / or The second performance index value includes at least one of the following: The first performance index value corresponding to the entire broadband; The first performance index value corresponding to each sub-band; The average value of the first performance index corresponding to a portion of the sub-band; The average of the first performance index values ​​corresponding to all sub-bands; The third performance index value includes at least one of the following: and / or The second performance index value corresponding to each time unit; The second performance index values ​​corresponding to each of the time units; The average value of the second performance index corresponding to all time units.

21. The method according to claim 19 or 20, characterized in that, The first performance index value includes a first reference value and one or more first difference values. The first reference value is a first value corresponding to a first transport layer among a plurality of transport layers. The first difference value is the difference between the first value corresponding to the other transport layers (excluding the first transport layer) and the first reference value; and / or The second performance index value includes a second reference value and one or more second difference values. The second reference value is a first value corresponding to a first sub-band among a plurality of sub-bands. The second difference value is the difference between the first value corresponding to other sub-bands (excluding the first sub-band) and the second reference value; and / or The third performance index value includes a third reference value and one or more third difference values. The third reference value is a first value corresponding to a first time unit among a plurality of time units. The third difference value is the difference between the first value corresponding to other times among the plurality of time units besides the first time unit and the third reference value.

22. The method according to claim 21, characterized in that, The first transport layer includes at least one of the following: The network device indicates the transport layer; The terminal and the network device negotiate a predefined transport layer; The terminal via The value of U, as indicated by the bit at the transport layer, is predefined or configured by the network device, or the value of U is equal to the rank indicated by the terminal. The first sub-band includes at least one of the following: and / or The subband indicated by the network device; The terminal and the network device negotiate predefined N sub-bands, where the value of N is equal to the total number of sub-bands configured by the network device; The terminal via The subband indicated by the bit, where the value of S is predefined or configured by the network device; The first time unit includes at least one of the following: and / or The time unit indicated by the network device; The terminal and the network device negotiate M predefined time units, where the value of M is equal to the total number of time units configured by the network device; The terminal via The time unit indicated by the bit, where the value of K is predefined or configured by the network device.

23. The method according to any one of claims 17-22, characterized in that, The quantization information of the first value is obtained using at least one of the following: The first value is a performance index value, which is quantized by x bits, where x is a positive integer; The first value includes a reference value and a difference value. The reference value is quantized by a bits, and the difference value is quantized by b bits, where a and b are positive integers.

24. The method according to any one of claims 17-23, characterized in that, The method further includes: Send second configuration information to the terminal, the second configuration information being used to send the first report; The second configuration information is associated with the first configuration information, and the first configuration information is used to send a second report corresponding to the channel state information inferred based on the first model.

25. The method according to claim 24, characterized in that, The first configuration information is associated with the second configuration information, including: The first configuration information includes indication information for identifying the second report; The second configuration information includes indication information for identifying the first report and indication information for identifying the second report.

26. The method according to any one of claims 17-25, characterized in that, The channel state information based on the first model inference, which is associated with the quantization information of the first value, has not been updated; The first report sent by the receiving terminal includes: receiving the first report sent by the terminal, wherein the first report includes quantization information of the first value associated with the channel state information based on the first model inference that has not been updated.

27. A communication method for a communication system, the communication system comprising a terminal and network equipment, characterized in that, The method includes: The terminal determines a first value according to at least one of the transmission layer, frequency granularity, and time unit, and the first value is used to determine the performance of the first model. The terminal sends a first report to the network device, the first report being used to indicate the quantification information of the first value.

28. A communication device, characterized in that, The communication device is used to perform the communication method according to any one of claims 1-16 and 17-26.

29. A communication system, characterized in that, The device includes a terminal and a network device, wherein the terminal is configured to implement the communication method according to any one of claims 1-16, and the network device is configured to implement the communication method according to any one of claims 17-26.

30. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the communication method as described in any one of claims 1-16 and 17-26.

31. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by the communication device, it implements the steps of the method according to any one of claims 1-16 and 17-26.

Images