Beam management model generation method and apparatus
By generating a beam management dataset free of measurement errors and then filtering and overlaying the measurement errors, the problem of misalignment in beam management performance evaluation was solved, thus improving the standardization and accuracy of the evaluation.
Patent Information
- Application Number
- PCT/CN2025/094092
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-12
AI Technical Summary
In existing technologies, beam management performance evaluation is not aligned, is difficult to standardize, and is greatly affected by measurement errors.
A beam management model is formed by generating a beam management dataset free of measurement errors, filtering it, and superimposing measurement error processing on it.
This has enabled the alignment of beam management performance evaluation results from different equipment vendors, improving the standardization and accuracy of the evaluation.
Smart Images

Figure CN2025094092_12112026_PF_FP_ABST
Abstract
Description
Beam management model generation method and apparatus Technical Field
[0001] This disclosure relates to the field of communication technology, and in particular to a method and apparatus for generating beam management models. Background Technology
[0002] Beam management is one of the key technologies for ensuring efficient and reliable communication, and beam management performance evaluation requires a large amount of data. This data needs to account for non-ideal factors, such as measurement errors, and how this data is generated will affect the performance evaluation results in practical beam management applications. Summary of the Invention
[0003] This disclosure presents a method and apparatus for generating beam management models, which addresses the technical problems of misalignment and difficulty in standardization of beam management performance evaluation in related technologies.
[0004] In a first aspect, embodiments of this disclosure propose a beam management model generation method, executed by a terminal, the method comprising:
[0005] M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data.
[0006] N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N;
[0007] The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
[0008] Secondly, embodiments of this disclosure propose a beam management model generation method, executed by a network device, the method comprising:
[0009] M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data.
[0010] N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N;
[0011] The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
[0012] Thirdly, embodiments of this disclosure provide a communication device for executing the beam management model generation method described in the first aspect above, or the beam management model generation method described in the second aspect above.
[0013] Fourthly, embodiments of this disclosure propose a communication system, including a terminal and a network device, wherein the terminal is configured to implement the beam management model generation method described in the first aspect above, and the network device is configured to implement the beam management model generation method described in the second aspect above.
[0014] Fifthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the beam management model generation method described in the first aspect or the beam management model generation method described in the second aspect.
[0015] In a sixth aspect, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program or instructions are executed by a communication device, they implement the beam management model generation method described in the first aspect or the beam management model generation method described in the second aspect.
[0016] This disclosure proposes a method and apparatus for generating a beam management model. The method generates M beam management datasets without measurement errors based on parameter configuration information; selects N beam management datasets from the M datasets; superimposes measurement errors onto the received power of each layer 1 reference signal included in the N datasets; and uses the N beam management datasets with superimposed measurement errors to generate a beam management model. The beam management model generation method and apparatus proposed in this disclosure employ a standardized generation process, enabling the alignment of beam management performance evaluation results from different equipment vendors and improving the standardization level of beam management performance evaluation. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.
[0018] Figure 1 is an exemplary schematic diagram of the architecture of the communication system provided in an embodiment of this disclosure.
[0019] Figure 2 is one of the exemplary interactive diagrams of the beam management model generation method provided in the embodiments of this disclosure.
[0020] Figure 3 is a second exemplary interactive schematic diagram of the beam management model generation method provided in this embodiment of the present disclosure.
[0021] Figure 4 is a third exemplary interactive schematic diagram of the beam management model generation method provided in this embodiment of the present disclosure.
[0022] Figure 5A is a schematic diagram of the structure of the terminal proposed in an embodiment of this disclosure.
[0023] Figure 5B is a schematic diagram of the structure of the network device proposed in an embodiment of this disclosure.
[0024] Figure 6A is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure.
[0025] Figure 6B is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation
[0026] This disclosure presents a method and apparatus for generating beam management models.
[0027] In a first aspect, embodiments of this disclosure propose a beam management model generation method, executed by a terminal, the method comprising:
[0028] M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data.
[0029] N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N;
[0030] The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
[0031] In the above embodiments, the standardized generation process enables the beam management performance evaluation results of different equipment vendors to be aligned, thereby improving the standardization level of beam management performance evaluation.
[0032] In conjunction with some embodiments of the first aspect, in some embodiments, the parameter configuration information includes at least one of the following:
[0033] Transmit beam mode parameters;
[0034] Receive beam mode parameters;
[0035] Channel parameters;
[0036] Scene parameters.
[0037] In the above embodiments, the parameter configuration when generating data includes at least one of the following: transmit beam mode parameters, receive beam mode parameters, channel parameters, and scene parameters. The configuration parameters are more detailed, which improves the accuracy of beam management performance evaluation.
[0038] In conjunction with some embodiments of the first aspect, in some embodiments, the transmit beam mode parameters include at least one of the following:
[0039] Number of panels;
[0040] Number of elements in a horizontal array;
[0041] Number of vertical array elements;
[0042] Main lobe direction;
[0043] Beamforming method.
[0044] In the above embodiments, the transmission beam mode parameters include at least one of the following: number of panels, number of horizontal array elements, number of vertical array elements, main lobe direction, and beamforming method. This fully considers the transmission beam mode parameters such as the number of panels, number of horizontal array elements, number of vertical array elements, main lobe direction, and beamforming method, which have a significant impact on the beam management performance evaluation results, thereby improving the accuracy of beam management performance evaluation.
[0045] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:
[0046] Receive a first message sent by a network device; the first message contains the transmission beam mode parameters.
[0047] In the above embodiments, the transmission beam mode parameters are configured by the network device according to the actual scenario, which improves the flexibility of the transmission beam mode parameters.
[0048] In conjunction with some embodiments of the first aspect, in some embodiments, the received beam mode parameters include at least one of the following:
[0049] Number of panels;
[0050] Number of elements in a horizontal array;
[0051] Number of vertical array elements;
[0052] Main lobe direction;
[0053] Beamforming method.
[0054] In the above embodiments, the received beam pattern parameters include at least one of the following: number of panels, number of horizontal array elements, number of vertical array elements, main lobe direction, and beamforming method. This fully considers the received beam pattern parameters such as the number of panels, number of horizontal array elements, number of vertical array elements, main lobe direction, and beamforming method, which have a significant impact on the beam management performance evaluation results, thereby improving the accuracy of beam management performance evaluation.
[0055] In conjunction with some embodiments of the first aspect, in some embodiments, the channel parameters include at least one of the following:
[0056] Carrier frequency;
[0057] Subcarrier spacing;
[0058] Channel model.
[0059] In the above embodiments, the channel parameters include at least one of carrier frequency, subcarrier spacing, and channel model, which fully considers the channel parameters such as carrier frequency, subcarrier spacing, and channel model that have a significant impact on the beam management performance evaluation results, thereby improving the accuracy of beam management performance evaluation.
[0060] In conjunction with some embodiments of the first aspect, in some embodiments, the scene parameters include at least one of the following:
[0061] Hongxiaoqu;
[0062] micro-region;
[0063] Indoor residential area;
[0064] Outdoor residential area;
[0065] The proportion of macrocells;
[0066] The proportion of micro-regions;
[0067] The proportion of indoor communities;
[0068] The proportion of outdoor residential areas.
[0069] In the above embodiments, the scenario parameters include at least one of macro cells, micro cells, indoor cells, outdoor cells, the proportion of macro cells, the proportion of micro cells, the proportion of indoor cells, and the proportion of outdoor cells. This fully considers different scenarios and proportions that have a significant impact on the beam management performance evaluation results, thereby improving the comprehensiveness and applicability of the beam management performance evaluation.
[0070] In conjunction with some embodiments of the first aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0071] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0072] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0073] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0074] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0075] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0076] In the above embodiments, the maximum signal-to-noise ratio of the beam management dataset selected by hierarchical control meets a uniform distribution, which improves the consistency of the maximum signal-to-noise ratio distribution.
[0077] In conjunction with some embodiments of the first aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0078] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0079] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0080] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0081] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0082] In the above embodiments, the signal-to-noise ratio of each beam management dataset selected by hierarchical control meets a uniform distribution, which improves the consistency of each beam management dataset.
[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0084] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0085] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0086] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0087] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0088] In the above embodiments, the signal-to-noise ratio of all beam management datasets selected by global control generally meets a uniform distribution, which improves the global consistency of beam management data.
[0089] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:
[0090] The measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0091] In the above embodiments, the measurement error of the superimposed received power of each layer 1 reference signal is determined by the mapping relationship between the signal-to-noise ratio and the Gaussian error variance, which can more accurately simulate the measurement error in the actual environment and improve the accuracy of the evaluation.
[0092] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:
[0093] The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0094] In the above embodiments, the measurement error of the superimposed receiving power of each layer 1 reference signal is determined by the mapping relationship between the receiving power of the layer 1 reference signal and the variance of the Gaussian error. This can more efficiently measure the superimposed measurement error of the receiving power of each layer 1 reference signal and improve the model generation efficiency.
[0095] In conjunction with some embodiments of the first aspect, in some embodiments, the mapping relationship is predefined;
[0096] Alternatively, the method may further include:
[0097] Receive a second message sent by a network device; the second message contains the mapping relationship.
[0098] In the above embodiments, the mapping relationship can be predefined, reducing signaling overhead. Alternatively, the mapping relationship can be determined by the network device based on actual conditions and sent to the terminal, improving the flexibility of the mapping relationship.
[0099] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes at least one of the following:
[0100] The beam management model is trained using N beam management datasets with superimposed measurement errors.
[0101] The beam management model was validated using N beam management datasets with superimposed measurement errors.
[0102] In the above embodiments, the beam management model is trained / validated using a beam management dataset with superimposed measurement errors, which improves the accuracy of the beam management model.
[0103] Secondly, embodiments of this disclosure propose a beam management model generation method, executed by a network device, the method comprising:
[0104] M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data.
[0105] N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N;
[0106] The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
[0107] In the above embodiments, the standardized generation process enables the beam management performance evaluation results of different equipment vendors to be aligned, thereby improving the standardization level of beam management performance evaluation.
[0108] In conjunction with some embodiments of the second aspect, in some embodiments, the parameter configuration information includes at least one of the following:
[0109] Transmit beam mode parameters;
[0110] Receive beam mode parameters;
[0111] Channel parameters;
[0112] Scene parameters.
[0113] In conjunction with some embodiments of the second aspect, in some embodiments, the received beam mode parameters include at least one of the following:
[0114] Number of panels;
[0115] Number of elements in a horizontal array;
[0116] Number of vertical array elements;
[0117] Main lobe direction;
[0118] Beamforming method.
[0119] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:
[0120] The receiving terminal sends a third message; the third message contains the receiving beam mode parameters.
[0121] In conjunction with some embodiments of the second aspect, in some embodiments, the transmit beam mode parameters include at least one of the following:
[0122] Number of panels;
[0123] Number of elements in a horizontal array;
[0124] Number of vertical array elements;
[0125] Main lobe direction;
[0126] Beamforming method.
[0127] In conjunction with some embodiments of the second aspect, in some embodiments, the channel parameters include at least one of the following:
[0128] Carrier frequency;
[0129] Subcarrier spacing;
[0130] Channel model.
[0131] In conjunction with some embodiments of the second aspect, in some embodiments, the scene parameters include at least one of the following:
[0132] Hongxiaoqu;
[0133] micro-region;
[0134] Indoor residential area;
[0135] Outdoor residential area;
[0136] The proportion of macrocells;
[0137] The proportion of micro-regions;
[0138] The proportion of indoor communities;
[0139] The proportion of outdoor residential areas.
[0140] In conjunction with some embodiments of the second aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0141] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0142] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0143] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0144] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0145] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0146] In conjunction with some embodiments of the second aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0147] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0148] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0149] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0150] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0151] In conjunction with some embodiments of the second aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0152] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0153] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0154] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0155] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0156] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:
[0157] The measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0158] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:
[0159] The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0160] In conjunction with some embodiments of the second aspect, in some embodiments, the mapping relationship is predefined;
[0161] Alternatively, the method may further include:
[0162] The receiving terminal sends a fourth message; the fourth message contains the mapping relationship.
[0163] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes at least one of the following:
[0164] The beam management model is trained using N beam management datasets with superimposed measurement errors.
[0165] The beam management model was validated using N beam management datasets with superimposed measurement errors.
[0166] Thirdly, embodiments of this disclosure provide a terminal, including:
[0167] The processing module is used to generate M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data; it is also used to filter N beam management datasets from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; it is also used to superimpose measurement errors on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing measurement errors are used to generate a beam management model.
[0168] In conjunction with some embodiments of the third aspect, in some embodiments, the parameter configuration information includes at least one of the following:
[0169] Transmit beam mode parameters;
[0170] Receive beam mode parameters;
[0171] Channel parameters;
[0172] Scene parameters.
[0173] In conjunction with some embodiments of the third aspect, in some embodiments, the transmit beam mode parameters include at least one of the following:
[0174] Number of panels;
[0175] Number of elements in a horizontal array;
[0176] Number of vertical array elements;
[0177] Main lobe direction;
[0178] Beamforming method.
[0179] In conjunction with some embodiments of the third aspect, in some embodiments, the terminal further includes a transceiver module;
[0180] The transceiver module is used to receive a first message sent by the network device; the first message contains the transmission beam mode parameters.
[0181] In conjunction with some embodiments of the third aspect, in some embodiments, the received beam mode parameters include at least one of the following:
[0182] Number of panels;
[0183] Number of elements in a horizontal array;
[0184] Number of vertical array elements;
[0185] Main lobe direction;
[0186] Beamforming method.
[0187] In conjunction with some embodiments of the third aspect, in some embodiments, the channel parameters include at least one of the following:
[0188] Carrier frequency;
[0189] Subcarrier spacing;
[0190] Channel model.
[0191] In conjunction with some embodiments of the third aspect, in some embodiments, the scene parameters include at least one of the following:
[0192] Hongxiaoqu;
[0193] micro-region;
[0194] Indoor residential area;
[0195] Outdoor residential area;
[0196] The proportion of macrocells;
[0197] The proportion of micro-regions;
[0198] The proportion of indoor communities;
[0199] The proportion of outdoor residential areas.
[0200] In conjunction with some embodiments of the third aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0201] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0202] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0203] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0204] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0205] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0206] In conjunction with some embodiments of the third aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0207] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0208] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0209] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0210] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0211] In conjunction with some embodiments of the third aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0212] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0213] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0214] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0215] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0216] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module is further configured to determine the measurement error of the superposition of the received power of each layer 1 reference signal based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0217] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module is further configured to determine the measurement error of the superposition of the received power of each layer 1 reference signal based on the mapping relationship between the received power of the layer 1 reference signal and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0218] In conjunction with some embodiments of the third aspect, in some embodiments, the mapping relationship is predefined;
[0219] Alternatively, the terminal may further include a transceiver module; the transceiver module is used to receive a second message sent by a network device; the second message contains the mapping relationship.
[0220] In conjunction with some embodiments of the third aspect, in some embodiments, the processing module is further configured to perform at least one of the following:
[0221] The beam management model is trained using N beam management datasets with superimposed measurement errors.
[0222] The beam management model was validated using N beam management datasets with superimposed measurement errors.
[0223] Fourthly, embodiments of this disclosure provide a network device, including:
[0224] The processing module is used to generate M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data; it is also used to filter N beam management datasets from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; it is also used to superimpose measurement errors on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing measurement errors are used to generate a beam management model.
[0225] In conjunction with some embodiments of the fourth aspect, in some embodiments, the parameter configuration information includes at least one of the following:
[0226] Transmit beam mode parameters;
[0227] Receive beam mode parameters;
[0228] Channel parameters;
[0229] Scene parameters.
[0230] In conjunction with some embodiments of the fourth aspect, in some embodiments, the received beam mode parameters include at least one of the following:
[0231] Number of panels;
[0232] Number of elements in a horizontal array;
[0233] Number of vertical array elements;
[0234] Main lobe direction;
[0235] Beamforming method.
[0236] In conjunction with some embodiments of the fourth aspect, in some embodiments, the network device further includes a transceiver module;
[0237] The transceiver module is used to receive a third message sent by the terminal; the third message contains the receiving beam mode parameters.
[0238] In conjunction with some embodiments of the fourth aspect, in some embodiments, the transmit beam mode parameters include at least one of the following:
[0239] Number of panels;
[0240] Number of elements in a horizontal array;
[0241] Number of vertical array elements;
[0242] Main lobe direction;
[0243] Beamforming method.
[0244] In conjunction with some embodiments of the fourth aspect, in some embodiments, the channel parameters include at least one of the following:
[0245] Carrier frequency;
[0246] Subcarrier spacing;
[0247] Channel model.
[0248] In conjunction with some embodiments of the fourth aspect, in some embodiments, the scene parameters include at least one of the following:
[0249] Hongxiaoqu;
[0250] micro-region;
[0251] Indoor residential area;
[0252] Outdoor residential area;
[0253] The proportion of macrocells;
[0254] The proportion of micro-regions;
[0255] The proportion of indoor communities;
[0256] The proportion of outdoor residential areas.
[0257] In conjunction with some embodiments of the fourth aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0258] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0259] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0260] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0261] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0262] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0263] In conjunction with some embodiments of the fourth aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0264] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0265] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0266] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0267] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0268] In conjunction with some embodiments of the fourth aspect, in some embodiments, the N beam management datasets satisfy at least one of the following conditions:
[0269] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0270] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0271] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0272] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0273] In conjunction with some embodiments of the fourth aspect, in some embodiments, the processing module is further configured to determine the measurement error of the superposition of the received power of each layer 1 reference signal based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0274] In conjunction with some embodiments of the fourth aspect, in some embodiments, the processing module is further configured to determine the measurement error of the superposition of the received power of each layer 1 reference signal based on the mapping relationship between the received power of the layer 1 reference signal and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0275] In conjunction with some embodiments of the fourth aspect, in some embodiments, the mapping relationship is predefined;
[0276] Alternatively, the network device may also include a transceiver module;
[0277] The transceiver module is used to receive a fourth message sent by the terminal; the fourth message contains the mapping relationship.
[0278] In conjunction with some embodiments of the fourth aspect, in some embodiments, the processing module is further configured to perform at least one of the following:
[0279] The beam management model is trained using N beam management datasets with superimposed measurement errors.
[0280] The beam management model was validated using N beam management datasets with superimposed measurement errors.
[0281] Fifthly, embodiments of this disclosure provide a communication device for performing the beam management model generation method of the first aspect or the beam management model generation method of the second aspect described above.
[0282] In a sixth aspect, embodiments of this disclosure provide a communication system including a terminal and a network device, wherein the terminal is configured to implement the beam management model generation method of the first aspect described above, and the network device is configured to implement the beam management model generation method of the second aspect described above.
[0283] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the beam management model generation method of the first aspect or the beam management model generation method of the second aspect described above.
[0284] Eighthly, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by a communication device, they implement the beam management model generation method of the first aspect or the beam management model generation method of the second aspect described above.
[0285] It is understood that the aforementioned communication equipment, communication system, storage medium, program product, etc., are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.
[0286] It is understood that the aforementioned communication equipment, communication system, storage medium, program product, etc., are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.
[0287] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0288] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.
[0289] In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.
[0290] In the embodiments disclosed herein, "multiple" refers to two or more.
[0291] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.
[0292] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.
[0293] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.
[0294] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.
[0295] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.
[0296] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.
[0297] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.
[0298] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.
[0299] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.
[0300] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).
[0301] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.
[0302] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.
[0303] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.
[0304] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.
[0305] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.
[0306] In some embodiments, data, information, etc., may be obtained with the user's consent.
[0307] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.
[0308] Figure 1 is an exemplary schematic diagram of the architecture of a communication system provided in an embodiment of this disclosure. As shown in Figure 1, the communication system 100 includes a terminal 101 and a network device 102.
[0309] In some embodiments, terminal 101 includes, for example, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home, but is not limited thereto.
[0310] In some embodiments, network device 102 may include at least one of access network device and core network device.
[0311] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system, but is not limited thereto.
[0312] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.
[0313] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.
[0314] In some embodiments, the core network equipment may be a single device, including a first network element, a second network element, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element, the second network element, etc. Network elements may be virtual, such as servers deployed in the cloud, or physical, such as servers deployed locally. The core network may include at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).
[0315] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.
[0316] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.
[0317] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).
[0318] In some embodiments, the generation of beam management datasets has the following candidate options:
[0319] 1. The training dataset, model input during inference, and errors in the actual values are not considered.
[0320] The simulation process for evaluating beam management performance in this case is as follows:
[0321] 1.1 Generate an ideal dataset: Based on the System Level Simulation (SLS) assumption in the relevant definition, generate an ideal Level 1 Reference Signal Received Power (L1-RSRP) dataset.
[0322] 1.2 Training the model: The model is trained using a subset of samples from the ideal dataset generated in step 1.1.
[0323] 1.3 Constructing the inference dataset: Select UEs with a signal-to-noise ratio (SNR) greater than -3dB from another subset of the ideal dataset (which does not overlap with the subset in step 1.2) (using this SNR range as the starting point) to obtain the ideal dataset for inference.
[0324] Note: UE distribution is 100% outdoor.
[0325] 1.4 Performance Evaluation: Inference is performed using an ideal dataset, and the performance metrics are evaluated as assumed that the true values have no measurement error.
[0326] 2. Some errors have been considered.
[0327] Case 2a: Ignore the error between the training dataset and the true values, and consider the error in the model input during inference.
[0328] Case 2b: During training, the error between the training dataset and the true value is not considered; during inference, the error is considered in both the model input and the true value.
[0329] The simulation process for evaluating beam management performance in this case is as follows:
[0330] 2.1 Generate an ideal dataset: Based on the SLS assumption in the relevant definition, generate an ideal L1-RSRP dataset.
[0331] 2.2 Training the model: The model is trained using a subset of samples from the ideal dataset generated in step 2.1.
[0332] 2.3 Constructing the inference dataset: Select UEs with an SNR greater than -3dB from another subset of the ideal dataset (which does not overlap with the subset in step 2.2) (using this SNR range as the starting point) to obtain the ideal dataset for inference.
[0333] Note: UE distribution is 100% outdoor.
[0334] 2.4 Generate Baseband Error: Based on the Link Level Simulation (LLS) assumption in the relevant definition, the L1-RSRP difference is generated as the baseband error.
[0335] 2.5 Generate RF Error: Generate RF error based on the RF error simulation assumptions in the relevant definitions.
[0336] 2.6 Injecting Measurement Errors: The measurement errors generated by the LLS assumptions are added to the ideal dataset generated by the SLS assumptions, resulting in a dataset containing errors. Measurement errors include the following options:
[0337] Option 1: Include only baseband error;
[0338] Option 2: Include only RF error;
[0339] Option 3: Includes both baseband error and RF error.
[0340] 2.7 Performance Evaluation: Inference is performed using a dataset containing errors, and performance metrics are evaluated based on the error in assuming the true value for different cases.
[0341] Case 2a: Assume the true value contains measurement error (consistent with the error option selected in step 2.6).
[0342] Case 2b: Assume that the true value does not contain measurement error.
[0343] In some embodiments, the method for generating beam management datasets in the relevant technical solutions suffers from at least one of the following technical problems:
[0344] 1. The impact of measurement error.
[0345] Baseband error and RF error significantly affect the accuracy of beam prediction. Differences in baseband algorithms and RF implementations among different equipment vendors lead to varying measurement errors under different SNR conditions. These differences make it difficult to compare and standardize evaluation results between different vendors.
[0346] 2. The issue of dataset standardization.
[0347] Inconsistent data generation methods: Different equipment manufacturers use different data generation methods and assumptions, resulting in inconsistent SNR distributions and error characteristics in the test data. This inconsistency makes it difficult to align test results from different equipment manufacturers, affecting the comparability and standardization of the evaluation.
[0348] Dataset diversity: In real-world communication environments, beam management faces a variety of scenarios, including indoor, outdoor, and high-speed mobile environments. Existing methods often struggle to generate datasets that cover these diverse scenarios, resulting in limited applicability of the evaluation results.
[0349] 3. Limitations of the evaluation method.
[0350] The difference between ideal and actual data: Existing evaluation methods typically use ideal data (without measurement error) as a benchmark, but in practical applications, measurement error is unavoidable. This difference causes the evaluation results to deviate from actual performance, affecting the accuracy of the evaluation.
[0351] To address the aforementioned technical issues, this disclosure provides a method and apparatus for generating beam management models. The method generates M beam management datasets without measurement errors based on parameter configuration information; selects N beam management datasets from the M datasets; superimposes measurement errors onto the received power of each layer 1 reference signal included in the N datasets; and uses the N beam management datasets with superimposed measurement errors to generate a beam management model. The beam management model generation method and apparatus proposed in this disclosure employ a standardized generation process, enabling the alignment of beam management performance evaluation results from different equipment vendors and improving the standardization level of beam management performance evaluation.
[0352] Figure 2 is one of the exemplary interactive diagrams of the beam management model generation method provided in this disclosure embodiment. As shown in Figure 2, this disclosure embodiment relates to a beam management model generation method, which includes:
[0353] Step 201: Network device 102 sends a configuration message to terminal 101. Terminal 101 receives the configuration message sent by network device 102.
[0354] In some implementations, the configuration message may include parameter configuration information used to generate beam management data. The configuration message may also include parameters for determining measurement errors.
[0355] In some implementations, the parameter configuration information includes predefined SLS assumption parameters.
[0356] In some implementations, the parameter configuration information may also include at least one of the following: transmit beam mode parameters; receive beam mode parameters; channel parameters; scenario parameters.
[0357] In some implementations, the transmitted beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0358] In some implementations, the received beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0359] In some implementations, the channel parameters include at least one of the following: carrier frequency; subcarrier spacing; channel model.
[0360] In some implementations, the scenario parameters include at least one of the following: macro cell; micro cell; indoor cell; outdoor cell; proportion of macro cells; proportion of micro cells; proportion of indoor cells; proportion of outdoor cells.
[0361] In some implementations, the parameters used to determine the measurement error include the mapping relationship between the signal-to-noise ratio and the target variance, with the measurement error conforming to a Gaussian distribution whose variance is equal to the target variance.
[0362] In some implementations, the parameters used to determine the measurement error include the mapping relationship between the layer 1 reference signal received power and the target variance, with the measurement error conforming to a Gaussian distribution with a variance equal to the target variance.
[0363] In some implementations, the configuration message includes a first message and a second message. The first message carries parameter configuration information. The second message carries parameters used to determine the measurement error. For example, the second message carries the mapping relationship between the signal-to-noise ratio and the target variance. As another example, the second message carries the mapping relationship between the layer 1 reference signal received power and the target variance.
[0364] Step 202: Terminal 101 generates M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data. M is an integer greater than 1.
[0365] In some implementations, the parameter configuration information can be predefined by the protocol.
[0366] In some implementations, parameter configuration information can be sent from the network device to the terminal.
[0367] In some implementations, each beam management data includes the Layer 1 reference signal received power and the signal-to-noise ratio corresponding to the Layer 1 reference signal received power for the transmit and receive beam pairs.
[0368] In some implementations, each beam management dataset can correspond to a simulation terminal, that is, the data is divided into M sets according to different simulation terminals.
[0369] Step 203: Terminal 101 selects N beam management datasets from the M beam management datasets; N is an integer greater than 1, and M is greater than or equal to N.
[0370] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0371] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0372] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0373] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0374] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0375] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0376] For example, the first preset threshold is -3dB. The maximum signal-to-noise ratio in each beam management dataset is equal to -3dB.
[0377] For example, the second preset threshold is -3dB, and the custom distribution is shown in Table 1.
[0378] Table 1 Example of a custom distribution
[0379] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0380] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0381] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0382] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0383] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0384] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0385] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0386] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0387] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0388] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0389] Step 204: Terminal 101 verifies the selected N beam management datasets.
[0390] In some implementations, the same method as the screening criteria is used to validate the selected N beam management datasets.
[0391] For example, the selected N beam management datasets meet the following conditions: the maximum signal-to-noise ratio (SNR) in each beam management dataset is greater than a second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum SNR of each beam management dataset. Then it can be verified whether the maximum SNR in each of the selected N beam management datasets is greater than the second preset threshold, and whether the data in the first dataset follows a Gaussian distribution.
[0392] For example, if the selected N beam management datasets meet the condition that the signal-to-noise ratio (SNR) of each beam management dataset follows a Gaussian distribution, then it can be verified that the SNR of each beam management dataset follows a Gaussian distribution.
[0393] In some implementations, the conditions for selecting N beam management datasets can be disregarded. After selecting N beam management datasets, a unified method is used to verify them. If the verification passes, the candidate step is executed; if the verification fails, the data is re-selected.
[0394] For example, generate the cumulative distribution function (CDF) curves of SNR for N beam management datasets. Use the CDF curves to determine the accuracy of the N beam management datasets. Calculate the SNR values at the 5% and 95% of the CDF curves and compare them to preset thresholds or thresholds configured in the network device. If the SNR values at the 5% and / or 95% are within the error range of the thresholds, the selected N beam management datasets are verified; otherwise, the data is re-selected.
[0395] Step 205, terminal 101 determines the measurement error.
[0396] In some implementations, the measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0397] The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0398] In some implementations, the above mapping relationship is predefined by the protocol.
[0399] In some implementations, the above mapping relationship is sent to the terminal by the network device.
[0400] In some implementations, the mapping relationship includes at least one of linear mapping, logarithmic mapping, and custom mapping.
[0401] In some implementations, measurement error can also be predefined by the protocol. Measurement error can be defined by defining the correspondence between SNR and variance. For example, the correspondence between SNR and variance is shown in Table 2.
[0402] Table 2 shows the relationship between SNR and variance.
[0403] Step 206: Terminal 101 injects measurement error.
[0404] In some implementations, after determining the measurement error corresponding to the received power of the reference signal at each layer 1, terminal 101 superimposes the corresponding measurement error onto the received power of the reference signal at each layer 1.
[0405] In some implementations, the received power of the Layer 1 reference signal after superimposed measurement errors can also be verified.
[0406] For example, select the maximum Layer 1 reference signal received power for each of the N beam management datasets, and verify whether the maximum Layer 1 reference signal received power conforms to at least one of the following distributions: custom distribution, Gaussian distribution, uniform distribution, CDF distribution, etc.
[0407] For example, verify whether the received power of each middle layer 1 reference signal conforms to at least one of the following distributions: custom distribution, Gaussian distribution, uniform distribution, CDF distribution, etc.
[0408] For example, consider the received power of all Layer 1 reference signals in N beam management datasets as a whole, and verify whether it conforms to at least one of the following distributions: custom distribution, Gaussian distribution, uniform distribution, CDF distribution, etc.
[0409] Step 207: Terminal 101 sends N beam management datasets after superimposing measurement errors to network device 102. Network device 102 receives the N beam management datasets after superimposing measurement errors sent by terminal 101.
[0410] In some implementations, beam management performance evaluation can be performed by the terminal.
[0411] In some implementations, beam management performance evaluation can also be performed by the network device.
[0412] When the data is generated by the terminal and the beam management performance evaluation is performed by the network device, the terminal sends N beam management datasets with superimposed measurement errors to the network device.
[0413] Step 208: Network device 102 performs beam management performance evaluation.
[0414] In some implementations, beam management performance evaluation includes generating a beam management model based on N beam management datasets with superimposed measurement errors.
[0415] In some implementations, network devices use N beam management datasets with superimposed measurement errors to train a beam management model, thus obtaining a trained beam management model.
[0416] In some implementations, network devices use N beam management datasets with superimposed measurement errors to validate the beam management model, thus obtaining the validated beam management model.
[0417] In some implementations, the beam management model is an artificial intelligence (AI) model.
[0418] For example, network devices train an AI model using N beam management datasets with superimposed measurement errors, resulting in a trained AI model. This trained AI model is then used for beam prediction.
[0419] For example, network devices use N beam management datasets with superimposed measurement errors to validate the AI model, resulting in a validated AI model. The validated AI model is then used for beam prediction.
[0420] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.
[0421] In some embodiments, the terms "codebook," "codeword," and "precoding matrix" can be used interchangeably. For example, a codebook can be a collection of one or more codewords / precoding matrices.
[0422] In some embodiments, the terms "uplink", "uplink", and "physical uplink" can be used interchangeably, as can the terms "downlink", "downlink", and "physical downlink", as well as the terms "sidelink", "sidelink", "sidelink communication", "sidelink communication", "direct connection", "direct link", "direct communication", and "direct link communication".
[0423] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.
[0424] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".
[0425] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.
[0426] In some embodiments, the terms "search space", "search space set", "search space configuration", "search space set configuration", "control resource set (CORESET)", and "CORESET configuration" can be used interchangeably.
[0427] In some embodiments, the terms "synchronization signal (SS)," "synchronization signal block (SSB)," "reference signal (RS)," "pilot," and "pilot signal" can be used interchangeably.
[0428] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”
[0429] In some embodiments, the terms "component carrier (CC)," "cell," "frequency carrier," and "carrier frequency" can be used interchangeably.
[0430] In some embodiments, the terms “resource block (RB)”, “physical resource block (PRB)”, “sub-carrier group (SCG)”, “resource element group (REG)”, “PRB pair”, “RB pair”, “resource element (RE)”, and “sub-carrier” can be used interchangeably.
[0431] In some embodiments, terms such as wireless access scheme and waveform can be used interchangeably.
[0432] In some embodiments, the terms "precoding", "precoder", "weight", "precoding weight", "quasi-co-location (QCL)", "transmission configuration indication (TCI) status", "spatial relation", "spatial domain filter", "transmission power", "phase rotation", "antenna port", "antenna port group", "layer", "the number of layers", "rank", "resource", "resource set", "resource group", "beam", "beam width", "beam angular degree", "antenna", "antenna element", and "panel" can be used interchangeably.
[0433] In some embodiments, the terms “frame”, “radio frame”, “subframe”, “slot”, “sub-slot”, “mini-slot”, “symbol”, “symbol”, and “transmission time interval (TTI)” can be used interchangeably.
[0434] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.
[0435] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.
[0436] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.
[0437] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values (e.g., a comparison with a predetermined value), but is not limited thereto.
[0438] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data and / or instructions received; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the receiver to respond to the sent content.
[0439] In some embodiments, if an arrow in the interaction diagram representing the sending of information, signaling, etc. from one subject to another passes through other subjects, it can be interpreted as the information being forwarded from one subject to another via other subjects, or it can be interpreted as the information being sent from one subject to another without passing through other subjects.
[0440] The beam management model generation method disclosed in this embodiment may include at least one of steps 201 to 208. For example, steps 202+203+206 can be implemented as independent embodiments, steps 201+202+203+206 can be implemented as independent embodiments, steps 202+203+204+206 can be implemented as independent embodiments, steps 202+203+205+206 can be implemented as independent embodiments, steps 202+203+204+205+206 can be implemented as independent embodiments, and steps 201+202+203+204+205+206+207+208 can be implemented as independent embodiments, but are not limited thereto.
[0441] In some embodiments, steps 201, 204, 205, 207, and 208 are optional, and one or more of these steps may be omitted or substituted in different embodiments.
[0442] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.
[0443] Figure 3 is a second exemplary interactive schematic diagram of the beam management model generation method provided in this embodiment of the present disclosure. As shown in Figure 3, this embodiment of the present disclosure relates to a beam management model generation method, which includes:
[0444] Step 301: Terminal 101 sends a configuration message to network device 102. Network device 102 receives the configuration message sent by terminal 101.
[0445] In some implementations, the configuration message may include parameter configuration information used to generate beam management data. The configuration message may also include parameters for determining measurement errors.
[0446] In some implementations, the parameter configuration information includes predefined SLS assumption parameters.
[0447] In some implementations, the parameter configuration information may also include at least one of the following: transmit beam mode parameters; receive beam mode parameters; channel parameters; scenario parameters.
[0448] In some implementations, the transmitted beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0449] In some implementations, the received beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0450] In some implementations, the channel parameters include at least one of the following: carrier frequency; subcarrier spacing; channel model.
[0451] In some implementations, the scenario parameters include at least one of the following: macro cell; micro cell; indoor cell; outdoor cell; proportion of macro cells; proportion of micro cells; proportion of indoor cells; proportion of outdoor cells.
[0452] In some implementations, the parameters used to determine the measurement error include the mapping relationship between the signal-to-noise ratio and the target variance, with the measurement error conforming to a Gaussian distribution whose variance is equal to the target variance.
[0453] In some implementations, the parameters used to determine the measurement error include the mapping relationship between the layer 1 reference signal received power and the target variance, with the measurement error conforming to a Gaussian distribution with a variance equal to the target variance.
[0454] In some implementations, the configuration message includes a first message and a second message. The first message carries parameter configuration information. The second message carries parameters used to determine the measurement error. For example, the second message carries the mapping relationship between the signal-to-noise ratio and the target variance. As another example, the second message carries the mapping relationship between the layer 1 reference signal received power and the target variance.
[0455] Step 302: Network device 102 generates M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data. M is an integer greater than 1.
[0456] In some implementations, the parameter configuration information can be predefined by the protocol.
[0457] In some implementations, parameter configuration information can be sent from the terminal to the network device.
[0458] Step 303: Network device 102 selects N beam management datasets from the M beam management datasets; N is an integer greater than 1, and M is greater than or equal to N.
[0459] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0460] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0461] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0462] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0463] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0464] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0465] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0466] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0467] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0468] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0469] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0470] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0471] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0472] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0473] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0474] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0475] Step 304, network device 102 determines the measurement error.
[0476] In some implementations, the measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0477] The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0478] In some implementations, the above mapping relationship is predefined by the protocol.
[0479] In some implementations, the above mapping relationship is sent by the terminal to the network device.
[0480] In some implementations, the mapping relationship includes at least one of linear mapping, logarithmic mapping, and custom mapping.
[0481] In some implementations, measurement errors can also be predefined by the protocol.
[0482] Step 305: Network device 102 injects measurement error.
[0483] In some implementations, after determining the measurement error corresponding to the received power of the reference signal at each layer 1, the network device 102 superimposes the corresponding measurement error onto the received power of the reference signal at each layer 1.
[0484] Step 306: Network device 102 performs beam management performance evaluation.
[0485] In some implementations, beam management performance evaluation includes generating a beam management model based on N beam management datasets with superimposed measurement errors.
[0486] In some implementations, network devices use N beam management datasets with superimposed measurement errors to train a beam management model, thus obtaining a trained beam management model.
[0487] In some implementations, network devices use N beam management datasets with superimposed measurement errors to validate the beam management model, thus obtaining the validated beam management model.
[0488] In some implementations, the beam management model is an artificial intelligence (AI) model.
[0489] For example, network devices train an AI model using N beam management datasets with superimposed measurement errors, resulting in a trained AI model. This trained AI model is then used for beam prediction.
[0490] For example, network devices use N beam management datasets with superimposed measurement errors to validate the AI model, resulting in a validated AI model. The validated AI model is then used for beam prediction.
[0491] The beam management model generation method disclosed in this embodiment may include at least one of steps 301 to 306. For example, steps 302+303+305 can be implemented as an independent embodiment, steps 301+302+303+305 can be implemented as an independent embodiment, steps 302+303+304+305 can be implemented as an independent embodiment, and steps 301+302+303+304+305+306 can be implemented as an independent embodiment, but are not limited thereto.
[0492] In some embodiments, steps 301, 304, and 306 are optional, and one or more of these steps may be omitted or substituted in different embodiments.
[0493] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.
[0494] Figure 4 is a third exemplary interactive schematic diagram of the beam management model generation method provided in this embodiment of the present disclosure. As shown in Figure 4, this embodiment of the present disclosure relates to a beam management model generation method, which includes:
[0495] Step 401: Terminal 101 generates M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data. M is an integer greater than 1.
[0496] In some implementations, the parameter configuration information can be predefined by the protocol.
[0497] In some implementations, the parameter configuration information includes predefined SLS assumption parameters.
[0498] In some implementations, the parameter configuration information may also include at least one of the following: transmit beam mode parameters; receive beam mode parameters; channel parameters; scenario parameters.
[0499] In some implementations, the transmitted beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0500] In some implementations, the received beam pattern parameters include at least one of the following: number of panels; number of horizontal array elements; number of vertical array elements; main lobe direction; beamforming method.
[0501] In some implementations, the channel parameters include at least one of the following: carrier frequency; subcarrier spacing; channel model.
[0502] In some implementations, the scenario parameters include at least one of the following: macro cell; micro cell; indoor cell; outdoor cell; proportion of macro cells; proportion of micro cells; proportion of indoor cells; proportion of outdoor cells.
[0503] Step 402, terminal 101 selects N beam management datasets from the M beam management datasets; N is an integer greater than 1, and M is greater than or equal to N.
[0504] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0505] The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold;
[0506] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0507] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0508] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset;
[0509] The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
[0510] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0511] The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value;
[0512] The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution;
[0513] The signal-to-noise ratio in each beam management dataset follows a uniform distribution;
[0514] In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
[0515] In some implementations, the N beam management datasets satisfy at least one of the following conditions:
[0516] The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value.
[0517] The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution.
[0518] The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution;
[0519] The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
[0520] Step 403, terminal 101 determines the measurement error.
[0521] In some implementations, the measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0522] The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
[0523] In some implementations, the above mapping relationship is predefined by the protocol.
[0524] In some implementations, the above mapping relationship is sent by the terminal to the network device.
[0525] In some implementations, the mapping relationship includes at least one of linear mapping, logarithmic mapping, and custom mapping.
[0526] In some implementations, measurement errors can also be predefined by the protocol.
[0527] Step 404: Terminal 101 injects measurement error.
[0528] In some implementations, after determining the measurement error corresponding to the received power of the reference signal at each layer 1, terminal 101 superimposes the corresponding measurement error onto the received power of the reference signal at each layer 1.
[0529] Step 405: Terminal 101 sends N beam management datasets after superimposing measurement errors to network device 102. Network device 102 receives the N beam management datasets after superimposing measurement errors sent by terminal 101.
[0530] In some implementations, beam management performance evaluation can be performed by the terminal.
[0531] In some implementations, beam management performance evaluation can also be performed by the network device.
[0532] When the data is generated by the terminal and the beam management performance evaluation is performed by the network device, the terminal sends N beam management datasets with superimposed measurement errors to the network device.
[0533] Step 406: Network device 102 performs beam management performance evaluation.
[0534] In some implementations, beam management performance evaluation includes generating a beam management model based on N beam management datasets with superimposed measurement errors.
[0535] In some implementations, network devices use N beam management datasets with superimposed measurement errors to train a beam management model, thus obtaining a trained beam management model.
[0536] In some implementations, network devices use N beam management datasets with superimposed measurement errors to validate the beam management model, thus obtaining the validated beam management model.
[0537] In some implementations, the beam management model is an artificial intelligence (AI) model.
[0538] For example, network devices train an AI model using N beam management datasets with superimposed measurement errors, resulting in a trained AI model. This trained AI model is then used for beam prediction.
[0539] For example, network devices use N beam management datasets with superimposed measurement errors to validate the AI model, resulting in a validated AI model. The validated AI model is then used for beam prediction.
[0540] The beam management model generation method disclosed in this embodiment may include at least one of steps 401 to 406. For example, steps 401+402+404 can be implemented as an independent embodiment, steps 401+402+403+404 can be implemented as an independent embodiment, steps 401+402+404+405+406 can be implemented as an independent embodiment, and steps 401+402+403+404+405+406 can be implemented as an independent embodiment, but are not limited thereto.
[0541] In some embodiments, steps 403, 405, and 406 are optional, and one or more of these steps may be omitted or substituted in different embodiments.
[0542] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.
[0543] The beam management model generation method in the above embodiments is further illustrated by the following example:
[0544] The beam management model generation method may include the following steps:
[0545] Step 1: Generate beam management data (L1-RSRP and corresponding SNR) without measurement errors.
[0546] The parameters configured to generate beam management data free of measurement errors are as follows:
[0547] Transmit beam pattern (TX beam pattern): Predefined or transmitted to the UE via signaling from the network, including at least one of the following parameters:
[0548] Number of panels;
[0549] Number of horizontal and vertical array elements;
[0550] Main lobe direction;
[0551] Beamforming method.
[0552] Receive beam pattern (RX beam pattern): Predefined or network device receives RX beam pattern parameters uploaded by the UE, including at least one of the following parameters:
[0553] Number of panels;
[0554] Number of horizontal and vertical array elements;
[0555] Main lobe direction;
[0556] Beamforming method.
[0557] Channel parameters include carrier frequency, subcarrier spacing, and channel model.
[0558] Scenario: Microcell (Umi), Macrocell (Uma), Indoor Cell, Outdoor Cell, and their respective proportions.
[0559] Multiple datasets are generated based on the parameter configuration. Each dataset includes the L1-RSRP values and corresponding SNR values of multiple TX-RX beam pairs. For example, this dataset is set A.
[0560] Step 2: Filter the data that meets the criteria.
[0561] Select a subset of TX-RX beam pairs from set A and their corresponding L1-RSRP values and SNR values to form dataset set B. Ensure that the SNR distribution of set B satisfies the following conditions:
[0562] Option A: A graded SNR distribution model, which must satisfy at least one of the following conditions:
[0563] 1. Maximum SNR distribution model:
[0564] The maximum SNR across multiple sets B must satisfy a predefined condition. For example, assuming there are 100 sets B, there are 100 maximum SNR values. These maximum SNRs must satisfy at least one of the following:
[0565] The maximum SNR is a fixed threshold value, such as -3dB;
[0566] The maximum SNR is greater than a certain threshold, and the maximum SNR follows a predefined distribution, which includes at least one of the following:
[0567] Gaussian distribution, for example, maximum SNR mean of 5, variance of 5dB;
[0568] Uniform distribution, for example, a range of SNR = [-3dB, 15dB];
[0569] A custom distribution is used to divide the maximum SNR into different ranges and determine the weight of each range. For example, if the total SNR range is [-5dB, 10dB], then the SNR in the range of [-5dB, 5dB] accounts for 40%, and the SNR in the range of [5dB, 10dB] accounts for 60%.
[0570] The CDF curve of SNR meets preset conditions. For example, the SNR corresponding to 5% CDF value is a1, and the SNR corresponding to 95% CDF value is b1. a1 and b1 are predefined values or values obtained through signaling interaction.
[0571] 2. SNR distribution model of TX-RX beam pairs within each Set B:
[0572] The SNR distribution of the TX-RX beam pairs in each set B satisfies a predefined distribution. This distribution includes at least one of the following:
[0573] Gaussian distribution, for example, maximum SNR mean of 5, variance of 5dB;
[0574] Uniform distribution, for example, a range of SNR = [-3dB, 15dB];
[0575] A custom distribution is used to divide the maximum SNR into different ranges and determine the weight of each range. For example, if the total SNR range is [-5dB, 10dB], then the SNR in the range of [-5dB, 5dB] accounts for 40%, and the SNR in the range of [5dB, 10dB] accounts for 60%.
[0576] The CDF curve of SNR meets preset conditions. For example, the SNR corresponding to 5% CDF value is a1, and the SNR corresponding to 95% CDF value is b1. a1 and b1 are predefined values or values obtained through signaling interaction.
[0577] Option B: The distribution of all SNRs in multiple setB sets satisfies a distribution model. This distribution includes at least one of the following:
[0578] Gaussian distribution, for example, maximum SNR mean of 5, variance of 5dB;
[0579] Uniform distribution, for example, a range of SNR = [-3dB, 15dB];
[0580] A custom distribution is used to divide the maximum SNR into different ranges and determine the weight of each range. For example, if the total SNR range is [-5dB, 10dB], then the SNR in the range of [-5dB, 5dB] accounts for 40%, and the SNR in the range of [5dB, 10dB] accounts for 60%.
[0581] The CDF curve of SNR meets preset conditions. For example, the SNR corresponding to 5% CDF value is a1, and the SNR corresponding to 95% CDF value is b1. a1 and b1 are predefined values or values obtained through signaling interaction.
[0582] Step 3: Data calibration / data verification.
[0583] Generate CDF curves based on the SNR from multiple setB sets.
[0584] Calculate the SNR values of the CDF curve at 5% and 95%.
[0585] Compare the calculated values with the predefined thresholds a2 and b2.
[0586] If the calculated values are within the threshold range (CDF(0.05)≈a2, CDF(0.95)≈b2), then the dataset calibration is successful; otherwise, adjust the error model parameters and regenerate the dataset.
[0587] Step 4: Measurement error generation.
[0588] The following schemes can be used to map the variance of the Gaussian distribution of the error:
[0589] Option 1: Create a mapping table for each TX-RX beam SNR to the variance or standard deviation of the Gaussian distribution of the error. This mapping table can be predefined.
[0590] For example, when the SNR of the TX-RX beam is -3dB, the measurement error variance σ = 1.0; when the SNR of the TX-RX beam is 0dB, the measurement error variance σ = 0.5.
[0591] Mode 1 (Linear Mapping): SNR(dB) = [-5, 0, 5] → σ 2 =[1.2,0.8,0.3].
[0592] Pattern 2 (Logarithmic mapping): SNR(dB) = [-3, 3, 9] → σ 2 =[1.0 / (1+SNR),0.5 / (1+SNR),...].
[0593] Option 2: Establish a fixed mapping table between TX-RX beams and Gaussian distribution variance / standard deviation. Sort the L1-RSRP of the TX-RX beams in descending order. The beam index ranked first is fixedly added with Gaussian noise with a variance of a, the beam index ranked second is fixedly added with Gaussian noise with a variance of b, and the beam index ranked third is fixedly added with Gaussian noise with a variance of c. The Gaussian error added to different beams is independent of the SNR, and is only related to the beam index ranking, where a<b<c, and the earlier the beam is ranked, the smaller the variance. For example, the corresponding variances of the three TX-RX beams are σ1=0.1, σ2=0.3, σ3=0.5.
[0594] Option 3: Support custom mapping table upload by equipment vendors.
[0595] The mapping table uploaded by the equipment vendor contains the corresponding relationship between SNR and variance or standard deviation. The corresponding relationship can also be a predefined array, and the interaction is the index number of the TX-RX beam. For example, the corresponding relationship between SNR and variance is shown in Table 2.
[0596] After determining the variance / standard deviation of the Gaussian distribution error, a measurement error value error conforming to the Gaussian distribution is generated.
[0597] Step 5: Error injection.
[0598] According to the generated measurement error value error, the measurement error conforming to the Gaussian variance is added to the L1-RSRP value of each TX-RX beam pair in the set B, so as to generate an error-containing L1-RSRP value. The calculation formula is as follows: L1-RSRP error =L1-RSRP+error
[0599] Step 6: Perform predictive capability model evaluation.
[0600] The L1-RSRP value after error superposition is used as reference data, which is input to the UE for model evaluation.
[0601] Record the evaluation results, including performance indicators such as beam prediction accuracy and absolute RSRP accuracy.
[0602] The beam management model generation method proposed in the embodiments of the present disclosure has at least one of the following effects:
[0603] 1. Unified dynamic error model:
[0604] Mapping rule between SNR and Gaussian error variance: a dynamic mapping relationship between SNR and Gaussian error variance is established, which supports predefinition or dynamic configuration through signaling. This mapping rule can more accurately simulate the measurement error in the actual environment, and improve the evaluation accuracy.
[0605] Multiple error mapping modes: It provides multiple error mapping modes such as linear mapping, logarithmic mapping, and fixed variance allocation based on beam index sorting. It also supports the upload of custom mapping tables by equipment manufacturers, which increases flexibility and adaptability.
[0606] 2. Controllable SNR distribution generation mechanism:
[0607] Multiple rounds of testing generate a Set B that satisfies the predefined SNR distribution: A Set B is generated through multiple tests to ensure that the SNR distribution of the dataset meets the requirements of the actual application scenario. It supports hierarchical control of the maximum SNR distribution and global control of the SNR distribution of all beam pairs within Set B, using CDF curve threshold constraints to ensure data distribution consistency.
[0608] 3. Statistical alignment calibration:
[0609] CDF curve calibration: By calculating the L1-RSRP values of the CDF curve at 5% and 95% and comparing them with predefined thresholds, it ensures that the dataset after error injection matches the target distribution. This calibration mechanism can effectively verify the accuracy of the dataset and improve the consistency of the evaluation.
[0610] 4. Beam mode dynamic configuration mechanism:
[0611] Dynamic configuration of TX-RX beam parameters: Supports predefined or signaling interaction of TX and RX beam parameters (number of panels, array element orientation, beamforming method), enabling the system to dynamically adjust the beam mode according to different scenarios and requirements.
[0612] Dynamic configuration of channel scenario parameters: Supports the configuration of proportions for different scenarios such as Umi, Uma, indoor, and outdoor, generating datasets covering multiple scenarios to improve the comprehensiveness and applicability of the evaluation.
[0613] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.
[0614] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.
[0615] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).
[0616] Figure 5A is a schematic diagram of the terminal structure proposed in an embodiment of this disclosure. The terminal 5100 is used to execute any of the above methods. In some embodiments, as shown in Figure 5A, the terminal 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, the processing module is used to generate M beam management datasets without measurement errors according to parameter configuration information; each beam management dataset includes multiple beam management data; select N beam management datasets from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; superimpose measurement errors on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing measurement errors are used to generate a beam management model. Optionally, the transceiver module is used to execute at least one of the communication steps (e.g., steps 201, 207, 301, 405, but not limited thereto) executed by the terminal 101 in any of the above methods, which will not be described in detail here. Optionally, the above processing module is used to execute at least one of the other steps executed by the terminal 101 in any of the above methods (e.g., steps 202, 203, 204, 205, 206, 401, 402, 403, 404, but not limited thereto), which will not be elaborated here.
[0617] Figure 5B is a schematic diagram of the structure of a network device proposed in an embodiment of this disclosure. The network device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the network device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the processing module is used to generate M beam management datasets without measurement errors based on parameter configuration information; each beam management dataset includes multiple beam management data; N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; measurement errors are superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing measurement errors are used to generate a beam management model. Optionally, the transceiver module is used to perform at least one of the communication steps (e.g., steps 201, 207, 301, 405, but not limited thereto) performed by the network device 102 in any of the above methods, which will not be elaborated further here. Optionally, the above processing module is used to execute at least one of the other steps (e.g., steps 208, 302, 303, 304, 305, 306, 406, but not limited thereto) executed by the network device 102 in any of the above methods, which will not be elaborated here.
[0618] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.
[0619] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module.
[0620] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.
[0621] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.
[0622] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a special-purpose processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.
[0623] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps 201, 207, 301, 405, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps 202, 203, 204, 205, 206, 401, 402, 403, 404, 208, 302, 303, 304, 305, 306, 406, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated together. Optionally, terms such as transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface can be used interchangeably; terms such as transmitter, transmitter unit, transmitter, and transmitter circuit can be used interchangeably; and terms such as receiver, receiver unit, receiver, and receiver circuit can be used interchangeably.
[0624] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In an optional embodiment, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6103 and can be used to receive data and / or instructions from the memory 6103 or other devices, and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and send the data and / or instructions to the processor 6101.
[0625] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.
[0626] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.
[0627] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.
[0628] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.
[0629] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps 201, 207, 301, and 405, but not limited thereto). The interface circuit 6202 performing the communication steps such as sending and / or receiving in the above-described method refers, for example, to the interface circuit 6202 performing data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps 202, 203, 204, 205, 206, 401, 402, 403, 404, 208, 302, 303, 304, 305, 306, and 406, but not limited thereto).
[0630] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.
[0631] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.
[0632] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.
[0633] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.
Claims
1. A method for generating a beam management model, executed by a terminal, characterized in that, The method includes: M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data. N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
2. The beam management model generation method according to claim 1, characterized in that, The parameter configuration information includes at least one of the following: Transmit beam mode parameters; Receive beam mode parameters; Channel parameters; Scene parameters.
3. The beam management model generation method according to claim 2, characterized in that, The transmission beam mode parameters include at least one of the following: Number of panels; Number of elements in a horizontal array; Number of vertical array elements; Main lobe direction; Beamforming method.
4. The beam management model generation method according to any one of claims 2 to 3, characterized in that, The method further includes: Receive a first message sent by a network device; the first message contains the transmission beam mode parameters.
5. The beam management model generation method according to claim 2, characterized in that, The received beam mode parameters include at least one of the following: Number of panels; Number of elements in a horizontal array; Number of vertical array elements; Main lobe direction; Beamforming method.
6. The beam management model generation method according to claim 2, characterized in that, The channel parameters include at least one of the following: Carrier frequency; Subcarrier spacing; Channel model.
7. The beam management model generation method according to claim 2, characterized in that, The scene parameters include at least one of the following: Hongxiaoqu; micro-region; Indoor residential area; Outdoor residential area; The proportion of macrocells; The proportion of micro-regions; The proportion of indoor communities; The proportion of outdoor residential areas.
8. The beam management model generation method according to any one of claims 1 to 7, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
9. The beam management model generation method according to any one of claims 1 to 8, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value; The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution; The signal-to-noise ratio in each beam management dataset follows a uniform distribution; In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
10. The beam management model generation method according to any one of claims 1 to 9, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value. The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution. The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution; The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
11. The beam management model generation method according to any one of claims 1 to 10, characterized in that, The method further includes: The measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
12. The beam management model generation method according to any one of claims 1 to 10, characterized in that, The method further includes: The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
13. The beam management model generation method according to any one of claims 11 to 12, characterized in that, The mapping relationship is predefined; Alternatively, the method may further include: Receive the second message sent by the network device; The second message contains the mapping relationship.
14. The beam management model generation method according to any one of claims 1 to 13, characterized in that, The method further includes at least one of the following: The beam management model is trained using N beam management datasets with superimposed measurement errors. The beam management model was validated using N beam management datasets with superimposed measurement errors.
15. A method for generating a beam management model, executed by a network device, characterized in that, The method includes: M beam management datasets without measurement errors are generated based on the parameter configuration information; each beam management dataset includes multiple beam management data. N beam management datasets are selected from the M beam management datasets; M is an integer greater than 1, N is an integer greater than 1, and M is greater than or equal to N; The measurement error is superimposed on the received power of each layer 1 reference signal included in the N beam management datasets; the N beam management datasets after superimposing the measurement error are used to generate the beam management model.
16. The beam management model generation method according to claim 15, characterized in that, The parameter configuration information includes at least one of the following: Transmit beam mode parameters; Receive beam mode parameters; Channel parameters; Scene parameters.
17. The beam management model generation method according to claim 16, characterized in that, The received beam mode parameters include at least one of the following: Number of panels; Number of elements in a horizontal array; Number of vertical array elements; Main lobe direction; Beamforming method.
18. The beam management model generation method according to any one of claims 16 to 17, characterized in that, The method further includes: The receiving terminal sends a third message; the third message contains the receiving beam mode parameters.
19. The beam management model generation method according to claim 16, characterized in that, The transmission beam mode parameters include at least one of the following: Number of panels; Number of elements in a horizontal array; Number of vertical array elements; Main lobe direction; Beamforming method.
20. The beam management model generation method according to claim 16, characterized in that, The channel parameters include at least one of the following: Carrier frequency; Subcarrier spacing; Channel model.
21. The beam management model generation method according to claim 16, characterized in that, The scene parameters include at least one of the following: Hongxiaoqu; micro-region; Indoor residential area; Outdoor residential area; The proportion of macrocells; The proportion of micro-regions; The proportion of indoor communities; The proportion of outdoor residential areas.
22. The beam management model generation method according to any one of claims 15 to 21, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The maximum signal-to-noise ratio in each beam management dataset is equal to the first preset threshold; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset follows a Gaussian distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the data in the first dataset satisfies a uniform distribution; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; The maximum signal-to-noise ratio in each beam management dataset is greater than the second preset threshold, and the signal-to-noise ratio corresponding to the cumulative probability x on the cumulative distribution function curve of the data in the first dataset is a, and the signal-to-noise ratio corresponding to the cumulative probability 1-x is b; the first dataset is a set composed of the maximum signal-to-noise ratio in each beam management dataset; x, a, and b are all preset values.
23. The beam management model generation method according to any one of claims 15 to 22, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The signal-to-noise ratio in each beam management dataset satisfies a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value; The signal-to-noise ratio in each beam management dataset follows a Gaussian distribution; The signal-to-noise ratio in each beam management dataset follows a uniform distribution; In each beam management dataset, the cumulative distribution function curve of the signal-to-noise ratio (SNR) corresponds to the SNR of cumulative probability y as c, and the cumulative probability of 1-y corresponds to the SNR of d; y, c, and d are all preset values.
24. The beam management model generation method according to any one of claims 15 to 23, characterized in that, The N beam management datasets satisfy at least one of the following conditions: The signal-to-noise ratios in the N beam management datasets satisfy a custom distribution; the custom distribution includes multiple continuous distribution intervals, the endpoints of each distribution interval are preset values, and the proportion of each distribution interval is a preset value. The signal-to-noise ratios in the N beam management datasets follow a Gaussian distribution. The signal-to-noise ratios in the N beam management datasets satisfy a uniform distribution; The cumulative distribution function curve of the signal-to-noise ratio (SNR) in the N beam management datasets has an SNR of e corresponding to a cumulative probability z, and an SNR of f corresponding to a cumulative probability of 1-z; z, e, and f are all preset values.
25. The beam management model generation method according to any one of claims 1 to 24, characterized in that, The method further includes: The measurement error of the superimposed received power of each layer 1 reference signal is determined based on the mapping relationship between the signal-to-noise ratio and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
26. The beam management model generation method according to any one of claims 1 to 24, characterized in that, The method further includes: The measurement error of the superimposed layer 1 reference signal received power is determined based on the mapping relationship between the layer 1 reference signal received power and the target variance; the measurement error conforms to a Gaussian distribution with a variance equal to the target variance.
27. The beam management model generation method according to any one of claims 25 to 26, characterized in that, The mapping relationship is predefined; Alternatively, the method may further include: The receiving terminal sends a fourth message; the fourth message contains the mapping relationship.
28. The beam management model generation method according to any one of claims 1 to 27, characterized in that, The method further includes at least one of the following: The beam management model is trained using N beam management datasets with superimposed measurement errors. The beam management model was validated using N beam management datasets with superimposed measurement errors.
29. A communication device, characterized in that, The communication device is used to execute the beam management model generation method according to any one of claims 1 to 14, or the beam management model generation method according to any one of claims 15 to 28.
30. A communication system, characterized in that, The device includes a terminal and a network device, wherein the terminal is configured to implement the beam management model generation method according to any one of claims 1 to 14, and the network device is configured to implement the beam management model generation method according to any one of claims 15 to 28.
31. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the beam management model generation method according to any one of claims 1 to 14, or the beam management model generation method according to any one of claims 15 to 28.
32. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by the communication device, it implements the beam management model generation method according to any one of claims 1 to 14, or the beam management model generation method according to any one of claims 15 to 28.
