Performance determination methods, communication methods, devices, terminal equipment and network equipment

Abstract

This application provides a performance determination method, communication method, apparatus, terminal device, and network device. The method includes: determining the performance of a first model based on first information; the first information includes at least one of the following: communication performance; a proxy model; or a CSI report. The first model is used for encoding and / or decoding of second information, and the proxy model is used to simulate an encoder and / or decoder. This method enables monitoring of the performance of the first model during communication, ensuring stable operation of the first model and improving communication stability.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a performance determination method, communication method, apparatus, terminal equipment, and network equipment. Background Technology

[0002] During communication, after the terminal device generates Channel State Information (CSI), it needs to send the CSI to the network device so that the network device can determine the channel information based on the CSI.

[0003] To avoid increased transmission overhead and storage requirements due to large CSI data volumes, CSI data can be compressed before being sent to network devices. Upon receiving the compressed CSI, the network device reconstructs it to obtain the final CSI. Currently, artificial intelligence or machine learning models can be introduced into the CSI compression and decompression process to process the CSI data.

[0004] However, determining the performance of artificial intelligence or machine learning models during processing and ensuring their stable operation is a problem that urgently needs to be solved. Summary of the Invention

[0005] This application provides a performance determination method, communication method, apparatus, terminal device, and network device to solve the problem of how to determine the performance of an artificial intelligence model or machine learning model during processing and ensure the stable operation of the artificial intelligence model or machine learning model.

[0006] In a first aspect, embodiments of this application provide a performance determination method, including:

[0007] Based on the first information, determine the performance of the first model;

[0008] The first information includes at least one of the following: communication performance; proxy model; or, CSI report;

[0009] Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0010] In this embodiment, the network device and the terminal device can monitor the performance of the first model based on the first information. This enables the determination of the performance of the first model during communication, ensures the stable operation of the first model, and improves communication stability.

[0011] Secondly, embodiments of this application provide a communication method, including:

[0012] According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing;

[0013] The first CSI is encoded using the first model to obtain the second encoding result;

[0014] Send the first encoding result and / or the second encoding result.

[0015] In this embodiment of the application, the network device can monitor the performance of the first model based on the first encoding result and / or the second encoding result sent.

[0016] Thirdly, embodiments of this application provide a performance determination method applied in a terminal device, the method comprising:

[0017] The performance of the first model is determined based on communication performance and / or proxy model;

[0018] Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0019] In this embodiment, the terminal device determines the performance of the first model through communication performance and / or a proxy model. This enables monitoring of the first model's performance during communication, reducing the likelihood of communication failures due to anomalies in the first model during use, and improving communication stability.

[0020] In one possible implementation, the second information includes at least one of the following:

[0021] Joint sources; or,

[0022] Channel information.

[0023] In one possible implementation, the communication performance includes at least one of the following:

[0024] Signal-to-noise ratio (SNR) of the received signal;

[0025] The distribution characteristics of the channel information;

[0026] Bit error rate;

[0027] Block error rate; or,

[0028] The probability of a non-response to a hybrid automatic repeat request.

[0029] In one possible implementation, determining the performance of the first model based on the proxy model includes:

[0030] Obtain the first result processed by the first model;

[0031] Obtain the second result of the proxy model processing;

[0032] Based on the results, determine the performance of the first model;

[0033] The result information includes at least one of the second information, the first result, or the second result.

[0034] In this embodiment, since the proxy model is used to simulate the encoder and / or decoder, the processing method corresponding to the proxy model is determined based on the processing method of the first model. (For example, the first model performs encoding processing, and the proxy model performs decoding processing. Or, the first model performs decoding processing, and the proxy model performs decoding processing, etc.) This determines the performance of the first model, improving the flexibility in determining the performance of the first model.

[0035] In one possible implementation, the method further includes:

[0036] According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing;

[0037] The first CSI is encoded using the first model to obtain the second encoding result;

[0038] Send the first encoding result and / or the second encoding result.

[0039] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0040] In one possible implementation, sending the first encoding result and / or the second encoding result includes:

[0041] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0042] In one possible implementation, sending the first encoding result and / or the second encoding result includes:

[0043] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0044] Send a second CSI report, which includes the second encoding result.

[0045] In one possible implementation, the method further includes:

[0046] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0047] In one possible implementation, the indication information is carried in at least one of the following:

[0048] Radio Resource Control (RRC) signaling;

[0049] Media access control MAC signaling; or,

[0050] Downlink Control Information (DCI).

[0051] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0052] The first CSI report and the second CSI report are associated with the same trigger state;

[0053] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0054] The DCI that triggers the first CSI report and the second CSI report is the same.

[0055] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0056] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0057] In one possible implementation, the first transmission resource and the second transmission resource overlap or partially overlap, and the method further includes:

[0058] Discard the first CSI report; or,

[0059] Discard the second CSI report; or,

[0060] Send the first CSI report; or,

[0061] Send a second CSI report; or,

[0062] Send the first CSI report, but do not send the second CSI report; or,

[0063] Send the second CSI report, but do not send the first CSI report.

[0064] Fourthly, embodiments of this application provide a communication method applied in a terminal device, the method comprising:

[0065] According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing;

[0066] The first CSI is encoded using the first model to obtain the second encoding result;

[0067] Send the first encoding result and / or the second encoding result.

[0068] In this embodiment, the terminal device sends a first encoding result and a second encoding result to the network device. This allows the network device to monitor the performance of the first model based on the first and second encoding results.

[0069] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0070] When transmission resources are limited, the priority of the first encoding result and / or the second encoding result is determined based on the priority of the second encoding result. This saves communication overhead and improves communication flexibility.

[0071] In one possible implementation, sending the first encoding result and / or the second encoding result includes:

[0072] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0073] In one possible implementation, sending the first encoding result and / or the second encoding result includes:

[0074] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0075] Send a second CSI report, which includes the second encoding result.

[0076] In one possible implementation, the method further includes:

[0077] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0078] In this embodiment, the network device can determine the second encoding result corresponding to the first encoding result based on the association between the indicated first CSI report and the second CSI report. The first encoding result and the corresponding second encoding result are encoding results obtained through the same CSI processing. Thus, the network device can determine the performance of the first model based on the first encoding result and the corresponding second encoding result.

[0079] In one possible implementation, the indication information is carried in at least one of the following:

[0080] Radio Resource Control (RRC) signaling;

[0081] Media access control MAC signaling; or,

[0082] Downlink Control Information (DCI).

[0083] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0084] The first CSI report and the second CSI report are associated with the same trigger state;

[0085] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0086] The DCI that triggers the first CSI report and the second CSI report is the same.

[0087] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0088] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0089] In one possible implementation, the first transmission resource and the second transmission resource overlap or partially overlap, and the method further includes:

[0090] Discard the first CSI report; or,

[0091] Discard the second CSI report; or,

[0092] Send the first CSI report; or,

[0093] Send a second CSI report; or,

[0094] Send the first CSI report, but do not send the second CSI report; or,

[0095] Send the second CSI report, but do not send the first CSI report.

[0096] Fifthly, embodiments of this application provide a performance determination method applied in a network device, the method comprising:

[0097] Based on the first information, determine the performance of the first model;

[0098] The first information includes at least one of the following: communication performance; proxy model; or, CSI report;

[0099] Wherein, the first model is used for encoding and / or decoding the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0100] In this embodiment, the network device determines the performance of the first model using first information. This enables monitoring of the first model's performance during communication, reducing the likelihood of communication failures due to abnormalities in the first model during use, and improving communication stability.

[0101] In one possible implementation, the second information includes at least one of the following:

[0102] Joint sources; or,

[0103] Channel information.

[0104] In one possible implementation, the communication performance includes at least one of the following:

[0105] Signal-to-noise ratio (SNR) of the received signal;

[0106] The distribution characteristics of the channel information;

[0107] Bit error rate;

[0108] Block error rate; or,

[0109] The probability of a non-response to a hybrid automatic repeat request.

[0110] In one possible implementation, the first information includes the agent model; determining the performance of the first model based on the first information includes:

[0111] Obtain the intermediate results processed by the first model;

[0112] Obtain the proxy result processed by the proxy model;

[0113] The performance of the first model is determined based on the result indication information, wherein the result indication information includes at least one of the second information, the intermediate result, or the proxy result.

[0114] In this embodiment, since the proxy model is used to simulate the encoder and / or decoder, the processing method corresponding to the proxy model is determined based on the processing method of the first model. (For example, the first model performs encoding processing, and the proxy model performs decoding processing. Or, the first model performs decoding processing, and the proxy model performs decoding processing, etc.) This determines the performance of the first model, improving the flexibility in determining the performance of the first model.

[0115] In one possible implementation, the method further includes:

[0116] Receive the CSI report, which includes a first encoding result and / or a second encoding result.

[0117] In one possible implementation, the CSI report includes a first CSI report and / or a second CSI report; the method further includes:

[0118] Receive the first CSI report, the first CSI report including the first encoding result; and / or,

[0119] Receive the second CSI report, which includes the second encoding result.

[0120] In one possible implementation, the method further includes:

[0121] Send indication information, which indicates that the first CSI report and the second CSI report are related.

[0122] In one possible implementation, the indication information is carried in at least one of the following:

[0123] Radio Resource Control (RRC) signaling;

[0124] Media access control MAC signaling; or,

[0125] Downlink Control Information (DCI).

[0126] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0127] The first CSI report and the second CSI report are associated with the same trigger state;

[0128] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0129] The DCI that triggers the first CSI report and the second CSI report is the same.

[0130] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0131] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0132] In one possible implementation, the first encoding result is the encoding result obtained by encoding the first CSI according to a preset method;

[0133] The second encoding result is the encoding result obtained by encoding the first CSI according to the first model;

[0134] The first CSI is the CSI generated by the terminal device;

[0135] The preset method is to not use the first model for encoding processing;

[0136] The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0137] In one possible implementation, the first information includes the CSI report; determining the performance of the first model based on the first information includes:

[0138] Based on the CSI report, the first encoding result and the second encoding result are determined;

[0139] The first encoding result is decoded using the preset method to obtain the second CSI corresponding to the first CSI.

[0140] The third CSI corresponding to the first CSI is obtained by decoding the second encoding result using the first model.

[0141] Obtain the similarity between the second CSI and the third CSI;

[0142] The performance of the first model is determined based on the similarity between the second CSI and the third CSI.

[0143] Sixthly, embodiments of this application provide a performance determination apparatus, the apparatus comprising:

[0144] A determination module is used to determine the performance of the first model based on communication performance and / or proxy model;

[0145] Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0146] In one possible implementation, the second information includes at least one of the following:

[0147] Joint sources; or,

[0148] Channel information.

[0149] In one possible implementation, the communication performance includes at least one of the following:

[0150] Signal-to-noise ratio (SNR) of the received signal;

[0151] The distribution characteristics of the channel information;

[0152] Bit error rate;

[0153] Block error rate; or,

[0154] The probability of a non-response to a hybrid automatic repeat request.

[0155] In one possible implementation, the determining module is specifically used for:

[0156] Obtain the first result processed by the first model;

[0157] Obtain the second result of the proxy model processing;

[0158] Based on the results, determine the performance of the first model;

[0159] The result information includes at least one of the second information, the first result, or the second result.

[0160] In one possible implementation, the device further includes a transmitting module and a receiving module.

[0161] The sending module is used for:

[0162] According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing;

[0163] The first CSI is encoded using the first model to obtain the second encoding result;

[0164] Send the first encoding result and / or the second encoding result.

[0165] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0166] The sending module is used for:

[0167] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0168] The sending module is used for:

[0169] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0170] Send a second CSI report, which includes the second encoding result.

[0171] The receiving module is used for:

[0172] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0173] In one possible implementation, the indication information is carried in at least one of the following:

[0174] Radio Resource Control (RRC) signaling;

[0175] Media access control MAC signaling; or,

[0176] Downlink Control Information (DCI).

[0177] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0178] The first CSI report and the second CSI report are associated with the same trigger state;

[0179] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0180] The DCI that triggers the first CSI report and the second CSI report is the same.

[0181] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0182] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0183] The sending module is used for:

[0184] Discard the first CSI report; or,

[0185] Discard the second CSI report; or,

[0186] Send the first CSI report; or,

[0187] Send a second CSI report; or,

[0188] Send the first CSI report, but do not send the second CSI report; or,

[0189] Send the second CSI report, but do not send the first CSI report.

[0190] Seventhly, embodiments of this application provide a communication device, the device comprising:

[0191] The first processing module is used to encode the first CSI according to a preset method to obtain a first encoding result, wherein the preset method is a method of encoding without using the first model;

[0192] The second processing module is used to encode the first CSI using the first model to obtain a second encoding result;

[0193] A sending module is used to send the first encoding result and / or the second encoding result.

[0194] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0195] In one possible implementation, the sending module is specifically used for:

[0196] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0197] In one possible implementation, the sending module is specifically used for:

[0198] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0199] Send a second CSI report, which includes the second encoding result.

[0200] In one possible implementation, the device further includes a receiving module.

[0201] The receiving module is used for:

[0202] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0203] In one possible implementation, the indication information is carried in at least one of the following:

[0204] Radio Resource Control (RRC) signaling;

[0205] Media access control MAC signaling; or,

[0206] Downlink Control Information (DCI).

[0207] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0208] The first CSI report and the second CSI report are associated with the same trigger state;

[0209] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0210] The DCI that triggers the first CSI report and the second CSI report is the same.

[0211] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0212] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0213] The sending module is also used for:

[0214] Discard the first CSI report; or,

[0215] Discard the second CSI report; or,

[0216] Send the first CSI report; or,

[0217] Send a second CSI report; or,

[0218] Send the first CSI report, but do not send the second CSI report; or,

[0219] Send the second CSI report, but do not send the first CSI report.

[0220] Eighthly, embodiments of this application provide a performance determination apparatus, the apparatus comprising:

[0221] The determination module is used to determine the performance of the first model based on the first information;

[0222] The first information includes at least one of the following: communication performance; proxy model; or, CSI report;

[0223] Wherein, the first model is used for encoding and / or decoding the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0224] In one possible implementation, the second information includes at least one of the following:

[0225] Joint sources; or,

[0226] Channel information.

[0227] In one possible implementation, the communication performance includes at least one of the following:

[0228] Signal-to-noise ratio (SNR) of the received signal;

[0229] The distribution characteristics of the channel information;

[0230] Bit error rate;

[0231] Block error rate; or,

[0232] The probability of a non-response to a hybrid automatic repeat request.

[0233] In one possible implementation, the determining module is specifically used for:

[0234] Obtain the intermediate results processed by the first model;

[0235] Obtain the proxy result processed by the proxy model;

[0236] The performance of the first model is determined based on the result indication information, wherein the result indication information includes at least one of the second information, the intermediate result, or the proxy result.

[0237] In one possible implementation, the determining module is specifically used for:

[0238] Based on the CSI report, the first encoding result and the second encoding result are determined;

[0239] The first encoding result is decoded using the preset method to obtain the second CSI corresponding to the first CSI.

[0240] The third CSI corresponding to the first CSI is obtained by decoding the second encoding result using the first model.

[0241] Obtain the similarity between the second CSI and the third CSI;

[0242] The performance of the first model is determined based on the similarity between the second CSI and the third CSI.

[0243] In one possible implementation, the device further includes a receiving module and a transmitting module.

[0244] The receiving module is used for:

[0245] Receive the CSI report, which includes a first encoding result and / or a second encoding result.

[0246] The receiving module is used for:

[0247] Receive the first CSI report, the first CSI report including the first encoding result; and / or,

[0248] Receive the second CSI report, which includes the second encoding result.

[0249] The sending module is used for:

[0250] Send indication information, which indicates that the first CSI report and the second CSI report are related.

[0251] In one possible implementation, the indication information is carried in at least one of the following:

[0252] Radio Resource Control (RRC) signaling;

[0253] Media access control MAC signaling; or,

[0254] Downlink Control Information (DCI).

[0255] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0256] The first CSI report and the second CSI report are associated with the same trigger state;

[0257] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0258] The DCI that triggers the first CSI report and the second CSI report is the same.

[0259] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0260] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0261] In one possible implementation, the first encoding result is the encoding result obtained by encoding the first CSI according to a preset method;

[0262] The second encoding result is the encoding result obtained by encoding the first CSI according to the first model;

[0263] The first CSI is the CSI generated by the terminal device;

[0264] The preset method is to not use the first model for encoding processing;

[0265] The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0266] Ninthly, this application provides a chip having a computer program stored thereon, which, when executed by the chip, implements the method as described in any one of the first to fifth aspects.

[0267] In a tenth aspect, this application provides a chip module on which a computer program is stored, and when the computer program is executed by the chip module, it implements the method as described in any one of the first to fifth aspects.

[0268] Eleventhly, embodiments of this application provide a terminal device, including:

[0269] At least one processor; and

[0270] A memory communicatively connected to the at least one processor; wherein,

[0271] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described in any one of the first to fourth aspects.

[0272] In a twelfth aspect, embodiments of this application provide a network device, including:

[0273] At least one processor; and

[0274] A memory communicatively connected to the at least one processor; wherein,

[0275] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of the first aspects or any one of the fifth aspects.

[0276] In a thirteenth aspect, embodiments of this application provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described in any one of the first to fifth aspects.

[0277] In a fourteenth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any one of the first to fifth aspects. Attached Figure Description

[0278] Figure 1 A schematic diagram illustrating the application scenarios provided in the embodiments of this application;

[0279] Figure 2 A flowchart illustrating a performance determination method provided in an embodiment of this application;

[0280] Figure 3 A flowchart illustrating a communication method provided in an embodiment of this application;

[0281] Figure 4A This application provides a schematic diagram of a process for determining a first encoding result in an embodiment of the present application.

[0282] Figure 4B This application provides a schematic diagram of a process for determining a second encoding result in an embodiment of the present application.

[0283] Figure 4C This is a schematic diagram illustrating another process for determining the second encoding result provided in an embodiment of this application;

[0284] Figure 5 A flowchart illustrating another performance determination method provided in an embodiment of this application;

[0285] Figure 6 A flowchart illustrating yet another performance determination method provided in this application embodiment;

[0286] Figure 7 This is a schematic diagram of the structure of a performance determination device provided in an embodiment of this application;

[0287] Figure 8 This is a schematic diagram of another performance determination device provided in an embodiment of this application;

[0288] Figure 9 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0289] Figure 10 This is a schematic diagram of another communication device provided in an embodiment of this application;

[0290] Figure 11This is a schematic diagram of another performance determination device provided in an embodiment of this application;

[0291] Figure 12 This is a schematic diagram of another performance determination device provided in an embodiment of this application;

[0292] Figure 13 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application;

[0293] Figure 14 This is a schematic diagram of the network device provided in an embodiment of this application. Detailed Implementation

[0294] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0295] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0296] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0297] The technical solutions provided in this application can be applied to a variety of systems. Applicable systems may include, but are not limited to: narrowband Internet of Things (NB-IoT), wideband code division multiple access (WCDMA), code division multiple access 2000 (CDMA2000), time division-synchronization code division multiple access (TDSCDMA), long term evolution (LTE), fifth-generation mobile communication systems or possible sixth-generation or seventh-generation mobile communication systems, vehicle-mounted short-range wireless communication systems, and future mobile communication systems.

[0298] The technical solutions provided in this application are also applicable to different network architectures, including but not limited to relay network architecture, dual-connectivity architecture, vehicle-to-everything (V2X) architecture, and device-to-device (D2D) architecture.

[0299] The communication architecture involved in this application includes core network equipment. Core network equipment can also be referred to as core network elements or core network functional entities. As an example, a core network functional entity may include any one of the following: a Policy Control Function (PCF) entity, a Network Slice Selection Function (NSSF) entity, a Unified Data Management (UDM) entity, a Network Repository Function (NRF) entity, a Session Management Function (SMF) entity, an Access and Mobility Management Function (AMF) entity, and a User Plane Function (UPF) entity. Core network functional entities can be logical entities or physical entities. As an example, the functions of the above functional entities are as follows:

[0300] The PCF entity is primarily used as a unified policy framework to guide network behavior, providing policy rule information to control plane entities (such as AMF, SMF, etc.).

[0301] The AMF entity is mainly used for functions such as access control, mobility management, registration and deregistration.

[0302] SMF entities are primarily used for user plane network element selection, user plane network element redirection, Internet Protocol (IP) address allocation for terminal devices, and session establishment, modification, release, and Quality of Service (QoS) control.

[0303] UPF entities are primarily used for receiving and forwarding user plane data. For example, a UPF entity can receive user plane data from a service server and send it to a terminal device via access network equipment. A UPF entity can also receive user plane data from a terminal device via access network equipment and forward it to a service server.

[0304] NSSF entities are primarily used for network slice selection.

[0305] UDM entities are primarily used for managing subscription data of terminal devices, including the storage and management of terminal device identifiers and access authorization for terminal devices.

[0306] The network devices involved in the embodiments of this application can be access network devices and core network devices. Taking access network devices as an example, they can include base stations and base station controllers.

[0307] The base station (BS) in this application embodiment, also referred to as base station equipment, is a device deployed in a radio access network (RAN) to provide wireless communication functions. For example, in wireless local area networks (WLANs), the equipment providing base station functions is an access point (AP); in 5G new radio (NR), the equipment providing base station functions is the gNB; and the next-generation eNodeB (ng-eNB). The gNB and terminal equipment communicate using NR technology, while the ng-eNB and terminal equipment communicate using evolved universal terrestrial radio access (E-UTRA) technology. Both the gNB and ng-eNB can connect to the 5G core network. The base station in this application embodiment also includes equipment that provides base station functions in future new communication systems.

[0308] The terminal device in this application is a device with wireless transceiver capabilities. The terminal device can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted; it can also be deployed on water (such as on ships); and it can also be deployed in the air (e.g., on airplanes, balloons, and satellites). The terminal device can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, vehicle-mounted terminal device, wireless terminal device in self-driving, wireless terminal device in remote medical care, wireless terminal device in smart grids, wireless terminal device in transportation safety, wireless terminal device in smart cities, wireless terminal device in smart homes, wearable terminal devices, terminal devices in 5G networks, or terminal devices in future evolved public land mobile networks (PLMNs), etc. This application does not limit the scope of these embodiments. The terminal equipment involved in the embodiments of this application may also be referred to as user equipment (UE), access terminal equipment, vehicle-mounted terminal equipment, industrial control terminal equipment, UE unit, UE station, mobile station, mobile station, remote station, remote user equipment, mobile device, wireless communication equipment, UE agent, or UE device, etc. The terminal equipment may also be fixed or mobile.

[0309] The following is a brief introduction to some of the terms and technologies involved in the embodiments of this application:

[0310] 1. Channel Information

[0311] In this application, channel information can be used to characterize channel features or characteristics. For example, channel information can be channel matrix information and / or CSI and / or channel eigenvectors. Alternatively, channel information can also be a CSI report. Furthermore, channel information can also be time-domain information, frequency-domain information, time-frequency-domain information, or delay-Doppler domain channel information, etc., without specific limitations. Channel matrix information and CSI are described below.

[0312] 1.1 Channel Matrix Information

[0313] In this application, channel matrix information can be used to describe information related to the channel matrix. For example, channel matrix information may include one or more of the following: channel matrix H, equivalent channel matrix, precoding matrix W (precoding matrix W can be derived from channel matrix H), right singular vector V of channel matrix H, and square matrix H. T The feature vector v of H i Vectors associated with the channel matrix H (e.g., vectors of the channel matrix H under certain transformations).

[0314] (1) Channel matrix H, equivalent channel matrix, precoding matrix W

[0315] In a multiple-input multiple-output (MIMO) system, for a transmitter with 'a' antennas and a receiver with 'b' antennas, the channel model of the MIMO channel can be represented as:

[0316] r = Hs + n0

[0317] Where r is the received signal vector after passing through the MIMO channel; s is the transmitted signal vector at the transmitter; H is the b×a channel matrix for the MIMO channel; and n0 is the additive noise vector. It should be noted that for a=1 and b=1, that is, when both the transmitter and receiver have one antenna, H can also be used to represent the 1×1 channel matrix.

[0318] In precoding, the transmitter can optimize the spatial characteristics of the transmitted signal vector s based on the channel matrix H, ensuring that the spatial distribution of the transmitted signal vector s matches the channel matrix H. This effectively reduces the dependence on the receiver algorithm and simplifies the receiver algorithm. Precoding can significantly improve system performance.

[0319] Precoding can employ linear or nonlinear methods. Due to complexity and other considerations, current wireless communication systems generally only consider linear precoding. After precoding, the channel model of the MIMO signal can be expressed as:

[0320] r = HWs + n0

[0321] Where W is the precoding matrix.

[0322] In multi-user MIMO (MU-MIMO) systems, the receiver cannot perform channel estimation on signals transmitted to other devices. Therefore, transmitter precoding can effectively suppress multi-user interference. It is evident that it is beneficial for the transmitter to know the channel matrix and process it using appropriate precoding.

[0323] Furthermore, in precoding methods, the precoding matrix W and the channel matrix H jointly determine the equivalent channel matrix (e.g., H·W), which in turn determines the channel characteristics / features. Additionally, in some cases, the precoding matrix W can be derived from the channel matrix H; for example, the precoding matrix W can be a matrix under a certain transformation of the channel matrix H.

[0324] (2) The right singular vector V of the channel matrix H and the square matrix H T The feature vector v of H i

[0325] The singular value decomposition of the channel matrix H can be:

[0326] H=U∑V T

[0327] Among them, U=[u1,u2,…,u b [v1, v2, ..., v] is a b×b orthogonal matrix or unitary matrix; V = [v1, v2, ..., v] a ] is an a×a orthogonal matrix or Σ matrix, and the column vectors in V can be called the right-singular vectors of the channel matrix H; ∑ is an a×a diagonal matrix, and the elements on the diagonal are the p = min(b,a) singular values ​​σ1,σ2,……,σ of the channel matrix H. p And arranged in descending order, i.e., σ1>σ2>……>σ p .

[0328] The conjugate transpose H of the channel matrix T Multiplying by the channel matrix H yields an a×a square matrix H. T H, against the formation H T Eigenvalues ​​and eigenvectors of H are obtained by performing eigendecomposition:

[0329] (H T H)v i =λ i v i i∈[1,a]

[0330] Where, λ i Represents the square matrix H T Eigenvalues ​​of H; v i Represents the square matrix H T The eigenvectors of H.

[0331] From H=U∑V T We can obtain (H) T H)v i =V∑ 2 V TTherefore, the square matrix H T The eigenvectors of H also represent the column vectors in V mentioned above. That is, the square matrix H... T All eigenvectors of H can form the above V, and the square matrix H T The eigenvectors of H can be the right singular vectors of the channel matrix H.

[0332] 1.2, CSI

[0333] In this application, the Channel Information System (CSI) can be used to describe information related to channel quality. For example, the CSI describes the propagation process of a wireless signal between a transmitter and a receiver, including the effects of distance, scattering, and fading on the signal. For downlink transmission, the CSI can be used by the terminal device to provide feedback on the downlink channel quality to the network device, so that the network device can perform beam management, mobility management, and other processing based on the CSI. The CSI sent by the terminal device to the network device can be carried in the CSI report. For example, the CSI may also include at least one of the following: CSI Reference Signal Resource Indicator (CSI-RS Resource Indicator, CRI), Rank Indicator (RI), Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI), Layer Indicator (LI), L1-RSRP, L1-SINR, channel information, and information processed from the channel information.

[0334] In this application, the terminal device performs channel measurements using a downlink reference signal to obtain channel information. The measurement can also be described as evaluation, detection, or estimation. The downlink reference signal may include, but is not limited to, CSI-RS, synchronization signals, and physical broadcast channel blocks (SSBs) or physical broadcast channel demodulation reference signals (PBCH DMRS). For example, the terminal device can perform downlink channel measurements based on the CSI-RS to obtain channel matrix information, and then obtain the CSI based on the channel matrix information.

[0335] Below, in conjunction with Figure 1 The application scenarios applicable to the embodiments of this application will be described.

[0336] Figure 1 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. Please refer to [link / reference]. Figure 1The system includes terminal device 101 and network device 102. Terminal device 101 can be a mobile phone, tablet computer, computer, etc. Network device 102 can be a base station. Terminal device 101 can perform channel estimation and generate a Communication Signal Indicator (CSI). Terminal device 101 sends the CSI to network device 102. Network device 102 can perform signal processing and resource allocation operations based on the CSI to improve communication efficiency and performance.

[0337] To avoid increased transmission overhead and storage requirements due to large CSI data volumes, CSI data can be compressed before being sent to network devices. Upon receiving the compressed CSI, the network device reconstructs it to obtain the final CSI. Currently, artificial intelligence (AI) or machine learning (MLM) models can be introduced during the CSI compression and decompression process to process the CSI. However, determining the performance of these AI or MLM models during processing and ensuring their stable operation remains a critical issue.

[0338] In this embodiment, the terminal device and network device can determine the performance of the first model through communication performance and / or a proxy model. The network device can also determine the performance of the first model based on the CSI report sent by the terminal device. The first model is used for encoding and / or decoding the second information, and the proxy model is used to simulate the encoder and / or decoder. In this way, the network device and terminal device can monitor the performance of the first model. This achieves the determination of the performance of the first model during communication, ensures the stable operation of the first model, and improves communication stability.

[0339] The method described in this application will now be illustrated through specific embodiments. It should be noted that the following embodiments may exist independently or in combination with each other; identical or similar content will not be repeated in different embodiments.

[0340] Figure 2 This is a flowchart illustrating a performance determination method provided in an embodiment of this application. Please refer to... Figure 2 The method may include:

[0341] S201. Determine the performance of the first model based on communication performance and / or proxy model.

[0342] The execution entity in this application embodiment can be a terminal device, or a chip, chip module, or performance determination device disposed in the terminal device. The performance determination device can be implemented by software or by a combination of software and hardware. The terminal device can be a mobile phone, tablet computer, etc.

[0343] The first model is used for encoding and / or decoding the second information, and the surrogate model is used to simulate the encoder and / or decoder.

[0344] For example, the first model can be an artificial intelligence (AI) model or a machine learning (ML) model.

[0345] For example, the encoding process of the first model for the second information may include at least one of the following: compression processing; channel coding processing; modulation processing. The decoding process of the first model may include at least one of the following: demodulation processing; channel decoding processing; or compression recovery processing.

[0346] It is understood that the encoding and / or decoding of the second information using the first model may also include other processing, which is only an example here and is not limited in this application.

[0347] For example, an encoder processes signals and / or data to add redundant information. This improves the noise and interference immunity of the signals and / or data during transmission, thereby enhancing communication reliability. A decoder can then recover the received, encoder-processed data back to its original state.

[0348] For example, an encoder processes signals and / or data to compress them. This reduces the resources required for signal and / or data transmission. A decoder can then restore the received, encoder-processed data to its original state before encoder processing.

[0349] In one possible implementation, the second information includes at least one of the following: joint information source; or, channel information.

[0350] For example, the joint information source may include at least one of voice signals, video signals, or sensor data. It is understood that the joint information source may also include other information; this is merely an example and is not intended to limit the scope of the application.

[0351] For example, channel information is used to indicate the state and quality of the channel. Channel information may include at least one of channel gain, fading characteristics, or delay spread. It is understood that channel information may also include other information; this is merely an example and is not intended to limit the scope of the application.

[0352] In one possible implementation, the communication performance includes at least one of the following: the signal-to-noise ratio (SNR) of the received signal; the distribution characteristics of the channel information; the bit error rate; the block error rate; or, the probability of a hybrid automatic repeat request acknowledgement (HARQ-ACK).

[0353] It is understood that communication performance may also include other information; this is only an example and is not a limitation of this application.

[0354] For example, channel information may include channel gain, fading characteristics, delay spread, etc., and these characteristics can be described by statistical distributions. The distribution characteristics of channel information can affect the propagation characteristics of signals and the performance of communication systems.

[0355] For example, both bit error rate (BER) and block error rate (BER) can be used to represent the proportion of data units that have transmission errors and / or demodulation errors. In a specific example, the BER of the data to be demodulated can be the proportion of data units (e.g., bits) that have demodulated errors after demodulation of the data to be demodulated. The BER of the data to be demodulated is the proportion of data units (e.g., code blocks) that have demodulated errors after demodulation of the data to be demodulated. In other words, the BER and BER of the data to be demodulated are the proportion of data units that differ from the data to be modulated after demodulation. The above are merely examples of the BER and BER of the data to be demodulated and do not constitute a limitation. The BER and BER of the data to be demodulated can also have other meanings or be obtained in other ways.

[0356] For example, the probability of HARQ ACK is the proportion of data packets that the receiver successfully receives and correctly decodes out of the actual data packets received. The probability of HARQ ACK is used to indicate the likelihood that the receiver will correctly receive or decode data packets.

[0357] Optionally, the performance of the first model is determined by comparing each piece of information in the communication performance with its corresponding performance threshold and / or performance threshold range, based on the comparison results. The performance thresholds and / or performance threshold ranges corresponding to each piece of information in the communication performance can be different or the same. The performance thresholds and / or performance threshold ranges can be, but are not limited to, predefined ones, obtained based on network configuration information, indicated based on downlink control information (DCI), or reported based on terminal device capabilities.

[0358] For example, if the communication performance does not include the probability of HARQ ACK, and at least one of the information items in the communication performance is greater than or equal to the corresponding performance threshold and / or performance threshold range, then it is determined that the performance of the first model cannot meet the performance requirements of the communication system for modulation and demodulation.

[0359] For example, if the communication performance includes the probability of HARQ ACK, and it is determined that the probability of HARQ ACK in the communication performance is less than or equal to the corresponding performance threshold and / or performance threshold range, and / or, at least one of the information items in the communication performance other than the probability of HARQ ACK is greater than or equal to the corresponding performance threshold and / or performance threshold range, then it is determined that the performance of the first model cannot meet the modulation and demodulation performance requirements of the communication system.

[0360] For example, if the bit error rate obtained by demodulating the data to be demodulated is 25%, which is greater than the bit error rate threshold of 10%, and it is determined that at least one of the communication performance parameters is greater than or equal to the corresponding performance threshold, then it is determined that the performance of the first model does not meet the performance requirements of the communication system for modulation and demodulation.

[0361] For example, suppose communication performance includes bit error rate (BER), block error rate (BRR), and the probability of HARQ ACK. The demodulated data has a BER of 6%, a BRR of 6%, and a HARQ ACK probability of 75%. The terminal device determines that the BER and BRR are both less than the BER threshold of 10%, and the HARQ ACK probability is less than the HARQ ACK probability threshold of 75%. Since the probability of HARQ ACK in the communication performance is determined to be less than the corresponding performance threshold, the performance of the first model does not meet the modulation and demodulation performance requirements of the communication system.

[0362] For example, the performance of the first model can also be determined based on its accuracy, precision, recall, etc. It is understood that the performance of the first model may also include other information; this is merely an example, and this application does not limit it.

[0363] In one possible implementation, the performance of the first model is determined based on the proxy model by: obtaining a first result processed by the first model; obtaining a second result processed by the proxy model; and determining the performance of the first model based on the result information; wherein the result information includes at least one of the second information, the first result, or the second result.

[0364] For example, a surrogate model is used to simulate the original model. In other words, the surrogate model and the original model have the same or similar functions. Based on the same inputs and / or outputs, similar model structures, etc., the surrogate model can achieve the same or similar functions as the original model.

[0365] For example, if the original model is an encoder and / or decoder, then a surrogate model can be used to simulate the encoder and / or decoder. Furthermore, a surrogate model can be used to simulate an encoder, implementing the same or similar functionality as the encoder. Similarly, a surrogate model can be used to simulate a decoder, implementing the same or similar functionality as the decoder. Finally, a surrogate model can be used to simulate both an encoder and a decoder, implementing the same or similar functionality as both the encoder and decoder.

[0366] In this context, the surrogate model shares the same inputs and / or outputs as the original model. Same inputs mean the data structure and / or meaning of the inputs to the surrogate model and the original model are identical. Same outputs mean the data structure and / or meaning of the outputs from the surrogate model and the original model are identical. Therefore, it can be understood that the surrogate model and the original model have the same functionality.

[0367] Optionally, the surrogate model may differ from the original model in at least one of the following aspects: model structure, number of layers, and parameter values ​​for each layer. Due to these differences, the performance of the surrogate model may also differ from the original model.

[0368] For example, but not limited to, there are differences in the precision of the model's output data and the time it takes for the model to obtain the output based on the input. Therefore, it can be understood that the surrogate model and the original model have similar functionalities.

[0369] Optionally, the proxy model is identical to the original model in several of the aforementioned aspects. Therefore, it can be understood that the proxy model and the original model have the same functionality.

[0370] It should be noted that the surrogate model and the original model may differ or be the same in other aspects, giving the surrogate model the same or similar functionality as the original model; this is not limited here. Based on the fact that the surrogate model and the original model have the same or similar functionality, the surrogate model can simulate the original model.

[0371] For example, taking a proxy model used in an analog decoder, the performance of determining the first model is described. First, the first result of encoding the second information using the first model is obtained. Second, the second result of decoding the first result using the proxy model is obtained. Then, based on the result information, the performance of the first model is determined.

[0372] For example, taking a surrogate model used to simulate an encoder, the performance of the first model is determined. The second result of the surrogate model encoding the second information is obtained. The first result of the first model decoding the second result is obtained. Then, based on the result information, the performance of the first model is determined.

[0373] For example, using a surrogate model to simulate an encoder and decoder, the performance of the first model is determined. The first result of the first model processing the second information is obtained, and the second result of the surrogate model processing the second information is obtained. Then, based on the results, the performance of the first model is determined.

[0374] For example, determining the performance of the first model based on the results information includes at least one of the following methods:

[0375] Method 1: If the proxy model is used to simulate the decoder, the performance of the first model is determined based on the similarity between the second result and the second information.

[0376] If the similarity between the second result and the second information is greater than or equal to the first preset similarity, then the performance of the first model meets the performance requirements of the communication system for modulation and demodulation.

[0377] If the similarity between the second result and the second information is less than the first preset similarity, then the performance of the first model does not meet the performance requirements of the communication system for modulation and demodulation.

[0378] Method 2: Determine the performance of the first model based on the similarity between the first and second results.

[0379] If the similarity between the first result and the second result is greater than or equal to the second preset similarity, then the performance of the first model meets the performance requirements of the communication system for modulation and demodulation.

[0380] If the similarity between the first result and the second result is less than the second preset similarity, then the performance of the first model does not meet the performance requirements of the communication system for modulation and demodulation.

[0381] For example, the first preset similarity and the second preset similarity may be, but are not limited to, predefined, obtained based on network configuration information, or based on DCI indication, or derived from the capability report of the terminal device.

[0382] For example, suppose a proxy model is used to simulate a decoder. The terminal device obtains a first result from the encoding of second information by the first model. It then obtains a second result from the decoding of the first result by the proxy model. The terminal device finds a similarity of 0.9 between the first and second results. Assuming a first preset similarity of 0.85, it can be determined that the similarity between the first and second results is greater than the first preset similarity. Therefore, the terminal device determines that the performance of the first model meets the modulation and demodulation performance requirements of the communication system.

[0383] The terminal device can also generate a CSI report and send it to the network device, so that the network device can determine the performance of the first model based on the CSI report. Based on any of the above embodiments, the following, in conjunction with... Figure 3 This section explains the process by which terminal devices send CSI reports to network devices.

[0384] Figure 3 This is a flowchart illustrating a communication method provided in an embodiment of this application. Please refer to [link / reference]. Figure 3 The method includes:

[0385] S301. The terminal device encodes the first CSI according to a preset method to obtain the first encoding result.

[0386] The default method is to not use the first model for encoding processing.

[0387] For example, the preset method can be a method predefined or specified by the protocol. It is understood that the preset method can also be other possible methods, which are only examples here and are not limited in this application.

[0388] For example, encoding CSI using a preset method may include at least one of the following: CSI compression, channel coding, or modulation. Decoding the encoded result using a preset method may include at least one of the following: channel decoding, demodulation, or CSI decompression.

[0389] Below, in conjunction with Figure 4A The process of obtaining the first encoding result is explained.

[0390] Figure 4A This is a schematic diagram illustrating a process for determining a first encoding result, provided in an embodiment of this application. Please refer to... Figure 4A The terminal device generates a CSI report based on the CSI. The terminal device encodes the CSI report / CSI using a preset method to obtain a first encoding result. The terminal device sends the first encoding result to the network device. After receiving the first encoding result, the network device can decode it using a preset method to obtain the CSI report / CSI. Encoding the CSI report / CSI using the preset method may include at least one of the following: CSI compression processing, channel coding processing, or modulation processing. Decoding the encoded result using the preset method may include at least one of the following: channel decoding processing, demodulation processing, or CSI decompression processing. CSI compression processing and CSI decompression processing can be optional steps. This is only an example, and this application does not limit the scope of the application.

[0391] S302. The terminal device encodes the first CSI using the first model to obtain the second encoding result.

[0392] Below, in conjunction with Figures 4B-4C The process of obtaining the second encoding result is explained.

[0393] Figure 4B This is a schematic diagram illustrating a process for determining a second encoding result, provided as an embodiment of this application. Please refer to... Figure 4B The terminal device generates a CSI report based on the CSI. The terminal device encodes the CSI / CSI report using a first model (e.g., compression and channel coding) and modulates the processed CSI / CSI report using a predefined protocol method to obtain a second encoding result. The terminal device sends the second encoding result to the network device. Upon receiving the second encoding result, the network device demodulates it using a preset method and decodes the demodulated second encoding result using the first model to obtain the CSI report / CSI.

[0394] Figure 4C This is a schematic diagram illustrating another process for determining the second encoding result provided in an embodiment of this application. Please refer to... Figure 4C The terminal device generates a CSI report based on the CSI. The terminal device encodes the CSI / CSI report using a first model (e.g., compression, channel coding, and modulation) to obtain a second encoding result. The terminal device sends the second encoding result to the network device. Upon receiving the second encoding result, the network device decodes it using the first model (e.g., demodulation, channel decoding, and decompression) to obtain the CSI / CSI report.

[0395] S303, The terminal device sends the first encoding result and / or the second encoding result to the network device.

[0396] Correspondingly, the network device receives the first encoding result and / or the second encoding result sent by the terminal device.

[0397] For example, the first encoding result and the second encoding result can be sent simultaneously or at different times. The first encoding result and the second encoding result can be sent using the same signaling or different signaling. This application does not impose any restrictions.

[0398] In one possible implementation, the first encoding result and / or the second encoding result are sent by sending a CSI report, which includes the first encoding result and / or the second encoding result.

[0399] For example, the transmission resources of the first encoding result and the second encoding result may partially overlap or not overlap. The transmission resources may include at least one of time-domain transmission resources, frequency-domain transmission resources, and code-domain transmission resources.

[0400] In one possible implementation, the first encoding result has a higher priority than the second encoding result, or vice versa. It is understood that if transmission resources are limited, the decision to send the first encoding result and / or the second encoding result can be based on priority.

[0401] For example, if transmission resources are limited, low-priority encoding results can be discarded, or high-priority encoding results can be discarded, or low-priority encoding results can be sent, or high-priority encoding results can be sent, or low-priority encoding results can be sent but high-priority encoding results can be not sent, or high-priority encoding results can be sent but low-priority encoding results can be not sent.

[0402] In one possible implementation, the first encoding result and / or the second encoding result are sent by: sending a first CSI report, the first CSI report including the first encoding result; and / or sending a second CSI report, the second CSI report including the second encoding result.

[0403] The terminal device can also receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0404] For example, the instruction information may be sent by the network device to the terminal device or preset by the protocol.

[0405] In one possible implementation, the indication information is sent from the network device to the terminal device, and the indication information is carried in at least one of the following: Radio Resource Control (RRC) signaling; Medium Access Control (MAC) signaling; or Downlink Control Information (DCI).

[0406] For example, a terminal device may obtain indication information through at least one of the following methods: The terminal device obtains RRC signaling sent by the network device, where the RRC signaling carries indication information. Alternatively, the terminal device obtains MAC signaling sent by the network device, where the MAC signaling carries indication information. Alternatively, the terminal device obtains DCI sent by the network device, where the DCI carries indication information. Alternatively, the network device obtains indication information through a pre-defined protocol method.

[0407] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following: the triggering states associated with the first CSI report and the second CSI report are the same; the code point values ​​of the fields of the DCI that trigger the first CSI report and the second CSI report are the same; or, the DCIs that trigger the first CSI report and the second CSI report are the same.

[0408] For example, the first CSI report and the second CSI report are associated with the same trigger state, and the first CSI report and the second CSI report can be triggered by the same trigger state (e.g., trigger state).

[0409] For example, the first CSI report and the second CSI report can be triggered at the same time or under the same conditions. That is, the first CSI report and / or the second CSI report are sent under the same triggering state. Furthermore, the time interval for sending the first CSI report is the same as the time interval for sending the second CSI report. Alternatively, the first CSI report and / or the second CSI report are sent when a preset event occurs. Or, the first CSI report and / or the second CSI report are sent when the channel quality threshold is less than or equal to a preset threshold. Here, the preset event is a change in channel quality.

[0410] In one possible implementation, the first transmission resource of the first CSI report and the second transmission resource of the second CSI report do not overlap; or, the first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0411] For example, the transmission resources include at least one of time-domain transmission resources, frequency-domain transmission resources, or code-domain transmission resources.

[0412] For example, the fact that the first transmission resource and the second transmission resource do not overlap indicates that the transmission resources corresponding to each item in the first transmission resource and each item in the second transmission resource do not overlap.

[0413] For example, suppose the transmission resources include time-domain transmission resources, frequency-domain transmission resources, and code-domain transmission resources. If the time-domain transmission resources of the first transmission resource and the second transmission resource, the frequency-domain transmission resources of the first transmission resource and the second transmission resource, and the code-domain transmission resources of the first transmission resource and the second transmission resource do not overlap, then it is determined that the first transmission resource and the second transmission resource do not overlap.

[0414] For example, the first transmission resource of the first CSI report includes time-domain transmission resource 1, frequency-domain transmission resource 1, and code-domain transmission resource 1. The second transmission resource of the second CSI report includes time-domain transmission resource 2, frequency-domain transmission resource 2, and code-domain transmission resource 2. Therefore, it can be determined that the first transmission resource of the first CSI report and the second transmission resource of the second CSI report do not overlap.

[0415] For example, suppose the transmission resources include time-domain transmission resources and frequency-domain transmission resources. If the time-domain transmission resources of the first transmission resource and the second transmission resource do not overlap, and the frequency-domain transmission resources of the first transmission resource and the second transmission resource do not overlap, then it is determined that the first transmission resource and the second transmission resource do not overlap.

[0416] For example, suppose the transmission resources include time-domain transmission resources. If the time-domain transmission resources of the first transmission resource and the second transmission resource do not overlap, then it is determined that the first transmission resource and the second transmission resource do not overlap.

[0417] For example, the partial overlap of the first transmission resource and the second transmission resource may include at least one of time-domain transmission resource overlap, frequency-domain transmission resource overlap, or code-domain transmission resource overlap. Specifically, time-domain resource overlap includes time-domain transmission resource overlap or complete overlap, frequency-domain transmission resource overlap includes frequency-domain transmission resource overlap or complete overlap, and code-domain transmission resource overlap includes code-domain transmission resource overlap or complete overlap.

[0418] For example, the first transmission resource in the first CSI report includes time-domain transmission resource 1, frequency-domain transmission resource 1, and code-domain transmission resource 1. The second transmission resource in the second CSI report includes time-domain transmission resource 1, frequency-domain transmission resource 2, and code-domain transmission resource 2. Where the time-domain transmission resources of the first and second transmission resources completely overlap, the frequency-domain transmission resources of the first and second transmission resources do not overlap, and the code-domain transmission resources of the first and second transmission resources do not overlap, then it is determined that the first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0419] For example, the first transmission resource in the first CSI report includes time-domain transmission resource 1, frequency-domain transmission resource A1, and code-domain transmission resource 1. The second transmission resource in the second CSI report includes time-domain transmission resource 2, frequency-domain transmission resource A2, and code-domain transmission resource 2. Where the time-domain transmission resources of the first and second transmission resources do not overlap, the frequency-domain transmission resources of the first and second transmission resources partially overlap, and the code-domain transmission resources of the first and second transmission resources do not overlap, then it is determined that the first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0420] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report overlap or partially overlap. The terminal device may discard the first CSI report, or discard the second CSI report, or send the first CSI report, or send the second CSI report, or send the first CSI report but not the second CSI report, or send the second CSI report but not the first CSI report.

[0421] For example, sending a first CSI report or a second CSI report, or not sending a first CSI report or a second CSI report, or discarding a first CSI report or a second CSI report, can be determined based on the priority of the first CSI report and the second CSI report, and this application does not impose any restrictions.

[0422] It should be noted that, Figure 3 The steps shown in the embodiments are optional. Figure 3 The steps shown in the embodiments can exist independently or in combination with each other. Figure 3 There is no requirement for the order of the steps shown in the embodiments. They are only examples and this application does not limit them.

[0423] For example, in practical applications, S301 and S302 can be executed simultaneously, or S301 can be executed first and then S302, or S302 can be executed first and then S301. The execution of S303 can be determined based on the execution results of S301 and S302. For example, executing S301 can lead to the transmission of the first encoded result in S303; executing S302 can lead to the transmission of the second encoded result in S303. There is no specific order requirement between transmitting the first encoded result in S303 and executing S302; there is no specific order requirement between transmitting the second encoded result in S303 and executing S301. This is only an example, and this application does not impose any limitations on this.

[0424] The communication method provided in this application embodiment involves a terminal device sending a first encoding result and / or a second encoding result to a network device. This allows the network device to monitor the performance of a first model using the first and / or second encoding results. This avoids communication failures caused by anomalies in the first model during its use, thus improving communication efficiency.

[0425] Below, in conjunction with Figure 5 The detailed process of determining the performance of the first model for network devices is explained.

[0426] Figure 5 This is a flowchart illustrating another performance determination method provided in an embodiment of this application. Please refer to... Figure 5 The method includes:

[0427] S501. Determine the performance of the first model based on the first information.

[0428] The execution entity in this application embodiment can be a network device, or a chip, chip module, or performance determination device disposed in the network device. The performance determination device can be implemented by software or by a combination of software and hardware. The network device can be a base station.

[0429] The first information includes at least one of the following: communication performance; proxy model; or, CSI report;

[0430] The first model is used for encoding and / or decoding the second information, and the surrogate model is used to simulate the encoder and / or decoder.

[0431] It should be noted that the second information, communication performance, and proxy model can be found in the description of any of the above embodiments, and will not be repeated here.

[0432] It should be noted that the execution process of determining the performance of the first model based on communication performance can be found in S201, which will not be repeated here.

[0433] In one possible implementation, the first information includes a proxy model, and the performance of the first model is determined based on the first information by: obtaining intermediate results processed by the first model; obtaining proxy results processed by the proxy model; and determining the performance of the first model based on result indication information, wherein the result indication information includes at least one of the second information, intermediate results, or proxy results.

[0434] For example, taking a proxy model used in an analog decoder, the performance of determining the first model is described. The intermediate result of the first model encoding the second information is obtained. The proxy result of the proxy model decoding the intermediate result is obtained. Then, based on the result indication information, the performance of the first model is determined.

[0435] For example, taking a surrogate model used to simulate an encoder, the performance of the first model is determined. The surrogate result of the surrogate model encoding the second information is obtained. The intermediate result of the first model decoding the surrogate result is obtained. Then, based on the result indication information, the performance of the first model is determined.

[0436] For example, taking a surrogate model used to simulate an encoder and decoder, the performance of the first model is described. The intermediate results of the first model processing the second information are obtained, as well as the surrogate results of the surrogate model processing the second information. Then, based on the result indication information, the performance of the first model is determined.

[0437] For example, determining the performance of the first model based on the results information includes at least one of the following methods:

[0438] Method 1: If the surrogate model is used to simulate the encoder, the performance of the first model is determined based on the similarity between the intermediate results and the second information.

[0439] If the similarity between the intermediate result and the second information is greater than or equal to the third preset similarity, then the performance of the first model meets the modulation and demodulation performance requirements of the communication system. If the similarity between the intermediate result and the second information is less than the third preset similarity, then the performance of the first model does not meet the modulation and demodulation performance requirements of the communication system.

[0440] Method 2: Determine the performance of the first model based on the similarity between the intermediate results and the proxy results.

[0441] If the similarity between the intermediate result and the proxy result is greater than or equal to the fourth preset similarity, then the performance of the first model is determined to meet the modulation and demodulation performance requirements of the communication system. If the similarity between the intermediate result and the proxy result is less than the fourth preset similarity, then the performance of the first model is determined to not meet the modulation and demodulation performance requirements of the communication system.

[0442] For example, the third and fourth preset similarities may be, but are not limited to, predefined, obtained based on network configuration information, based on DCI indications, or based on terminal device capability reports.

[0443] For example, suppose a proxy model is used to simulate an encoder. The terminal device obtains the intermediate result of the proxy model encoding the second information. It then obtains the second result of the proxy model decoding the first result. The terminal device finds a similarity of 0.9 between the first and second results. Assuming a first preset similarity of 0.85, it can be determined that the similarity between the first and second results is greater than the first preset similarity. Therefore, the terminal device determines that the performance of the first model meets the modulation and demodulation performance requirements of the communication system.

[0444] Before determining the performance of the first model based on the CSI report, the network device receives the CSI report, which includes the first encoding result and / or the second encoding result;

[0445] The first encoding result is the encoding result obtained by encoding the first CSI according to a preset method; the second encoding result is the encoding result obtained by encoding the first CSI according to a first model; the first CSI is the CSI generated by the terminal device; the preset method is the method of not using the first model for encoding processing.

[0446] The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0447] The CSI report includes a first CSI report and a second CSI report. Before determining the performance of the first model based on the CSI report, the network device may also receive the first CSI report, which includes a first encoding result; and / or receive the second CSI report, which includes a second encoding result.

[0448] The first encoding result is the encoding result obtained by encoding the first CSI according to a preset method; the second encoding result is the encoding result obtained by encoding the first CSI according to the first model; the first CSI is the CSI generated by the terminal device.

[0449] For example, the preset method can be as described above. Figure 4AAs shown in the diagram.

[0450] Network devices can determine the correlation between the first CSI report and the second CSI report, and then send indication information to the terminal device.

[0451] In one possible implementation, an indication message is sent to indicate that the first CSI report and the second CSI report are related.

[0452] It should be noted that the specific information required by the indication information, the first CSI report, and the second CSI report can be found in any of the above embodiments, and will not be repeated here.

[0453] The network device can determine the correlation between the first CSI report and the second CSI report based on the indication information. Thus, the network device can determine the second encoding result corresponding to the first encoding result based on the correlated first and second CSI reports. That is, the first encoding result and the corresponding second encoding result are encoding results obtained from the same CSI processing. This allows the network device to determine the performance of the first model based on the first encoding result and the corresponding second encoding result.

[0454] In one possible implementation, the first information includes a CSI report, which includes a first encoding result and a second encoding result. The performance of the first model can be determined based on the first information as follows: determining the first encoding result and the second encoding result based on the CSI report; decoding the first encoding result using a preset method to obtain the second CSI corresponding to the first CSI; decoding the second encoding result using the first model to obtain the third CSI corresponding to the first CSI; obtaining the similarity between the second CSI and the third CSI; and determining the performance of the first model based on the similarity between the second CSI and the third CSI.

[0455] For example, if the similarity between the second CSI and the third CSI is greater than or equal to a fifth preset similarity, it can be determined that the performance of the first model meets the modulation and demodulation performance requirements of the communication system. If the similarity between the second CSI and the third CSI is less than the fifth preset similarity, it can be determined that the performance of the first model does not meet the modulation and demodulation performance requirements of the communication system.

[0456] For example, the third and fourth preset similarities may be, but are not limited to, predefined, obtained based on network configuration information, based on DCI indications, or based on terminal device capability reports.

[0457] For example, the CSI report includes encoding result 1 and encoding result 2. Encoding result 1 is the encoding result obtained by encoding the first CSI according to a preset method. Encoding result 2 is the encoding result obtained by encoding the first CSI according to a first model. Decoding encoding result 1 using the preset method yields the second CSI corresponding to the first CSI, and decoding encoding result 2 using the first model yields the third CSI corresponding to the first CSI. The similarity between the second and third CSIs is found to be 0.95. Assuming a fifth preset similarity of 0.9, it can be determined that the performance of the first model meets the modulation and demodulation performance requirements of the communication system.

[0458] The performance determination method provided in this application allows a network device to determine the performance of a first model based on first information. This enables the network device to monitor the performance of the first model and determine its performance during communication. It avoids communication failures caused by anomalies in the first model during its use, thus improving communication efficiency.

[0459] During communication, network devices and terminal devices can determine the performance of the first model. Based on any of the above embodiments, the following, in conjunction with... Figure 6 This paper describes the process by which network devices and terminal devices determine the performance of the first model during communication.

[0460] Figure 6 This is a flowchart illustrating another performance determination method provided in an embodiment of this application. Please refer to... Figure 6 The method includes:

[0461] S601, terminal equipment and network equipment communicate to determine communication performance.

[0462] For example, terminal devices and network devices can determine communication performance through data transmission.

[0463] For example, terminal devices and network devices can communicate by sending or receiving messages or signals.

[0464] S602. The terminal device determines the performance of the first model based on communication performance and / or proxy model.

[0465] It should be noted that the execution process of S602 can be found in S201, and will not be repeated here.

[0466] S603. The terminal device sends a CSI report to the network device, or the terminal device sends a first CSI report and / or a second CSI report to the network device.

[0467] Accordingly, the network device receives the CSI report sent by the terminal device, or the network device receives the first CSI report and / or the second CSI report sent by the terminal device.

[0468] For example, a terminal device sends a CSI report to a network device, the CSI report including a first encoding result and / or a second encoding result.

[0469] For example, the terminal device sends a first CSI report and / or a second CSI report to the network device. The first CSI report includes a first encoding result, and / or the second CSI report includes a second encoding result.

[0470] It should be noted that the execution process of S603 can be referred to any of the above embodiments, and will not be repeated here.

[0471] S604. The network device determines the performance of the first model based on the first information.

[0472] It should be noted that the execution process of S604 can be found in S401, and will not be repeated here.

[0473] It should be noted that, Figure 6 The steps shown in the embodiments are optional. Figure 6 The steps shown in the embodiments can exist independently or in combination with each other. Figure 6 There is no requirement for the order of the steps shown in the embodiments. This is only an example and is not intended to be limiting.

[0474] In this embodiment, the terminal device and the network device can determine the performance of the first model through communication performance and / or a proxy model. The network device can also determine the performance of the first model based on the CSI report sent by the terminal device. The first model is used for encoding and / or decoding the second information, and the proxy model is used to simulate an encoder and / or decoder. In this way, the network device and the terminal device can monitor the performance of the first model, thus determining its performance during communication.

[0475] Figure 7 This is a schematic diagram of a performance determination device provided in an embodiment of this application. The performance determination device 10 can be a terminal device, or a chip or chip module in the terminal device. Please refer to... Figure 7 The performance determining device 10 may include:

[0476] Module 11 is used to determine the performance of the first model based on communication performance and / or proxy model;

[0477] Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0478] In one possible implementation, the second information includes at least one of the following:

[0479] Joint sources; or,

[0480] Channel information.

[0481] In one possible implementation, the communication performance includes at least one of the following:

[0482] Signal-to-noise ratio (SNR) of the received signal;

[0483] The distribution characteristics of the channel information;

[0484] Bit error rate;

[0485] Block error rate; or,

[0486] The probability of a non-response to a hybrid automatic repeat request.

[0487] In one possible implementation, the determining module 11 is specifically used for:

[0488] Obtain the first result processed by the first model;

[0489] Obtain the second result of the proxy model processing;

[0490] Based on the results, determine the performance of the first model;

[0491] The result information includes at least one of the second information, the first result, or the second result.

[0492] The performance determination device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0493] Figure 8 This is a schematic diagram of another performance determination device provided in an embodiment of this application. Figure 7 Based on the illustrated embodiments, please refer to Figure 8 The performance determination device 10 also includes a transmitting module 12 and a receiving module 13.

[0494] The sending module 12 is used for:

[0495] According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing;

[0496] The first CSI is encoded using the first model to obtain the second encoding result;

[0497] Send the first encoding result and / or the second encoding result.

[0498] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0499] The sending module 12 is used for:

[0500] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0501] The sending module 12 is used for:

[0502] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0503] Send a second CSI report, which includes the second encoding result.

[0504] The receiving module 13 is used for:

[0505] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0506] In one possible implementation, the indication information is carried in at least one of the following:

[0507] Radio Resource Control (RRC) signaling;

[0508] Media access control MAC signaling; or,

[0509] Downlink Control Information (DCI).

[0510] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0511] The first CSI report and the second CSI report are associated with the same trigger state;

[0512] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0513] The DCI that triggers the first CSI report and the second CSI report is the same.

[0514] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0515] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0516] The sending module is used for:

[0517] Discard the first CSI report; or,

[0518] Discard the second CSI report; or,

[0519] Send the first CSI report; or,

[0520] Send a second CSI report; or,

[0521] Send the first CSI report, but do not send the second CSI report; or,

[0522] Send the second CSI report, but do not send the first CSI report.

[0523] The performance determination device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0524] Figure 9 This is a schematic diagram of a communication device provided in an embodiment of this application. The communication device 20 can be a terminal device, or a chip or chip module within a terminal device. Please refer to... Figure 9 The communication device 20 may include:

[0525] The first processing module 21 is used to encode the first CSI according to a preset method to obtain a first encoding result, wherein the preset method is a method of encoding without using the first model;

[0526] The second processing module 22 is used to encode the first CSI using the first model to obtain a second encoding result;

[0527] The sending module 23 is used to send the first encoding result and / or the second encoding result.

[0528] In one possible implementation, the priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0529] In one possible implementation, the sending module 23 is specifically used for:

[0530] Send a CSI report, which includes the first encoding result and / or the second encoding result.

[0531] In one possible implementation, the sending module 23 is specifically used for:

[0532] Send a first CSI report, the first CSI report including the first encoding result; and / or,

[0533] Send a second CSI report, which includes the second encoding result.

[0534] The communication device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0535] Figure 10 This is a schematic diagram of another communication device provided in an embodiment of this application. The communication device 20 can be a terminal device, or a chip or chip module within a terminal device. Figure 9 Based on the illustrated embodiments, please refer to Figure 10 The communication device 20 also includes a receiving module.

[0536] The receiving module 24 is used for:

[0537] Receive indication information, which indicates that the first CSI report and the second CSI report are related.

[0538] In one possible implementation, the indication information is carried in at least one of the following:

[0539] Radio Resource Control (RRC) signaling;

[0540] Media access control MAC signaling; or,

[0541] Downlink Control Information (DCI).

[0542] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0543] The first CSI report and the second CSI report are associated with the same trigger state;

[0544] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0545] The DCI that triggers the first CSI report and the second CSI report is the same.

[0546] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0547] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0548] The sending module 23 is further configured to:

[0549] Discard the first CSI report; or,

[0550] Discard the second CSI report; or,

[0551] Send the first CSI report; or,

[0552] Send a second CSI report; or,

[0553] Send the first CSI report, but do not send the second CSI report; or,

[0554] Send the second CSI report, but do not send the first CSI report.

[0555] The communication device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0556] Figure 11 This is a schematic diagram illustrating the structure of another performance determination device provided in an embodiment of this application. The performance determination device 30 can be a network device, or a chip or chip module within a network device. Please refer to... Figure 11 The performance determining device 30 may include:

[0557] The determination module 31 is used to determine the performance of the first model based on the first information;

[0558] The first information includes at least one of the following: communication performance; proxy model; or, CSI report;

[0559] Wherein, the first model is used for encoding and / or decoding the second information, and the proxy model is used to simulate the encoder and / or decoder.

[0560] In one possible implementation, the second information includes at least one of the following:

[0561] Joint sources; or,

[0562] Channel information.

[0563] In one possible implementation, the communication performance includes at least one of the following:

[0564] Signal-to-noise ratio (SNR) of the received signal;

[0565] The distribution characteristics of the channel information;

[0566] Bit error rate;

[0567] Block error rate; or,

[0568] The probability of a non-response to a hybrid automatic repeat request.

[0569] In one possible implementation, the determining module 31 is specifically used for:

[0570] Obtain the intermediate results processed by the first model;

[0571] Obtain the proxy result processed by the proxy model;

[0572] The performance of the first model is determined based on the result indication information, wherein the result indication information includes at least one of the second information, the intermediate result, or the proxy result.

[0573] In one possible implementation, the determining module 31 is specifically used for:

[0574] Based on the CSI report, the first encoding result and the second encoding result are determined;

[0575] The first encoding result is decoded using the preset method to obtain the second CSI corresponding to the first CSI.

[0576] The third CSI corresponding to the first CSI is obtained by decoding the second encoding result using the first model.

[0577] Obtain the similarity between the second CSI and the third CSI;

[0578] The performance of the first model is determined based on the similarity between the second CSI and the third CSI.

[0579] The performance determination device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0580] Figure 12 This is a schematic diagram of another performance determination device provided in an embodiment of this application. Figure 11 Based on the illustrated embodiments, please refer to Figure 12 The performance determination device 30 also includes a receiving module 32 and a transmitting module 33.

[0581] The receiving module 32 is used for:

[0582] Receive the CSI report, which includes a first encoding result and / or a second encoding result.

[0583] The receiving module 32 is used for:

[0584] Receive the first CSI report, the first CSI report including the first encoding result; and / or,

[0585] Receive the second CSI report, which includes the second encoding result.

[0586] The sending module 33 is used for:

[0587] Send indication information, which indicates that the first CSI report and the second CSI report are related.

[0588] In one possible implementation, the indication information is carried in at least one of the following:

[0589] Radio Resource Control (RRC) signaling;

[0590] Media access control MAC signaling; or,

[0591] Downlink Control Information (DCI).

[0592] In one possible implementation, the first CSI report and the second CSI report satisfy at least one of the following:

[0593] The first CSI report and the second CSI report are associated with the same trigger state;

[0594] The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or,

[0595] The DCI that triggers the first CSI report and the second CSI report is the same.

[0596] In one possible implementation, the first transmission resources of the first CSI report and the second transmission resources of the second CSI report do not overlap; or...

[0597] The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

[0598] In one possible implementation, the first encoding result is the encoding result obtained by encoding the first CSI according to a preset method;

[0599] The second encoding result is the encoding result obtained by encoding the first CSI according to the first model;

[0600] The first CSI is the CSI generated by the terminal device;

[0601] The preset method is to not use the first model for encoding processing;

[0602] The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

[0603] The performance determination device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0604] Figure 13 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. The terminal device can be exemplarily described above. Please refer to... Figure 13 The terminal device 40 includes a transceiver 41, a memory 42, and a processor 44. The transceiver 41 may include a transmitter and / or a receiver. The transmitter may also be referred to as a transmitter, transmitter, transmitting port, or transmitting interface, and the receiver may also be referred to as a receiver, receiver, receiving port, or receiving interface, etc. Exemplarily, the transceiver 41, memory 42, and processor 43 are interconnected via a bus 44.

[0605] Memory 42 is used to store program instructions;

[0606] The processor 43 is used to execute the program instructions stored in the memory so that the terminal device 40 performs any of the communication methods shown above.

[0607] The transceiver 41 is used to perform the transmit and receive functions of the terminal device 40 in the above communication method.

[0608] The terminal device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0609] Figure 14 This is a schematic diagram of the structure of a network device provided in an embodiment of this application. The network device can be exemplarily described above. Please refer to... Figure 14 The network device 50 includes a transceiver 51, a memory 52, and a processor 53. The transceiver 51 may include a transmitter and / or a receiver. The transmitter may also be referred to as a transmitter, transmitter port, or transmitter interface, etc., and the receiver may also be referred to as a receiver, receiver port, or receiver interface, etc. Exemplarily, the transceiver 51, memory 52, and processor 53 are interconnected via a bus 54.

[0610] Memory 52 is used to store program instructions;

[0611] The processor 53 is used to execute the program instructions stored in the memory to cause the network device 40 to perform any of the communication methods shown above.

[0612] The transceiver 51 is used to perform the transmit and receive functions of the network device 50 in the above communication method.

[0613] The network device provided in this application embodiment can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar, and will not be described again here.

[0614] This application provides a chip, which includes at least one processor, the processor being configured to execute program instructions to perform the methods described in any of the above embodiments.

[0615] This application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above-described method when executed by a processor.

[0616] This application embodiment may also provide a computer program product, including a computer program that, when executed by a processor, can implement the above-described method.

[0617] All or part of the steps in the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, it performs the steps of the above-described method embodiments; and the aforementioned memory (storage medium) includes: read-only memory (ROM), random access memory (RAM), flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0618] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0619] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0620] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0621] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

[0622] In this application, the term "comprising" and its variations can refer to non-limiting inclusion; the term "or" and its variations can refer to "and / or". The terms "first", "second", etc., in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

Claims

1. A method for determining performance, characterized in that, include: Based on the first information, determine the performance of the first model; The first information includes at least one of the following: communication performance; proxy model; or, CSI report; Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

2. The method according to claim 1, characterized in that, The second information includes at least one of the following: Joint sources; or, Channel information.

3. The method according to claim 1, characterized in that, The communication performance includes at least one of the following: Signal-to-noise ratio (SNR) of the received signal; The distribution characteristics of the channel information; Bit error rate; Block error rate; or, The probability of a non-response to a hybrid automatic repeat request.

4. The method according to claim 1, characterized in that, The first information includes the proxy model; determining the performance of the first model based on the first information includes: Obtain the first result processed by the first model; Obtain the second result of the proxy model processing; Based on the results, determine the performance of the first model; The result information includes at least one of the second information, the first result, or the second result.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Send the CSI report, which includes a first encoding result and / or a second encoding result.

6. The method according to any one of claims 1-4, characterized in that, The CSI report includes a first CSI report and / or a second CSI report; the method further includes: Send the first CSI report, the first CSI report including the first encoding result; and / or, Send the second CSI report, which includes the second encoding result.

7. The method according to any one of claims 1-4, characterized in that, The method further includes: Receive the CSI report, which includes a first encoding result and / or a second encoding result.

8. The method according to any one of claims 1-4, characterized in that, The CSI report includes a first CSI report and / or a second CSI report; the method further includes: Receive the first CSI report, the first CSI report including the first encoding result; and / or, Receive the second CSI report, which includes the second encoding result.

9. The method according to any one of claims 5-8, characterized in that, The first encoding result is the encoding result obtained by encoding the first CSI according to a preset method; The second encoding result is the encoding result obtained by encoding the first CSI according to the first model; The preset method is to not use the first model for encoding processing.

10. The method according to any one of claims 5-9, characterized in that, The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

11. The method according to claim 6 or 8, characterized in that, The first CSI report and the second CSI report satisfy at least one of the following: The first CSI report and the second CSI report are associated with the same trigger state; The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or, The DCI that triggers the first CSI report and the second CSI report is the same.

12. The method according to claim 11, characterized in that, The first transmission resource of the first CSI report and the second transmission resource of the second CSI report do not overlap; or, The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

13. The method according to any one of claims 5-12, characterized in that, The first information includes the CSI report; Based on the first information, determine the performance of the first model, including: Based on the CSI report, the first encoding result and the second encoding result are determined; The first encoding result is decoded using a preset method to obtain the second CSI corresponding to the first CSI. The third CSI corresponding to the first CSI is obtained by decoding the second encoding result using the first model. Obtain the similarity between the second CSI and the third CSI; The performance of the first model is determined based on the similarity between the second CSI and the third CSI.

14. A communication method, characterized in that, include: According to a preset method, the first CSI is encoded to obtain a first encoding result, wherein the preset method is a method that does not use the first model for encoding processing; The first CSI is encoded using the first model to obtain the second encoding result; Send the first encoding result and / or the second encoding result.

15. The method according to claim 14, characterized in that, The priority of the first encoding result is higher than the priority of the second encoding result, or the priority of the first encoding result is lower than the priority of the second encoding result.

16. The method according to claim 14 or 15, characterized in that, Sending the first encoded result and / or the second encoded result includes: Send a CSI report, which includes the first encoding result and / or the second encoding result.

17. The method according to claim 14 or 15, characterized in that, Sending the first encoded result and / or the second encoded result includes: Send a first CSI report, the first CSI report including the first encoding result; and / or, Send a second CSI report, which includes the second encoding result.

18. The method according to claim 17, characterized in that, The method further includes: Receive indication information, which indicates that the first CSI report and the second CSI report are related.

19. The method according to claim 18, characterized in that, The indication information is carried in at least one of the following: Radio Resource Control (RRC) signaling; Media access control MAC signaling; or, Downlink Control Information (DCI).

20. The method according to any one of claims 17-19, characterized in that, The first CSI report and the second CSI report satisfy at least one of the following: The first CSI report and the second CSI report are associated with the same trigger state; The code point values ​​of the DCI fields that trigger the first CSI report and the second CSI report are the same; or, The DCI that triggers the first CSI report and the second CSI report is the same.

21. The method according to claims 17-20, characterized in that, The first transmission resource of the first CSI report and the second transmission resource of the second CSI report do not overlap; or, The first transmission resource of the first CSI report and the second transmission resource of the second CSI report partially overlap.

22. The method according to any one of claims 17-21, characterized in that, The method further includes: The first transmission resource and the second transmission resource overlap or partially overlap. Discard the first CSI report; or, Discard the second CSI report; or, Send the first CSI report; or, Send a second CSI report; or, Send the first CSI report, but do not send the second CSI report; or, Send the second CSI report, but do not send the first CSI report.

23. A performance determination device, characterized in that, The device includes: The determination module is used to determine the performance of the first model based on the first information; The first information includes at least one of the following: communication performance; proxy model; or, CSI report; Wherein, the first model is used to encode and / or decode the second information, and the proxy model is used to simulate the encoder and / or decoder.

24. A communication device, characterized in that, The device includes: The first processing module is used to encode the first CSI according to a preset method to obtain a first encoding result, wherein the preset method is a method of encoding without using the first model; The second processing module is used to encode the first CSI using the first model to obtain a second encoding result; A sending module is used to send the first encoding result and / or the second encoding result.

25. A terminal device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1 to 6, or any one of claims 14 to 22.

26. A network device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 4, or any one of claims 7 to 13.

27. A chip comprising at least one processor, the processor being configured to execute program instructions to perform the method of any one of claims 1 to 13, or any one of claims 14 to 22.

28. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 13, or any one of claims 14 to 22.

29. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements any one of claims 1 to 13, or any one of claims 14 to 22.

Images