Information transmission method and apparatus, and storage medium

Abstract

The present disclosure provides an information transmission method and apparatus, and a storage medium. The method comprises: determining reporting information meeting a reporting condition, the reporting information being used for training an artificial intelligence model or being used for determining a beam / beam pair having an optimal transmission signal; and splitting the reporting information into a first part of information and a second part of information and sending same to a network device.

Description

Information transmission method, device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number 202310723470.X, filed on June 16, 2023, entitled “Information Transmission Method, Device and Storage Medium,” which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates to the field of communication technologies, and in particular to an information transmission method, device, and storage medium. Background Art

[0004] Currently, artificial intelligence (AI / ML)-based beam management requires the terminal / user equipment (UE) to report X layer 1 reference signal received powers (L1-RSRP) and the corresponding X reference signal indices to the network device, or report the optimal K (Top-K) beams or beam pairs obtained through model inference.

[0005] To reduce UE feedback overhead, some proposals suggest that the UE can report the L1-RSRP of only some beams / beam pairs, or reduce the number of optimal beams / beam pairs reported. In other words, X and K are configured by the base station and can be set to smaller values.

[0006] However, although the above solution can reduce the UE's feedback overhead, it cannot guarantee the performance of the AI / ML model.

[0007] Summary of the Invention

[0008] The embodiments of the present disclosure provide an information transmission method, device, and storage medium to solve the technical problem of poor performance of AI / ML models in related technologies.

[0009] In a first aspect, an embodiment of the present disclosure provides an information transmission method, applied to a terminal, comprising:

[0010] Determining reporting information that meets reporting conditions; the reporting information is used for training an artificial intelligence model or for determining a beam / beam pair that optimizes the transmission signal;

[0011] The reported information is divided into a first part of information and a second part of information and sent to the network device.

[0012] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0013] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0014] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0015] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0016] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0017] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0018] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0019] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0020] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0021] In some embodiments, the method further comprises:

[0022] Perform model inference based on the trained AI model to determine the confidence level of each beam / beam pair output by the AI ​​model;

[0023] The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

[0024] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0025] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0026] In a second aspect, an embodiment of the present disclosure provides an information transmission method, applied to a network device, comprising:

[0027] Obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0028] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0029] In some embodiments, the method further comprises:

[0030] Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions;

[0031] The artificial intelligence model is trained using the training samples.

[0032] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0033] In some embodiments, the method further comprises:

[0034] Beam scanning is performed according to the index of the beam / beam pair that meets the reporting conditions; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0035] Obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0036] In a third aspect, an embodiment of the present disclosure provides a terminal, including a memory, a transceiver, and a processor;

[0037] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0038] Determining reporting information that meets reporting conditions; the reporting information is used for training an artificial intelligence model or for determining a beam / beam pair that optimizes the transmission signal;

[0039] The reported information is divided into a first part of information and a second part of information and sent to the network device.

[0040] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0041] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0042] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0043] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0044] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0045] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0046] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0047] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0048] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0049] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0050] Perform model inference based on the trained AI model to determine the confidence level of each beam / beam pair output by the AI ​​model;

[0051] The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

[0052] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0053] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0054] In a fourth aspect, an embodiment of the present disclosure provides a network device, including a memory, a transceiver, and a processor;

[0055] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0056] Obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0057] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0058] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0059] Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions;

[0060] The artificial intelligence model is trained using the training samples.

[0061] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0062] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0063] Beam scanning is performed according to the index of the beam / beam pair that meets the reporting conditions; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0064] Obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0065] In a fifth aspect, an embodiment of the present disclosure provides an information transmission device, including:

[0066] A first determination module is configured to determine reporting information that meets a reporting condition; the reporting information is used for training an artificial intelligence model or for determining a beam / beam pair that optimizes a signal transmission;

[0067] The sending module is used to split the reported information into a first part of information and a second part of information and send the second part of information to the network device.

[0068] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0069] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0070] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0071] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0072] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0073] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0074] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0075] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0076] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0077] In some embodiments, the apparatus further comprises a second determination module and a third determination module;

[0078] The second determination module is used to perform model inference based on the trained artificial intelligence model to determine the confidence level corresponding to each beam / beam pair output by the artificial intelligence model;

[0079] The third determination module is configured to determine an index of a beam / beam pair that meets a reporting condition based on a confidence level corresponding to each beam / beam pair.

[0080] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0081] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0082] In a sixth aspect, an embodiment of the present disclosure provides an information transmission device, including:

[0083] The first acquisition module is used to obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0084] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0085] In some embodiments, the apparatus further comprises a fourth determination module and a training module;

[0086] The fourth determining module is used to determine the training samples for model training based on the quality and index of the reference signal that meets the reporting condition;

[0087] The training module is used to train the artificial intelligence model using the training samples.

[0088] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0089] In some embodiments, the apparatus further comprises a beam scanning module and a second acquisition module;

[0090] The beam scanning module is used to perform beam scanning according to the index of the beam / beam pair that meets the reporting conditions; the purpose of performing beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0091] The second acquisition module is used to obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0092] In a seventh aspect, an embodiment of the present disclosure further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the information transmission method described in the first aspect or the second aspect above.

[0093] In an eighth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the information transmission method described in the first aspect or the second aspect above.

[0094] In the ninth aspect, an embodiment of the present disclosure further provides a communication device-readable storage medium, wherein the communication device-readable storage medium stores a computer program, and the computer program is used to enable the communication device to execute the information transmission method described in the first aspect or the second aspect above.

[0095] In the tenth aspect, an embodiment of the present disclosure further provides a chip product readable storage medium, wherein the chip product readable storage medium stores a computer program, and the computer program is used to enable the chip product to execute the information transmission method described in the first aspect or the second aspect above.

[0096] The information transmission method, device and storage medium provided by the embodiments of the present disclosure, when reporting information related to the artificial intelligence model, split the reported information that meets the reporting conditions into a first part of information and a second part of information and send them to the network device, thereby reducing the feedback overhead of the UE and ensuring the performance of the artificial intelligence model. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0098] FIG1 is a flow chart of an information transmission method according to an embodiment of the present disclosure;

[0099] FIG2 is a second flow chart of the information transmission method provided in an embodiment of the present disclosure;

[0100] FIG3 is a schematic structural diagram of a terminal provided by an embodiment of the present disclosure;

[0101] FIG4 is a schematic diagram of the structure of a network device provided by an embodiment of the present disclosure;

[0102] FIG5 is a schematic diagram of a structure of an information transmission device according to an embodiment of the present disclosure;

[0103] FIG6 is a second structural diagram of an information transmission device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0104] In the New Radio (NR) system, to combat path loss in high-frequency scenarios, the transmitter and receiver use beam management (BM) to obtain matching beam pairs to improve beamforming gain. In the related downlink beam management process, the base station is required to cyclically send transmit beams (Tx beams) in different directions. The UE uses a receive beam (Rx beam) to receive the Tx beams and measures the Channel State Information-Reference Signal (CSI-RS) / Synchronization Signal Block (SSB) signals sent on all Tx beams. It selects the X beams (X = 1, 2, 4) with the best reception performance (such as L1-RSRP) and reports the reference signal index information corresponding to these X beams to the base station. Based on the information reported by the UE, the base station selects the appropriate Tx beam for subsequent communication and indicates the selected beam information to the UE.

[0105] To obtain the optimal beam pair, the base station needs to transmit CSI-RS / SSBs on all transmit beams, resulting in significant consumption of reference signal resources. Furthermore, the UE needs to use all receive beams to measure the CSI-RS / SSBs transmitted on all transmit beams, resulting in significant measurement overhead. To address these issues, artificial intelligence (AI / ML) technology has been proposed. Based on measurements of some beams / beam pairs or historical beam / beam pair measurements, the optimal beam / beam pair can be predicted, thereby reducing reference signal (RS) transmission resources, UE measurement overhead, and UE measurement latency.

[0106] Model training / model inference / model monitoring / model update can be done on the base station side or on the UE side. If the model inference is on the base station side, the UE needs to report the measured beam / beam pair quality (such as L1-RSRP) to the base station as model input. If the model training / update is on the base station side, in addition to reporting the measured beam / beam pair quality, the UE also needs to report the label information used for model training. The label information can be the Top-K beam / beam pair indexes or the predicted L1-RSRP of the beam / beam pair set. When the number of reported beams / beam pairs and corresponding L1-RSRPs is large, the reporting overhead is large. If the model inference is on the UE side, the UE needs to report the predicted Top-K beam / beam pair indexes based on the inference results.

[0107] AI / ML-based beam management is one of the research use cases for the air interface AI / ML project. Currently, the following two sub-use cases are considered as sub-use cases for AI / ML beam management:

[0108] BM-case1: Spatial beam prediction, that is, predicting the top-K beams / beam pairs in SetA based on SetB measured at a certain moment;

[0109] BM-case2: Time-domain beam prediction, that is, predicting the Top-K beams / beam pairs of SetA at the next N' moments based on SetB measured at the past N moments.

[0110] SetB and SetA can be sets of downlink transmit beams (DL Tx beams) or sets of transmit-receive beam pairs (Tx-Rx beam pairs). In downlink transmit beam prediction, the UE fixes or selects the best Rx beam and measures the Reference Signal Received Power (RSRP) of a portion of the DL Tx beams (SetB) transmitted by the base station. The base station or UE predicts the Tx beam corresponding to the Top-K RSRP in SetA based on the measurement results of SetB. This is the Top-K downlink transmit beam prediction. In transmit-receive beam pair prediction, a beam pair consisting of a Tx beam of the base station and an Rx beam of the UE is formed. The UE measures the RSRP of the beam pair in SetB. The base station or UE predicts the beam pair corresponding to the Top-K RSRP in SetA based on the measurement results of SetB. This is the Top-K transmit-receive beam pair prediction. The output of the AI / ML model can be the predicted IDs of the top-K beam pairs in SetA or the predicted RSRPs of the beam pairs in SetA. The latter can be used to select the top-K beam pairs based on the predicted RSRPs. SetB can be a subset of SetA or not (for example, SetB has wide beams and SetA has narrow beams).

[0111] The method for reporting L1-RSRP in the relevant Channel State Information (CSI) reporting scheme is as follows: the base station configures the UE with a measurement reference signal and the number of reported reference signals X (X = 1 / 2 / 4). The UE uses a differential method to report the L1-RSRP of the X reference signals (the maximum L1-RSRP uses 7 bits, and the remaining L1-RSRPs use 4 bits) and the reference signal index corresponding to each L1-RSRP.

[0112] The above-mentioned method of reporting the L1-RSRP of the reference signal is to report X L1-RSRPs and the corresponding X reference signal indices. Since X is configured by the base station, the overhead of each report is fixed. For beam management based on AI / ML models, on the one hand, if the model is trained on the network side, the network equipment needs to obtain the L1-RSRP of all beams / beam pairs in SetB, or the L1-RSRP of all beams / beam pairs in SetA and SetB. In order to reduce the feedback overhead of the UE, there is a solution that proposes that the UE only reports the L1-RSRP of some beams / beam pairs, and the number of reports is configured by the network side. When the channel environment is different, the quality of the beam pairs between the UE and the base station will also change. For example, most of the beam pairs measured at time 1 are of good quality, and most of the beam pairs measured at time 2 are of poor quality. If the base station is used to configure the reporting number, in some cases, due to the small number of reports configured by the base station, the UE may only report some beams with better quality. In other cases, the base station may configure a large number of reports, and in addition to beams with better quality, some beams with poorer quality are also reported, resulting in poor performance of AI / ML model training.

[0113] On the other hand, if the model inference is on the UE side, the UE needs to report the information of the Top-K beams / beam pairs obtained by inference to the base station. In order to improve the accuracy of obtaining the optimal beam, after receiving the information of the Top-K beams reported by the UE, the base station can scan these K beams / beam pairs. After measuring these K beams / beam pairs, the UE reports the optimal beam / beam pair to the base station. If a classification model is used on the UE side, the AI / ML model output on the UE side is the confidence (i.e., probability) that each beam / beam pair is the optimal beam / beam pair in SetA. Under different channel environments, the L1-RSRP value of SetB is different, and the probability obtained by each inference is also different. If the K optimal beams / beam pairs reported by the UE after model inference are fixed, it may happen that the probability of certain beams / beam pairs is higher in some cases, and there is no need to report the indexes of other beams / beam pairs with lower probabilities, that is, K is set too large. In other cases, the probabilities of many beams or beam pairs may be similar, and K may be set too small. Setting K too large or too small will reduce the accuracy of the optimal beam or beam pair obtained by the AI / ML model, resulting in poor performance.

[0114] Based on the above technical problems, the embodiments of the present disclosure set reporting conditions. For example, the UE can report beam quality with better conditions (such as L1-RSRP is greater than or equal to a certain threshold). Under this reporting rule, the number of L1-RSRPs or indexes that meet the reporting conditions (such as greater than or equal to the threshold) is variable. By reasonably splitting the L1-RSRP reporting content, it is avoided that the base station does not know the quality of the beam reported by the UE or the number of bits required for reporting in advance and cannot demodulate, thereby taking into account the training performance and reporting overhead of the AI / ML model.

[0115] In addition, for model inference on the UE side, the number of predicted optimal beams / beam pairs to be reported is determined based on the UE's inference results. For example, the indices of beams whose summed confidence obtained by model inference is greater than or equal to a threshold are reported, arranged in descending order of confidence. At this point, the number of beams / beam pairs that meet the reporting conditions obtained by each inference varies. By rationally splitting the L1-RSRP reporting content, this prevents the base station from being unable to demodulate the UE's reported beam quality or the number of bits required for the report, thereby balancing the accuracy and reporting overhead of the optimal beam / beam pair obtained based on the AI / ML model.

[0116] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0117] FIG1 is a flow chart of an information transmission method provided by an embodiment of the present disclosure. As shown in FIG1 , an embodiment of the present disclosure provides an information transmission method, the execution subject of which may be a terminal, such as a mobile phone. The method includes:

[0118] Step 101: Determine reporting information that meets the reporting conditions; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal.

[0119] Specifically, in the embodiment of the present disclosure, the UE first determines reporting information that meets the reporting conditions.

[0120] The reporting conditions may be pre-agreed upon by the protocol or configured by the network device. The network device in the embodiments of the present disclosure may be an access network device, such as a base station, or a core network device, such as an access and mobility management function (AMF) network element.

[0121] The content of the reported information may be different in different application scenarios.

[0122] For example, in the case of model training on the network side, the reported information includes the quality and index of the reference signal that meets the reporting conditions, and the reported information is used for training the artificial intelligence model.

[0123] For example, in the case of model reasoning on the UE side, the reported information includes the index of the beam / beam pair that meets the reporting conditions obtained through model reasoning, and the reported information is used to determine the beam / beam pair that is optimal for transmitting the signal.

[0124] Step 102: Split the reported information into a first part of information and a second part of information and send the results to a network device.

[0125] Specifically, in the embodiment of the present disclosure, after the terminal determines that the reporting information meets the reporting conditions, it splits the reporting information into a first part of information (part1) and a second part of information (part2), and sends the split part1 and part2 to the network device.

[0126] For example, part 1 may occupy a fixed number of bits, and the content of part 1 determines the number of bits occupied by part 2. The network device may determine the number of bits of part 2 based on the content of part 1. When both part 1 and part 2 are reported through the Physical Uplink Control Channel (PUCCH) resources, the UE determines the number of bits to report part 2 based on the referenced reported content of part 2 to ensure that the network device and the UE have consistent determinations of the PUCCH resources for transmitting the reported information, wherein the referenced reported content of part 2 is configured by the network side or specified by the protocol.

[0127] For example, part 1 may occupy a fixed number of bits, and the number of bits occupied by part 2 may be reported to the network device through other information, so as to ensure that the network device and the UE consistently determine the PUCCH resources for transmitting the reported information.

[0128] For example, part 1 and part 2 may use the same transmission code rate.

[0129] For example, part 1 and part 2 may use different transmission code rates, or part 1 may use a fixed transmission code rate, and the network device determines the transmission code rate of part 2 based on the content of part 1.

[0130] The information transmission method provided by the embodiment of the present disclosure, when reporting information related to the artificial intelligence model, splits the reported information that meets the reporting conditions into a first part of information and a second part of information and sends them to the network device, thereby reducing the feedback overhead of the UE and ensuring the performance of the artificial intelligence model.

[0131] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0132] Specifically, in the embodiment of the present disclosure, part 1 occupies a fixed number of bits, and the content of part 1 determines the number of bits occupied by part 2.

[0133] The network device determines the number of bits for part 2 based on the content of part 1. When both part 1 and part 2 are reported via PUCCH resources, the network device determines the number of bits for reporting part 2 based on the reported content of part 2, ensuring that the network device and the UE have consistent determination of the PUCCH resources for transmitting the reporting information.

[0134] In the information transmission method provided by the embodiment of the present disclosure, part 1 occupies a fixed number of bits, and the content of part 1 determines the number of bits occupied by part 2. While ensuring the performance of the artificial intelligence model, the feedback overhead is further reduced.

[0135] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0136] Specifically, in an embodiment of the present disclosure, the reported information is used for training an artificial intelligence model, and the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0137] After the network device obtains the quality and index of the reference signal that meets the reporting conditions, it determines the training samples for model training based on the quality and index of the reference signal that meets the reporting conditions, and uses the training samples to train the artificial intelligence model.

[0138] For example, the UE may only report L1-RSRP and index that meet the conditions. In the model training phase, the reporting condition of L1-RSRP is greater than or equal to a threshold Threshold 1, and Threshold 1 may be configured by the network side or specified by the protocol.

[0139] If the model input is the RSRP of SetB's beams / beam pairs, and the model output is the predicted IDs of SetA's top-K beams / beam pairs, then during training, the RSRP of SetB's beams / beam pairs whose RSRP is lower than the threshold Threshold1 is set to 0, and the RSRP of SetB is used as the model input for training.

[0140] If the model input is the RSRP of SetB's beam / beam pair, and the model output is the predicted RSRP of SetA's beam / beam pair, then during training, the RSRP of SetB (after setting the RSRP of beams / beam pairs whose RSRP is lower than the threshold Threshold1) is set to 0. The RSRP of SetA (after setting the RSRP of beams / beam pairs whose RSRP is lower than the threshold Threshold1) is used as the model input. The RSRP of SetA (after setting the RSRP of beams / beam pairs whose RSRP is lower than the threshold Threshold1) is used as the training label for model training.

[0141] During the model inference phase, if the network performs model inference, the UE reports the reference signal index and corresponding L1-RSRP for SetB where the L1-RSRP is greater than or equal to the threshold. The base station uses the UE's reported L1-RSRP and sets the L1-RSRP of the beams / beam pairs in SetB not reported by the UE to 0 as model input for inference. If the UE performs model inference, it reports the index value that meets the conditions after model inference. This index value is used to represent the beam / beam pair in SetA.

[0142] The information transmission method provided by the embodiment of the present disclosure, when the reported information is used for training an artificial intelligence model, includes the quality and index of the reference signal that meets the reporting conditions, thereby ensuring the performance of the artificial intelligence model training.

[0143] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0144] Specifically, in the embodiment of the present disclosure, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold. For example, the reporting condition of L1-RSRP is greater than or equal to a threshold Threshold 1, which can be configured by the network side or specified by the protocol.

[0145] The information transmission method provided by the embodiment of the present disclosure, in which the reference signal that meets the reporting conditions includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold, reduces the feedback overhead of the UE and ensures the performance of artificial intelligence model training.

[0146] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0147] Specifically, there are multiple ways to split the reporting information into part 1 and part 2. In the embodiment of the present disclosure, part 1 includes the number of reference signals that meet the reporting conditions, and part 2 includes the quality and index of the reference signals that meet the reporting conditions.

[0148] The quality of the reference signal may be an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0149] For example, part 1 includes the number N of reference signals that meet the reporting requirements (or are reported in part 2), and part 2 includes N L1-RSRPs and their corresponding indexes. When reporting N RSRPs, differential reporting can be used, reporting the baseline measurement value (e.g., the maximum L1-RSRP measurement value) and the difference between the maximum L1-RSRP and the remaining N-1 RSRPs that meet the reporting requirements. The maximum L1-RSRP is quantized to L bits, and the differential L1-RSRP is quantized to X bits.

[0150] The number of bits occupied by UE reporting part1 is Where M is the number of reference signals measured by the user configured by the base station (for example, the number of reference signals corresponding to the beam / beam pair in SetB). When the UE determines the resource size for reporting part2, it is determined based on the reference part2 reporting content. The reference part2 reporting content is to report S L1-RSRPs and corresponding indexes, where the value of S is specified by the base station configuration or protocol.

[0151] The information transmission method provided by the embodiment of the present disclosure, part 1 includes the number of reference signals that meet the reporting conditions, and part 2 includes the quality and index of the reference signals that meet the reporting conditions, which ensures that the network side knows the number of bits required for the information reported by the UE, thereby ensuring that the network side can successfully demodulate the information reported by the UE.

[0152] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0153] Specifically, there are multiple ways to split the reporting information into part 1 and part 2. In the embodiment of the present disclosure, part 1 includes a bitmap of index mapping of reference signals that meet the reporting conditions, and part 2 includes the quality of the reference signals corresponding to the index order of the reference signals mapped in the bitmap.

[0154] For example, part 1 includes a bitmap that indicates which of the measured reference signals meet the reporting condition. The length of the bitmap is the number of measured reference signals. For example, if the i-th bit in the bitmap is 1, it indicates that the i-th reference signal among the measured reference signals meets the reporting condition, and if it is 0, it indicates that the reporting condition is not met.

[0155] When the quality of the reference signal is the L1-RSRP value of the reference signal, part 2 includes N L1-RSRPs that meet the reporting conditions and correspond to the index order of the reference signals mapped in the bitmap. Each reported L1-RSRP is quantized into L bits, and the RSRP is sorted in the order of the reference signal index corresponding to the bit 1 in the bitmap. For example, if the UE determines based on the reference signal measurement results that the L1-RSRP of the 1st, 5th, and 7th reference signals measured is greater than or equal to the threshold, the UE determines the reporting content of part 1 to be 10001010. If the L1-RSRP greater than or equal to the threshold is quantized into 7 bits, the UE quantizes the RSRP of the 1st, 5th, and 7th reference signals into 7 bits and maps them in order.

[0156] When the quality of the reference signal is the differential value of the L1-RSRP of the reference signal, part2 includes the index of N L1-RSRPs that meet the reporting conditions and the maximum L1-RSRP corresponding to the index order of the reference signal mapped in the bitmap, where the maximum L1-RSRP is quantized into L bits, and the difference between the remaining N-1 L1-RSRPs and the maximum L1-RSRP is quantized into X bits.

[0157] The number of bits occupied by the UE reporting part1 is M, where M is the number of reference signals measured by the user configured by the base station. When the UE determines the resource size for reporting part2, it is determined based on the reference part2 reporting content. The reference part2 reporting content is to report S RSRPs, where the value of S is specified by the base station configuration or protocol.

[0158] The information transmission method provided by the embodiment of the present disclosure, part 1 includes a bitmap of index mapping of reference signals that meet reporting conditions, and part 2 includes the quality of the reference signals corresponding to the index order of the reference signals mapped in the bitmap, ensuring that the network side knows the number of bits required for the information reported by the UE, thereby ensuring that the network side can successfully demodulate the information reported by the UE.

[0159] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0160] Specifically, there are multiple ways to split the reported information into part 1 and part 2. In the embodiment of the present disclosure, part 1 includes the quality and index of a part of the reference signals in the reference signals that meet the reporting conditions, and also includes the number of reference signals reported in part 2. Part 2 includes the quality and index of another part of the reference signals in the reference signals that meet the reporting conditions.

[0161] For example, part 1 includes the L1-RSRPs of N1 reference signals, the corresponding N1 reference signal indices, and N2, where N2 = N - N1. Part 2 reports N2 RSRPs and their corresponding indices, where N1 is configured by the network.

[0162] When the quality of the reference signal is the L1-RSRP value of the reference signal, the UE reports the L1-RSRP and index of a fixed N1 reference signals in Part 1, and reports the L1-RSRP and index of the remaining reference signals that meet the reporting conditions in Part 2. If the number of reference signals that meet the reporting conditions, N, is less than N1, the UE reports the L1-RSRP and index of N reference signals in Part 1, and reports the remaining N1-N L1-RSRP values ​​as special values ​​(such as all 0s or all 1s).

[0163] When the reference signal quality is the difference between the L1-RSRP values ​​of the reference signals, the L1-RSRP reported by the UE for N1 reference signals is a maximum L1-RSRP and N1-1 differential L1-RSRPs, and the L1-RSRP reported for N2 reference signals is N2 differential L1-RSRPs. The maximum L1-RSRP is quantized into L bits, and the differential L1-RSRP is the difference between the measured L1-RSRP and the maximum L1-RSRP, quantized into X bits.

[0164] The number of bits occupied by the UE reporting part 1 is the sum of the number of bits used to report the L1-RSRP of N1 reference signals and the corresponding index. When the UE determines the resource size of the reported part 2, it is determined based on the referenced reported content of the part 2. The referenced reported content of the part 2 is to report W differential RSRPs and corresponding indexes, where the value of W is configured by the base station or specified by the protocol.

[0165] The information transmission method provided by the embodiment of the present disclosure, part 1 includes the quality and index of a part of the reference signals in the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by part 2, and part 2 includes the quality and index of another part of the reference signals in the reference signals that meet the reporting conditions, thereby ensuring that the network side knows the number of bits required for the information reported by the UE, thereby ensuring that the network side can successfully demodulate the information reported by the UE.

[0166] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0167] Specifically, there are multiple ways to split the reporting information into part 1 and part 2. In the embodiment of the present disclosure, part 1 includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of the reference signals corresponding to the index order of the reference signals mapped by the bitmap. Part 2 includes the quality of another part of the reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0168] For example, part 1 includes the L1-RSRPs of N1 reference signals, the index corresponding to the maximum RSRP, and the bitmap, while part 2 includes the L1-RSRPs of N2 reference signals. The N1 L1-RSRPs reported in part 1 include the maximum L1-RSRP quantized to L bits and the N1-1 L1-RSRPs quantized to X bits that are differential from the maximum L1-RSRP. The N2 L1-RSRPs reported in part 2 are the L1-RSRPs quantized to X bits that are differential from the maximum L1-RSRP. The differential L1-RSRPs reported in parts 1 and 2 are mapped according to the index order in the bitmap.

[0169] The number of bits occupied by the UE reporting part 1 is the sum of the number of bits occupied by the L1-RSRP of the N1 reference signals, the index of the maximum RSRP, and the bitmap, where the number of bits for reporting the L1-RSRP of the N1 reference signals is L+X*(N1-1), and the number of bits for reporting the index of the maximum RSRP is The number of bits in the reporting bitmap is M, where M is the number of reference signals measured by the user configured by the base station. When the UE determines the resource size for reporting part 2, it determines it based on the reported content of part 2, which refers to reporting W differential RSRPs, where the value of W is specified by the base station configuration or protocol.

[0170] The information transmission method provided by the embodiment of the present disclosure, part 1 includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of the reference signals corresponding to the index order of the reference signals mapped by the bitmap, and part 2 includes the quality of another part of the reference signals corresponding to the index order of the reference signals mapped by the bitmap, which ensures that the network side knows the number of bits required for the information reported by the UE, thereby ensuring that the network side can successfully demodulate the information reported by the UE.

[0171] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0172] Specifically, in the embodiments of the present disclosure, the qualities of the reference signals may all be L1-RSRP values ​​of the reference signals, or may all be differential values ​​of the L1-RSRP of the reference signals, or may include both the L1-RSRP values ​​of a portion of the reference signals and the differential values ​​of the L1-RSRP of a portion of the reference signals.

[0173] In the case where the quality of the reference signal is the L1-RSRP value of the reference signal, the calculation amount of the network device can be reduced.

[0174] In the case where the quality of the reference signal is the difference value of the L1-RSRP of the reference signal, the feedback overhead of the UE can be further reduced.

[0175] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0176] Specifically, in an embodiment of the present disclosure, model inference is performed on the UE side. After model inference, the UE reports the index value of the beam / beam pair that meets the conditions. After the base station receives the information of the Top-K beams reported by the UE, it can scan these K beams / beam pairs. After measuring these K beams / beam pairs, the UE reports the optimal beam / beam pair to the base station.

[0177] For example, a classification model is used on the UE side, and the AI / ML model output on the UE side is the confidence (i.e., probability) that each beam / beam pair is the optimal beam / beam pair in Set A. In different channel environments, the L1-RSRP value of Set B varies, and the probability obtained from each inference is also different.

[0178] In the information transmission method provided by the embodiment of the present disclosure, after model inference, the UE reports the index value of the beam / beam pair that meets the conditions. That is, the number of reported optimal beam / beam pair indices is not fixed. In some cases, the probability of a few beams / beam pairs is high, and the number of reported beam / beam pair indices is small. In other cases, the probability of a plurality of beams / beam pairs is relatively close, and the number of reported beam / beam pair indices is large, thereby ensuring that the beam / beam pair received by the network device based on AI / ML model inference is more accurate, thereby ensuring the accuracy of the determined optimal beam / beam pair.

[0179] In some embodiments, the method further comprises:

[0180] Perform model inference based on the trained AI model to determine the confidence level of each beam / beam pair output by the AI ​​model;

[0181] The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

[0182] Specifically, in the disclosed embodiments, a classification model is used on the UE side, and the AI / ML model output on the UE side is the confidence (i.e., probability) that each beam / beam pair is the optimal beam / beam pair in Set A. In different channel environments, the L1-RSRP value of Set B varies, and the probability obtained from each inference is also different.

[0183] Before reporting the index of the beam / beam pair that meets the reporting conditions obtained through model inference, the UE also needs to perform model inference based on the trained AI / ML model to determine the confidence corresponding to each beam / beam pair output by the AI / ML model, and then determine the index of the beam / beam pair that meets the reporting conditions based on the confidence corresponding to each beam / beam pair.

[0184] The information transmission method provided by the embodiment of the present disclosure performs model reasoning on the UE side, thereby improving the efficiency of beam management.

[0185] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0186] Specifically, in an embodiment of the present disclosure, the index of the beam / beam pair that meets the reporting conditions includes the index corresponding to the beam / beam pair with the smallest number and a total confidence score greater than or equal to the second threshold Threshold2. Threshold2 can be configured by the network side or specified by the protocol.

[0187] For example, when the UE side performs model inference, the UE needs to determine the number K of reported inference beam indices based on the above conditions. K is the minimum number of beams / beam pairs whose sum of confidences is greater than or equal to the threshold Threshold2. For example, assuming that SetA has 8 beams / beam pairs, the confidence reporting threshold Threshold2 is set to 0.7, and the confidence output by the AI / ML model is [0.15, 0.3, 0.2, 0.15, 0.05, 0.05, 0.05, 0.05], the UE reports the indices corresponding to the first 4 predicted beams (the sum of confidences is greater than or equal to the threshold). When the confidence output by the AI / ML model is [0.05, 0.5, 0.2, 0.05, 0.05, 0.05, 0.05, 0.05], the UE reports the indices corresponding to the 2nd and 3rd predicted beams.

[0188] The information transmission method provided by the embodiment of the present disclosure is a method in which the indexes of beams / beam pairs that meet the reporting conditions include the indexes corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold Threshold2 and whose number is the smallest, thereby ensuring that the beams / beam pairs received by the network device based on AI / ML model reasoning are more accurate, thereby ensuring the accuracy of the determined optimal beams / beam pairs.

[0189] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0190] Specifically, in the embodiment of the present disclosure, when the UE reports the index of the beam / beam pair that meets the reporting conditions obtained through model inference, the reported content is split into part 1 and part 2.

[0191] For example, the splitting method is that part 1 is K1 index values ​​and K2 values, where K2 = (K-K1), and part 2 is K2 index values, where K1 is configured by the base station.

[0192] When the UE determines the size of the reported resources, it is determined based on the number of bits occupied by part1 and the number of bits occupied by the reference part2 content. The reference part2 content is the resources occupied by reporting the indexes of R predicted beams / beam pairs, where R is configured by the base station or specified by the protocol.

[0193] The information transmission method provided by the embodiment of the present disclosure, part 1 includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions, and part 2 includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions, which ensures that the network side knows the number of bits required for the information reported by the UE, thereby ensuring that the network side can successfully demodulate the information reported by the UE.

[0194] It should be noted that: in the above embodiment, when the index content of the L1-RSRP or the inferred beam / beam pair is split, if the number of bits occupied by the actually reported part2 is less than the number of bits occupied by the reference part2, the coding rate of the transmitted part2 is lower than the target code rate when the PUCCH transmits the information; if the number of bits occupied by the actually reported part2 is greater than the number of bits occupied by the reference part2, the coding rate of part2 is greater than the target code rate when the PUCCH transmits the information.

[0195] The method in the above embodiment is further illustrated below with several specific examples.

[0196] Example 1:

[0197] The base station configures the UE to measure 32 reference signals, corresponding to the 32 beam pairs in Set B. The base station configures the UE reporting threshold to -100dBm, meaning that the UE reports reference signal qualities with L1-RSRP greater than or equal to -100dBm to the base station. Assuming that the UE measures 8 of these 32 reference signals with L1-RSRP greater than or equal to -100dBm, the reported content is shown in Table 1. Part 1 reports the number of reference signals that meet the criteria, and part 2 reports the reference signal indices and corresponding L1-RSRPs that meet the reporting criteria. The maximum L1-RSRP is quantized to 7 bits, and the differential L1-RSRP is quantized to 4 bits.

[0198] Table 1

[0199] Example 2:

[0200] The base station configures the UE to measure 32 reference signals, corresponding to the 32 beam pairs of SetB. The base station configures the UE reporting threshold to -100dBm, meaning that the UE reports reference signal quality with an L1-RSRP greater than or equal to -100dBm to the base station. The base station configures the UE to report four reference L1-RSRPs, the index corresponding to the maximum RSRP, and the bitmap in Part 1. Assuming that the UE measures eight reference signals with an L1-RSRP greater than or equal to -100dBm among these 32 reference signals, the reported content is shown in Table 2. Part 1 reports the bitmap indicating the reference signals that meet the reporting conditions, the index of the maximum L1-RSRP, and the L1-RSRP of four reference signals (one maximum L1-RSR and three differential L1-RSRPs). Part 2 reports four differential L1-RSRPs that meet the reporting conditions, with the maximum L1-RSRP quantized to 7 bits and the differential L1-RSRP quantized to 4 bits.

[0201] Table 2

[0202] The differential L1-RSRP reported by the UE in Table 2 is reported in the order indicated by the bitmap in part 1. For example, the bitmap in Table 2 indicates that 8 of the 32 reference signals measured by the UE meet the reporting conditions, and indicates that the reference signal with the maximum L1-RSRP is the 4th reference signal. The other differential reference signals are mapped in sequence according to the order of the reference signal indexes indicated by the bitmap.

[0203] Example three:

[0204] When model inference is performed on the UE side and the confidence of the AI / ML model output is [0.15, 0.3, 0.2, 0.15, 0.05, 0.05, 0.05, 0.05]. The base station configures the inference result reported by the UE to be the index of the beam whose sum of confidence is greater than or equal to 0.7, and configures the UE to report 3 indexes in part1 and 2 indexes as reference part2. According to the reporting conditions, the indexes of the beams corresponding to the first 4 confidences meet the conditions. The reporting content is shown in Table 3. Part1 includes the indexes of the beams corresponding to the first 3 confidences and the value of K2 is 1; part2 includes the index of the beam corresponding to the 4th confidence. Since the number of bits of the actually transmitted part is less than the number of bits of the reference part2, the actual coding rate of part2 is less than the target bit rate.

[0205] Table 3

[0206] The disclosed embodiments solve the problem of how the UE reports the L1-RSRP measurement results of some beams to the base station according to the reporting conditions when the base station side performs model training and model inference, so that the base station can perform operations such as model training / model inference of spatial or time domain beam prediction based on the AI / ML model, which not only reduces the reporting overhead but also ensures the performance of the AI ​​model; when the UE side performs model inference, the UE reports the inference results to the base station according to the reporting conditions, balancing the reporting overhead and the accuracy of obtaining the optimal beam.

[0207] FIG2 is a second flow chart of an information transmission method provided by an embodiment of the present disclosure. As shown in FIG2 , an embodiment of the present disclosure provides an information transmission method, the execution subject of which may be a network device, such as a base station. The method includes:

[0208] Step 201: Obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0209] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0210] In some embodiments, the method further comprises:

[0211] Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions;

[0212] The artificial intelligence model is trained using the training samples.

[0213] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0214] In some embodiments, the method further comprises:

[0215] Beam scanning is performed according to the index of the beam / beam pair that meets the reporting conditions; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0216] Obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0217] Specifically, the information transmission method provided in the embodiment of the present disclosure can refer to the above-mentioned information transmission method embodiment in which the execution subject is the terminal, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the above-mentioned corresponding method embodiments will not be described in detail here.

[0218] FIG3 is a schematic diagram of the structure of a terminal provided by an embodiment of the present disclosure. As shown in FIG3 , the terminal includes a memory 320, a transceiver 300, and a processor 310, wherein:

[0219] The memory 320 is used to store computer programs; the transceiver 300 is used to send and receive data under the control of the processor 310; the processor 310 is used to read the computer program in the memory 320 and perform the following operations:

[0220] Determining reporting information that meets reporting conditions; the reporting information is used for training an artificial intelligence model or for determining a beam / beam pair that optimizes the transmission signal;

[0221] The reported information is divided into a first part of information and a second part of information and sent to the network device.

[0222] In FIG3 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits connected together by one or more processors represented by processor 310 and memory represented by memory 320. The bus architecture may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not described further herein. The bus interface provides an interface. The transceiver 300 may be a plurality of components, including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. For different user devices, the user interface 330 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0223] The processor 310 is responsible for managing the bus architecture and general processing, and the memory 320 can store data used by the processor 310 when performing operations.

[0224] In some embodiments, the processor 310 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0225] The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0226] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0227] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0228] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0229] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0230] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0231] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0232] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0233] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0234] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0235] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0236] Perform model inference based on the trained AI model to determine the confidence level of each beam / beam pair output by the AI ​​model;

[0237] The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

[0238] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0239] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0240] It should be noted here that the above-mentioned terminal provided in the embodiment of the present disclosure can implement all the method steps implemented by the method embodiment in which the execution subject is the terminal, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0241] FIG4 is a schematic diagram of the structure of a network device provided by an embodiment of the present disclosure. As shown in FIG4 , the network device includes a memory 420, a transceiver 400, and a processor 410, wherein:

[0242] The memory 420 is used to store computer programs; the transceiver 400 is used to send and receive data under the control of the processor 410; the processor 410 is used to read the computer program in the memory 420 and perform the following operations:

[0243] Obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0244] In FIG4 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits linked together by one or more processors represented by processor 410 and memory represented by memory 420. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 400 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 410 is responsible for managing the bus architecture and general processing, and the memory 420 may store data used by the processor 410 when performing operations.

[0245] The processor 410 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0246] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0247] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0248] Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions;

[0249] The artificial intelligence model is trained using the training samples.

[0250] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0251] In some embodiments, the processor is further configured to read the computer program in the memory and perform the following operations:

[0252] Beam scanning is performed according to the index of the beam / beam pair that meets the reporting conditions; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0253] Obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0254] Specifically, the above-mentioned network device provided in the embodiment of the present disclosure can implement all the method steps implemented by the method embodiment in which the execution subject is the network device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0255] FIG5 is a schematic diagram of a structure of an information transmission device provided by an embodiment of the present disclosure. As shown in FIG5 , an embodiment of the present disclosure provides an information transmission device, including a first determining module 501 and a sending module 502, wherein:

[0256] The first determination module 501 is used to determine the reporting information that meets the reporting conditions; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the sending module 502 is used to split the reporting information into a first part of information and a second part of information and send them to a network device.

[0257] In some embodiments, the first portion of information occupies a fixed number of bits; the content of the first portion of information determines the number of bits occupied by the second portion of information.

[0258] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0259] In some embodiments, the reference signal that meets the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to a first threshold.

[0260] In some embodiments, the first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

[0261] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; and the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

[0262] In some embodiments, the first part of information includes the quality and index of a part of the reference signals among the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals among the reference signals that meet the reporting conditions.

[0263] In some embodiments, the first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

[0264] In some embodiments, the quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

[0265] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0266] In some embodiments, the apparatus further comprises a second determination module and a third determination module;

[0267] The second determination module is used to perform model inference based on the trained artificial intelligence model to determine the confidence level corresponding to each beam / beam pair output by the artificial intelligence model;

[0268] The third determination module is configured to determine an index of a beam / beam pair that meets a reporting condition based on a confidence level corresponding to each beam / beam pair.

[0269] In some embodiments, the index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

[0270] In some embodiments, the first part of information includes the index of a part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs in the beams / beam pairs that meet the reporting conditions.

[0271] Specifically, the above-mentioned information transmission device provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiment in which the execution subject is the terminal, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0272] FIG6 is a second structural diagram of an information transmission device provided by an embodiment of the present disclosure. As shown in FIG6 , an embodiment of the present disclosure provides an information transmission device, including a first acquisition module 601 .

[0273] The first acquisition module 601 is used to obtain reporting information reported by the terminal; the reporting information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reporting information is split into a first part of information and a second part of information and then reported.

[0274] In some embodiments, when the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

[0275] In some embodiments, the apparatus further comprises a fourth determination module and a training module;

[0276] The fourth determining module is used to determine the training samples for model training based on the quality and index of the reference signal that meets the reporting condition;

[0277] The training module is used to train the artificial intelligence model using the training samples.

[0278] In some embodiments, when the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting conditions obtained through model reasoning.

[0279] In some embodiments, the apparatus further comprises a beam scanning module and a second acquisition module;

[0280] The beam scanning module is used to perform beam scanning according to the index of the beam / beam pair that meets the reporting conditions; the purpose of performing beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal;

[0281] The second acquisition module is used to obtain the optimal beam / beam pair for the transmission signal reported by the terminal.

[0282] Specifically, the above-mentioned information transmission device provided in the embodiment of the present disclosure can implement all the method steps implemented by the method embodiment in which the execution subject is a network device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0283] It should be noted that the division of units / modules in the above-mentioned embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The above-mentioned integrated units may be implemented in the form of hardware or software functional units.

[0284] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0285] In some embodiments, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the information transmission method provided by the above-mentioned method embodiments.

[0286] Specifically, the above-mentioned computer-readable storage medium provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0287] It should be noted that the computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0288] It should also be noted that the terms "first," "second," and the like in the embodiments of the present disclosure are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present disclosure can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "first" and "second" generally distinguish objects of the same type, and do not limit the number of objects. For example, the first object can be one or more.

[0289] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0290] In the embodiments of the present disclosure, "determine B based on A" means that the factor A must be considered when determining B. This is not limited to "determine B based only on A", but should also include: "determine B based on A and C", "determine B based on A, C and E", "determine C based on A, and further determine B based on C", etc. It can also include taking A as a condition for determining B, for example, "when A meets the first condition, use the first method to determine B"; for example, "when A meets the second condition, determine B"; for example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor in determining B, for example, "when A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0291] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0292] The technical solution provided by the embodiments of the present disclosure can be applicable to a variety of systems, especially 5G systems. For example, applicable systems may be global system of mobile communication (GSM) systems, code division multiple access (CDMA) systems, wideband code division multiple access (WCDMA) general packet radio service (GPRS) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, long term evolution advanced (LTE-A) systems, universal mobile telecommunication systems (UMTS), worldwide interoperability for microwave access (WiMAX) systems, 5G new air interface (NR) systems, etc. These various systems include terminal devices and network devices. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0293] The terminal device involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing device connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called User Equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, or a user device, but is not limited in the embodiments of the present disclosure.

[0294] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal device through one or more sectors on an air interface, or may be called another name. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a base transceiver station (BTS) in the Global System for Mobile communications (GSM) or code division multiple access (CDMA), a network device (NodeB) in wide-band code division multiple access (WCDMA), an evolutionary Node B (eNB or e-NodeB) in the long term evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), a home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in the embodiments of the present disclosure. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be geographically separated.

[0295] Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO. It can also use diversity transmission, precoding transmission, or beamforming transmission.

[0296] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0297] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0298] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0299] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0300] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. An information transmission method, applied to a terminal, comprising: Determine the reporting information that meets the reporting conditions; The reported information is used for training an artificial intelligence model or for determining an optimal beam / beam pair for transmitting a signal; The reported information is divided into a first part of information and a second part of information and sent to the network device.

2. The information transmission method according to claim 1, wherein: The first part of information occupies a fixed number of bits; the content of the first part of information determines the number of bits occupied by the second part of information.

3. The information transmission method according to claim 1, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

4. The information transmission method according to claim 3, wherein: The reference signal satisfying the reporting condition includes a reference signal whose corresponding layer 1 reference signal received power L1-RSRP is greater than or equal to the first threshold.

5. The information transmission method according to claim 4, wherein: The first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

6. The information transmission method according to claim 4, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

7. The information transmission method according to claim 4, wherein: The first part of information includes the quality and index of a part of the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals that meet the reporting conditions.

8. The information transmission method according to claim 4, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

9. The information transmission method according to any one of claims 5 to 8, wherein: The quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

10. The information transmission method according to claim 1, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

11. The information transmission method according to claim 10, wherein: The method further comprises: Perform model inference based on the trained artificial intelligence model to determine the confidence level corresponding to each beam / beam pair output by the artificial intelligence model; The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

12. The information transmission method according to claim 10 or 11, wherein: The index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

13. The information transmission method according to claim 10 or 11, wherein: The first part of information includes the index of a part of the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs that meet the reporting conditions.

14. An information transmission method, applied to a network device, comprising: Get the reporting information reported by the terminal; The reported information is used for training an artificial intelligence model or for determining an optimal beam / beam pair for transmitting a signal; The reported information is split Reported after the first and second parts of information.

15. The information transmission method according to claim 14, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

16. The information transmission method according to claim 15, wherein: The method further comprises: Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions; The artificial intelligence model is trained using the training samples.

17. The information transmission method according to claim 14, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

18. The information transmission method according to claim 17, wherein: The method further comprises: Beam scanning is performed according to the index of the beam / beam pair that meets the reporting condition; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal; Obtain an optimal beam / beam pair for the transmission signal reported by the terminal.

19. A terminal comprising a memory, a transceiver, and a processor; Memory for storing computer programs; a transceiver, configured to transmit and receive data under the control of the processor; and a processor, configured to read the computer program in the memory and perform the following operations: Determine the reporting information that meets the reporting conditions; The reported information is used for training an artificial intelligence model or for determining an optimal beam / beam pair for transmitting a signal; The reported information is divided into a first part of information and a second part of information and sent to the network device.

20. The terminal according to claim 19, wherein: The first part of information occupies a fixed number of bits; the content of the first part of information determines the number of bits occupied by the second part of information.

21. The terminal according to claim 19, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

22. The terminal according to claim 21, wherein: The reference signal satisfying the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to the first threshold.

23. The terminal according to claim 22, wherein: The first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

24. The terminal according to claim 22, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet reporting conditions; the second part of information includes the quality of reference signals corresponding to the index sequence of the reference signals mapped in the bitmap.

25. The terminal according to claim 22, wherein: The first part of information includes the quality and index of a part of the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals that meet the reporting conditions.

26. The terminal according to claim 22, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

27. The terminal according to any one of claims 23 to 26, wherein: The quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

28. The terminal according to claim 19, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

29. The terminal according to claim 28, wherein: The processor is further configured to read the computer program in the memory and perform the following operations: Perform model inference based on the trained artificial intelligence model to determine the confidence level corresponding to each beam / beam pair output by the artificial intelligence model; The index of the beam / beam pair that meets the reporting condition is determined based on the confidence corresponding to each beam / beam pair.

30. The terminal according to claim 28 or 29, wherein: The index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

31. The terminal according to claim 28 or 29, wherein: The first part of information includes the index of a part of the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs that meet the reporting conditions.

32. A network device comprising a memory, a transceiver, and a processor; Memory for storing computer programs; a transceiver, configured to transmit and receive data under the control of the processor; and a processor, configured to read the computer program in the memory and perform the following operations: Get the reporting information reported by the terminal; The reported information is used for training an artificial intelligence model or for determining the optimal beam / beam pair for transmitting a signal; the reported information is split into a first part of information and a second part of information and then reported.

33. The network device according to claim 32, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

34. The network device according to claim 33, wherein: The processor is further configured to read the computer program in the memory and perform the following operations: Determine training samples for model training based on the quality and index of the reference signal that meets the reporting conditions; The artificial intelligence model is trained using the training samples.

35. The network device according to claim 32, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

36. The network device according to claim 35, wherein: The processor is further configured to read the computer program in the memory and perform the following operations: Beam scanning is performed according to the index of the beam / beam pair that meets the reporting condition; the purpose of beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal; Obtain an optimal beam / beam pair for the transmission signal reported by the terminal.

37. An information transmission device, comprising: A first determination module, used to determine the reporting information that meets the reporting conditions; The reported information is used for training an artificial intelligence model or for determining an optimal beam / beam pair for transmitting a signal; The sending module is used to split the reported information into a first part of information and a second part of information and send the second part of information to the network device.

38. The information transmission device according to claim 37, wherein: The first part of information occupies a fixed number of bits; the content of the first part of information determines the number of bits occupied by the second part of information.

39. The information transmission device according to claim 37, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

40. The information transmission device according to claim 39, wherein: The reference signal satisfying the reporting condition includes a reference signal whose corresponding L1-RSRP is greater than or equal to the first threshold.

41. The information transmission device according to claim 40, wherein: The first part of information includes the number of reference signals that meet the reporting conditions; the second part of information includes the quality and index of the reference signals that meet the reporting conditions.

42. The information transmission device according to claim 40, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet the reporting condition; The second part of information includes the quality of the reference signal corresponding to the index order of the reference signal mapped in the bitmap.

43. The information transmission device according to claim 40, wherein: The first part of information includes the quality and index of a part of the reference signals that meet the reporting conditions, and also includes the number of reference signals reported by the second part of information; the second part of information includes the quality and index of another part of the reference signals that meet the reporting conditions.

44. The information transmission device according to claim 40, wherein: The first part of information includes a bitmap of index mapping of reference signals that meet the reporting conditions, and the quality of a part of reference signals corresponding to the index order of the reference signals mapped by the bitmap; the second part of information includes the quality of another part of reference signals corresponding to the index order of the reference signals mapped by the bitmap.

45. The information transmission device according to any one of claims 41 to 44, wherein: The quality of the reference signal is an L1-RSRP value of the reference signal and / or a difference value of the L1-RSRP of the reference signal.

46. ​​The information transmission device according to claim 37, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

47. The information transmission device according to claim 46, wherein: The device also includes a second determination module and a third determination module; The second determination module is used to perform model reasoning based on the trained artificial intelligence model to determine the confidence level corresponding to each beam / beam pair output by the artificial intelligence model; The third determination module is used to determine the index of the beam / beam pair that meets the reporting condition based on the confidence corresponding to each beam / beam pair.

48. The information transmission device according to claim 46 or 47, wherein: The index of the beams / beam pairs that meet the reporting conditions includes the index corresponding to the beams / beam pairs whose total confidence is greater than or equal to the second threshold and whose number is the smallest.

49. The information transmission device according to claim 46 or 47, wherein: The first part of information includes the index of a part of the beams / beam pairs that meet the reporting conditions; the second part of information includes the index of another part of the beams / beam pairs that meet the reporting conditions.

50. An information transmission device, comprising: A first acquisition module, used to acquire reporting information reported by the terminal; The reported information is used for training an artificial intelligence model or for determining an optimal beam / beam pair for transmitting a signal; The reported information is split into a first part of information and a second part of information before being reported.

51. The information transmission device according to claim 50, wherein: When the reported information is used for training an artificial intelligence model, the reported information includes the quality and index of a reference signal that meets the reporting conditions.

52. The information transmission device according to claim 51, wherein: The device also includes a fourth determination module and a training module; The fourth determination module is used to determine the training samples for model training based on the quality and index of the reference signal that meets the reporting condition; The training module is used to train the artificial intelligence model using the training samples.

53. The information transmission device according to claim 50, wherein: In the case where the reporting information is used to determine the optimal beam / beam pair for transmitting a signal, the reporting information includes an index of the beam / beam pair that meets the reporting condition and is obtained through model reasoning.

54. The information transmission device according to claim 53, wherein: The device also includes a beam scanning module and a second acquisition module; The beam scanning module is used to perform beam scanning according to the index of the beam / beam pair that meets the reporting condition; the purpose of the beam scanning is to perform beam measurement to determine the beam / beam pair with the best transmission signal; The second acquisition module is used to acquire the optimal beam / beam pair for the transmission signal reported by the terminal.

55. A computer-readable storage medium storing a computer program, wherein the computer program is used to cause a computer to execute the information transmission method according to any one of claims 1 to 13.

56. A computer-readable storage medium storing a computer program, wherein the computer program is used to cause a computer to execute the information transmission method according to any one of claims 14 to 18.

Images