Information transmission method and communication device

Abstract

The invention provides an information transmission method and a communication device, and relates to the technical field of communication. In the method, a first device can determine a sample needing to be reported according to a sample distribution condition in a plurality of obtained samples and send indication information for indicating the sample needing to be reported to a second device, and the second device sends the sample needing to be reported to the first device according to the indication information. Therefore, the first device can construct the sample set with more uniform sample distribution, the sample set can be used for AI model training, and in the training process, the AI model can learn the characteristics of most or all samples, so that the accuracy of the AI model can be improved, and a more objective reasoning result can be output.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to an information transmission method and a communication device. Background Art

[0002] During the beam management process, both the network device and the terminal device need to traverse the candidate beams, and determine their respective optimal beams based on the comparison of the beam measurement results, and establish beam pairs between the network device and the terminal device, such as the optimal transmit beam and the optimal receive beam.

[0003] In order to reduce the overhead of beam scanning, artificial intelligence (AI) technology is now introduced. For example, the terminal device first performs a first round of beam scanning on some beams, and inputs the acquired data into the AI ​​model. The AI ​​model outputs the identification of one or more beams based on reasoning, and the terminal device then performs a second round of beam scanning on the one or more beams to finally determine the optimal beam.

[0004] In order to ensure the accuracy of the AI ​​model, a large amount of data can be input for model training. However, the accuracy of the AI ​​model obtained based on the above solution may still not meet the needs. Therefore, how to improve the accuracy of the AI ​​model is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method and a communication device for information transmission to support improving the accuracy of AI models.

[0006] In a first aspect, a method for information transmission is provided, comprising: sending indication information, the indication information being used to indicate a rule for sample reporting, the rule for sample reporting being used by a terminal device to determine samples that need to be reported, the samples that need to be reported comprising at least one of beam identification information and beam measurement report; receiving a first sample, the first sample belonging to the sample that needs to be reported.

[0007] The execution subject of the solution described in the first aspect may be the first device, or a module in the first device (such as a chip system, etc.), or a logical node, logical module or software that can realize all or part of the functions of the first device, without limitation. For ease of description, the following description takes the first device as an example.

[0008] In the above scheme, the first device sends indication information for indicating the sample reporting rules to the second device. The second device determines the samples that need to be reported according to the sample reporting rules, and selectively reports the samples that need to be reported, rather than reporting all the samples obtained by the second device to the first device. This can support the construction of a sample set with a more even sample distribution, which can be used for AI model training.

[0009] Compared with existing AI models that, during the training process, may regard some samples with a relatively small proportion as noise and thus ignore learning the features of such samples, and may then output less objective inference results, the above solution can support the AI model in learning the features of most or all samples during the training process (compared with the training of existing AI models, the above solution can support the AI model in learning the features of more samples), which can support improving the accuracy of the AI model and thus output relatively objective inference results.

[0010] In the first aspect, the method further includes: receiving a plurality of samples.

[0011] Optionally, the sample to be reported does not belong to the plurality of samples.

[0012] For example, after receiving the plurality of samples, if the first device determines that some samples are lacking in the plurality of samples, then these samples are the samples to be reported. In this way, it can support constructing a sample set with a richer sample composition.

[0013] Optionally, the sample to be reported belongs to the plurality of samples.

[0014] For example, after receiving the plurality of samples, if the first device determines that the proportion of some samples in the plurality of samples is relatively small, then these samples are the samples to be reported. In this way, it can support constructing a sample set with a more uniform sample distribution. Additionally, when the sample to be reported belongs to the plurality of samples, the second device can selectively report samples instead of reporting all the samples obtained, which can effectively reduce the resource overhead and power consumption of the second device.

[0015] When the first device receives a plurality of samples, it can detect the sample distribution of the plurality of samples and determine the samples to be reported in the plurality of samples, so as to construct a sample set with a more uniform sample distribution, thereby enabling the AI model to learn the features of most or all samples (compared with the training of existing AI models, the above solution can support the AI model in learning the features of more samples), and then output relatively objective inference results.

[0016] In the second aspect, there is provided a method for information transmission, including: receiving indication information, where the indication information is used to indicate a sample reporting rule, and the sample reporting rule is used for a terminal device to determine the sample to be reported, and the sample to be reported includes at least one of the identification information of a beam and the measurement report of the beam; according to the indication information, sending a first sample, where the first sample belongs to the sample to be reported.

[0017] The execution entity of the solution described in the second aspect may be a second device, or a module in the second device (such as a chip system, etc.), or a logical node, logical module, or software that can implement all or part of the functions of the second device, and this is not limited. For the convenience of description, the second device will be used as an example for description below.

[0018] In the above solution, the second device can determine the samples to be reported according to the sample reporting rules, and selectively report the samples to be reported, rather than reporting all the samples obtained by the second device to the first device. This can support constructing a sample set or multiple samples with a relatively uniform sample distribution, and the sample set or multiple samples can be used for AI model training.

[0019] Compared with the existing AI models that will regard some samples with a small proportion as noise and thus ignore learning the features of these samples during the training process, and then will output less objective inference results, the above solution can support the AI model to learn the features of each sample during the training process, which can support improving the accuracy of the AI model and thus can output relatively objective inference results.

[0020] By selectively reporting samples to the first device, this can effectively reduce the resource overhead and power consumption of the second device.

[0021] In the second aspect, the method further includes: sending at least one sample.

[0022] By reporting at least one sample to the first device, the first device can detect the distribution of the samples already collected and determine the samples to be reported.

[0023] Combined with the solution described in any one of the first aspect and the second aspect, the indication information includes the identification information corresponding to the first sample.

[0024] When the samples to be reported include the identification information of the beam, the indication information includes the identification information corresponding to the first sample. It can be understood that: the indication information includes the identification information of the beam; it can also be understood that: the indication information includes an index for indicating or determining the identification information of the beam, etc. In other words, the second device can determine to report the first sample according to the identification information corresponding to the first sample.

[0025] Among them, the association between the index of the identification information of the beam and the identification information of the beam can be indicated by the first device to the second device, or, the association between the index of the identification information of the beam and the identification information of the beam can be predefined. In this way, the second device can determine the corresponding identification information of the beam according to the association between the index of the identification information of the beam and the identification information of the beam and the index of the identification information of the beam.

[0026] When the sample to be reported includes the measurement report of the beam, the indication information includes the identification information corresponding to the first sample. It can be understood that: the indication information includes the identification information of the measurement report of the beam, such as one or more of the identification of the beam, the index of the measurement report of the beam, or the identification information of the resource corresponding to the measurement report, etc. In this way, the second device can determine that the first sample needs to be reported accordingly.

[0027] When the sample to be reported includes the identification information of the beam and the measurement report of the beam, the indication information includes the identification information corresponding to the first sample. It can be understood that: the indication information includes the identification of the beam or the identification of the measurement report of the beam, etc. The second device can determine that the first sample needs to be reported accordingly.

[0028] It can be understood that whether the sample to be reported specifically includes the identification information of the beam or the measurement report of the beam can be based on protocol pre - definition, or based on pre - configuration or indication.

[0029] Optionally, there may be a corresponding relationship between the identification of the beam, the index of the measurement report of the beam, or the identification information of the resource corresponding to the measurement report. Their corresponding relationship can be protocol - predefined or based on configuration.

[0030] Optionally, at least two of the identification of the beam, the index of the measurement report of the beam, or the identification information of the resource corresponding to the measurement report are the same identification.

[0031] The second device can determine that the first sample needs to be reported according to the identification information corresponding to the first sample. In this way, this can effectively reduce the resource overhead and power consumption of the second device.

[0032] Combined with the solution described in any one of the first aspect and the second aspect, the number of samples in the multiple samples is greater than the first threshold.

[0033] In this way, when the number of samples in the multiple samples does not reach the threshold, the first device does not need to detect the sample distribution of the multiple samples, which can effectively reduce the power consumption of the first device.

[0034] Combined with the solution described in any one of the first aspect and the second aspect, the first sample belongs to the multiple samples, and the first sample satisfies at least one of the following: the difference between the proportion of the second sample in the multiple samples and the proportion of the first sample in the multiple samples is greater than or equal to the second threshold, the proportion of the second sample in the multiple samples is higher than the proportion of the first sample in the multiple samples, the second sample belongs to the multiple samples; or the proportion of the first sample in the multiple samples is less than or equal to the third threshold.

[0035] In this way, the first device can determine the sample to be reported based on any one of the above.

[0036] Optionally, the first sample may not belong to the plurality of samples. In this way, it is possible to support the construction of a sample set with a richer sample composition.

[0037] Combining the solutions described in any one of the first aspect and the second aspect, the beam is a beam with a received signal quality greater than a fourth threshold.

[0038] By feeding back information related to the beam with a received signal quality greater than the threshold (such as the identifier of the beam and the measurement report of the beam), the AI model can output the identifiers of one or more beams with better received signal quality during inference, so as to more effectively reduce the beam scanning overhead.

[0039] Combining the solutions described in any one of the first aspect and the second aspect, the beam is a beam of a channel state information reference signal, the first sample includes the identifier information of the channel state information reference signal, and the first sample is associated with the synchronization signal block corresponding to the terminal device.

[0040] The beam is a beam of a channel state information reference signal, which can be understood as: the beam is used to carry the channel state information reference signal. Exemplarily, the channel state information reference signal can be sent through the beam.

[0041] A terminal device in a specific area (which can be within the coverage range of the beam (a wide beam) corresponding to the SSB) feeds back information about the beam corresponding to the specific area (such as one or more narrow beams, and the one or more narrow beams correspond to the wide beam corresponding to the SSB), and does not need to feed back information about the beam irrelevant to the specific area (one or more narrow beams not corresponding to the SSB). This is beneficial to the quality of the samples obtained by the second device, and thus beneficial to the training of the AI model.

[0042] Combining the solutions described in any one of the first aspect and the second aspect, the indication information is determined according to the sample distribution among the plurality of samples.

[0043] The above-mentioned sample distribution can be understood as: the proportion of different samples. For example, the proportion of sample 1, the proportion of sample 2, the proportion of sample 3, the proportion of sample 4, and the proportion of sample 5, etc.

[0044] The above-mentioned sample distribution can also be understood as: the difference between the proportions of different samples. For example, the difference between the proportion of sample 1 and the proportion of sample 2, the difference between the proportion of sample 1 and the proportion of sample 3, the difference between the proportion of sample 2 and the proportion of sample 5, etc.

[0045] The first device can determine the samples to be reported according to the sample distribution among the multiple samples. The first device can construct a sample set with a more uniform sample distribution based on the samples to be reported, and can perform AI model training based on this sample set.

[0046] Compared with the existing AI models that may regard samples with a relatively small proportion as noise and thus ignore learning the features of such samples, the embodiments of the present application can support the AI model to learn the features of most or all samples (compared with the existing AI model training, the above solution can support the AI model to learn the features of more samples). Thus, this can support improving the accuracy of the AI model.

[0047] Combined with the solution described in any one of the first aspect and the second aspect, the types of the samples to be reported are more than or equal to the types of the samples obtained by the terminal device.

[0048] When the types of the samples to be reported are more than the types of the samples obtained by the terminal device (which can be the second device), multiple terminal devices can jointly report the samples to be reported, which is beneficial to completing the collection of the samples to be reported faster.

[0049] When the types of the samples to be reported are the same as the types of the samples obtained by the terminal device (which can be the second device), the second device can report the samples to be reported, so that it is not necessary for multiple terminal devices to jointly report the samples to be reported, which is beneficial to overall reducing the power consumption of the terminal device.

[0050] Combined with the solution described in any one of the first aspect and the second aspect, the samples to be reported are used for the training of the artificial intelligence model, and the artificial intelligence model obtained after training is used for beam management.

[0051] In this way, the accuracy of the AI model for beam management can be effectively improved.

[0052] In a third aspect, a communication device is provided. The communication device can be the first device, or a device or module for performing the functions of the first device, etc.

[0053] In a possible implementation, the communication device can include modules or units corresponding one by one to the methods / operations / steps / actions described in the first aspect. The module or unit can be a hardware circuit, software, or a combination of hardware circuit and software.

[0054] The above-mentioned first device can be a terminal device or a network device, and this is not limited.

[0055] Fourthly, a communication device is provided. The communication device may be the second device, or a device or module for performing the functions of the second device, etc.

[0056] In a possible implementation, the communication device may include modules or units corresponding one by one to the methods / operations / steps / actions described in the second aspect. The modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0057] The above-mentioned second device may be a terminal device.

[0058] Fifthly, a communication device is provided, including a processor. The processor is configured to cause the communication device to execute the methods described in the first aspect and any possible implementation of the first aspect by executing computer programs or instructions, or by means of logic circuits; or to cause the communication device to execute the methods described in the second aspect and any possible implementation of the second aspect.

[0059] In a possible implementation, the communication device further includes a memory for storing the computer programs or instructions.

[0060] In a possible implementation, the communication device further includes a communication interface for inputting and / or outputting signals.

[0061] Sixthly, a communication device is provided, including a logic circuit and an input / output interface. The input / output interface is used for inputting and / or outputting signals, and the logic circuit is configured to execute the methods described in the first aspect and any possible implementation of the first aspect; or the logic circuit is configured to execute the methods described in the second aspect and any possible implementation of the second aspect.

[0062] Seventhly, a computer-readable storage medium is provided. A computer program or instructions are stored on the computer-readable storage medium. When the computer program or the instructions are run on a computer, the methods described in the first aspect and any possible implementation of the first aspect are caused to be executed; or the methods described in the second aspect and any possible implementation of the second aspect are caused to be executed.

[0063] Eighthly, a computer program product is provided, including instructions. When the instructions are run on a computer, the methods described in the first aspect and any possible implementation of the first aspect are caused to be executed; or the methods described in the second aspect and any possible implementation of the second aspect are caused to be executed.

[0064] In a ninth aspect, a chip system is provided, including: a processor configured to execute a computer program or instruction in the memory, such that the chip system implements the method in the first aspect and any possible implementation manner of the first aspect; or, such that the chip system implements the method in the second aspect and any possible implementation manner of the second aspect.

[0065] For the beneficial effects of any aspect from the third aspect to the ninth aspect, reference may be made to the description of the beneficial effects of the first aspect and the second aspect, which will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 FIG. 100 is a schematic diagram of an application framework applicable to an embodiment of the present application.

[0067] Figure 2 FIG. 200 is a schematic diagram of an application framework applicable to an embodiment of the present application.

[0068] Figure 3 FIG. 300 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0069] Figure 4 FIG. 400 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0070] Figure 5 FIG. 500 is a schematic diagram of beam management.

[0071] Figure 6 FIG. 600 is a schematic diagram of an interaction process of a communication method according to an embodiment of the present application.

[0072] Figure 7 FIG. 700 is a schematic diagram of a correspondence relationship between a terminal device and an SSB.

[0073] Figure 8 FIG. 800 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0074] Figure 9 FIG. 900 is a schematic block diagram of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0075] Hereinafter, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0076] To facilitate understanding of the embodiments of the present application, the following points are first explained.

[0077] 1. In the present application, unless otherwise specified, "a plurality of" means two or more.

[0078] Second, in each embodiment of the present application, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be mutually referenced. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0079] Third, the various digital numbers involved in the present application are only for the convenience of description and are not used to limit the protection scope of the present application. The magnitude of the serial numbers involved in the present application does not mean the order of execution. The execution order of each process should be determined by its function and internal logic. For example, the terms "first", "second", "third", "fourth" and other various term numbers in the specification, claims and drawings of the present application (if any) are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. Among them, such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here.

[0080] At the same time, any embodiment or design described in the present application as "exemplarily" or "for example" should not be construed as more preferred or more advantageous than other embodiments or designs. Exactly speaking, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific way for easy understanding.

[0081] Fourth, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0082] Fifth, in the present application, "for indicating" can be understood as "enabling", and "enabling" can include direct enabling and indirect enabling. When describing that a certain piece of information is used to enable A, it may include that the information directly enables A or indirectly enables A, and it does not mean that A must be carried in the information.

[0083] The information enabled by the information is called the information to be enabled. In the specific implementation process, there are many ways to enable the information to be enabled. For example, but not limited to, the information to be enabled can be directly enabled, such as the information to be enabled itself or the index of the information to be enabled. It is also possible to indirectly enable the information to be enabled by enabling other information, where there is an association relationship between the other information and the information to be enabled. It is also possible to only enable a part of the information to be enabled, while the other parts of the information to be enabled are known or pre-agreed. For example, it is also possible to achieve the enabling of specific information by means of the arrangement order of each piece of information pre-agreed (such as protocol regulations), thereby reducing the enabling overhead to a certain extent. At the same time, it is also possible to identify the common parts of each piece of information and enable them uniformly to reduce the enabling overhead caused by enabling the same information separately.

[0084] VI. In this application, "pre-configuration" may include pre-definition. For example, protocol definition. Among them, "pre-definition" can be achieved by pre-saving corresponding codes, tables or other ways that can be used to indicate relevant information in the device (for example, including each network element). This application does not limit its specific implementation method.

[0085] VII. The "storage" or "saving" involved in this application may refer to being saved in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, and this is not limited.

[0086] VIII. The "protocol" involved in this application may refer to the standard protocol in the communication field. For example, it may include the fourth generation (4G) network, the fifth generation (5G) network protocol, the new radio (NR) protocol, the 5.5G network protocol, the sixth generation (6 th generation, 6G) network protocol and related protocols applied to future communication systems. This application does not limit this.

[0087] IX. The arrows or boxes shown by the dotted lines in the schematic diagrams in the attached drawings of this application specification indicate optional steps or optional modules.

[0088] X. In this application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B. The "and / or" in this application is merely a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural.

[0089] XI. In this application, indication includes direct indication (also known as explicit indication) and implicit indication. Directly indicating information A means including this information A. Implicitly indicating information A means indicating information A through the correspondence between information A and information B and directly indicating information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0090] XII. In this application, information C is used for the determination of information D, which includes both the case where information D is determined only based on information C and the case where it is determined based on information C and other information. In addition, for the case where information C is used for the determination of information D, there can also be an indirect determination situation. For example, information D is determined based on information E, and information E is determined based on information C.

[0091] XIII. In this application, "device A sends information A to device B" can be understood as the destination of this information A or an intermediate network element in the transmission path between the destination and the source is device B, which can include directly or indirectly sending information to device B.

[0092] XIV. In this application, "device B receives information A from device A" can be understood as the source of this information A or an intermediate network element in the transmission path between the source and the destination is device A, which can include directly or indirectly receiving information from device A. Necessary processing may be performed on the information between the source and the destination of the information transmission, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0093] First, the communication system applicable to the embodiments of this application is described.

[0094] The technical solutions provided by this application can be applied to various communication systems, such as: 5G or NR systems, Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Wireless Local Area Network (WLAN) systems, satellite communication systems, future communication systems such as 6G mobile communication systems, or integrated systems of multiple systems, etc. The technical solutions provided by this application can also be applied to Device-to-Device (D2D) communication, Vehicle-to-Everything (V2X) communication, Machine-to-Machine (M2M) communication, Machine Type Communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0095] A device in a communication system can send a signal to another device or receive a signal from another device. The signal can include information, signaling, data, etc. The device can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. This application describes it by taking a device as an example. For example, a communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device.

[0096] In the embodiments of this application, the terminal device can also be referred to as a User Equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile device, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user device.

[0097] The terminal device can be a device that provides voice / data. For example, it can be a handheld device, a vehicle-mounted device, etc. with wireless connection capabilities. Currently, some examples of terminals are: mobile phone, tablet computer, laptop computer, palmtop computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing devices connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0098] By way of example and not limitation, the terminal device can also be a wearable device. A wearable device can also be referred to as a wearable intelligent device, which is a general term for devices developed by applying wearable technology to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, and shoes, etc. A wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not just a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smartphone, such as smart watches or smart glasses, etc., and those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0099] In the embodiments of the present application, the device for implementing the functions of the terminal device may be the terminal device itself, or a device capable of supporting the terminal device to implement such functions, such as a chip system. This device may be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system may be composed of chips, or may include chips and other discrete devices. In the embodiments of the present application, only the case where the device for implementing the functions of the terminal device is the terminal device is taken as an example for illustration, which does not limit the solutions of the embodiments of the present application.

[0100] The network device in the embodiments of the present application may be a device for communicating with the terminal device. This network device may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network.

[0101] The base station may generally cover various names as follows, or be replaced with the following names, such as: Node B, evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, slave station, multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, RAN intelligent controller (RIC), etc.

[0102] The base station can also be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station can also refer to a communication module, a modem, or a chip configured to be disposed within the foregoing device or apparatus. The base station can also be a mobile switching center and devices that perform the functions of a base station in D2D, V2X, M2M communications, network-side devices in a 6G network, devices that perform the functions of a base station in future communication systems, etc. The base station can support networks with the same or different access technologies.

[0103] Optionally, the RAN node can also be a server, a wearable device, a vehicle, or an in-vehicle device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the network device.

[0104] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the position of the mobile base station. In other examples, a helicopter or a drone can be configured to be used as a device for communicating with another base station.

[0105] In some deployments, the network device can be a device including a CU or a DU or including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device includes a gang-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0106] In some deployments, multiple RAN nodes cooperate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement some functions of the base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately provided, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as included in an RRU, an AAU, or an RRH.

[0107] The RAN node can support one or more types of fronthaul interfaces, and different fronthaul interfaces respectively correspond to DUs and RUs with different functions.

[0108] If the fronthaul interface between the DU and the RU is the Common Public Radio Interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions.

[0109] If the fronthaul interface between the DU and the RU is another interface, compared with the CPRI, some of the downlink and / or uplink baseband functions, for example, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition, are moved from the DU to the RU for implementation; for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation.

[0110] A possible implementation is that this interface can be the Enhanced Common Public Radio Interface (eCPRI). Under the eCPRI architecture, the splitting methods between the DU and the RU are different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0111] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the division, the DU is configured to implement layer mapping and one or more functions before it (i.e., one or more of encoding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (such as one or more of RE mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU for implementation. For uplink transmission, with de-RE mapping as the division, the DU is configured to implement demapping and one or more functions before it (i.e., one or more of decoding, derate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions after demapping (such as one or more of digital BF or fast Fourier transform (FFT) / removing CP) are moved to the RU for implementation. It can be understood that for the function descriptions of the DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol and will not be elaborated here.

[0112] In a possible design, the processing unit in the BBU for implementing baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is called the baseband low (BBL) unit.

[0113] In different communication systems, the CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (ORAN) system, the CU can also be called O-CU (open CU), the DU can also be called O-DU, the CU-CP can also be called O-CU-CP, the CU-UP can also be called O-CU-UP, and the RU can also be called O-RU. Any one of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0114] In the embodiments of the present application, the device for implementing the functions of a network device may be a network device; or it may be a device capable of supporting the network device to implement such functions, such as a chip system, a hardware circuit, a software module, or a combination of a hardware circuit and a software module. This device may be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the case where the device for implementing the functions of the network device is a network device is taken as an example for illustration, which does not limit the solutions of the embodiments of the present application.

[0115] The network device and / or the terminal device may be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; or may be deployed on water; or may also be deployed on airplanes, balloons, and satellites in the air. In the embodiments of the present application, the scenarios where the network device and the terminal device are located are not limited.

[0116] In addition, the terminal device and the network device may be hardware devices, or may be software functions running on dedicated hardware or software functions running on general hardware. For example, they may be virtualized functions instantiated on a platform (such as a cloud platform), or may be entities including dedicated or general hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the network device.

[0117] In a wireless communication network (such as a mobile communication network), the services supported by the network are becoming more and more diverse, and the requirements to be met are also becoming more and more diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latencies, and massive connections. This characteristic makes network planning, network configuration, and resource scheduling more and more complex. Due to the fact that the functions of the network are becoming more and more powerful, such as supporting higher and higher frequencies, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new requirements, new scenarios, and new characteristics have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet this challenge, AI technology can be introduced into the wireless communication network to achieve network intelligence.

[0118] To be able to support AI technology in a wireless network, the communication system may also introduce an AI node.

[0119] Optionally, the AI node may be deployed at one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc. Or, the AI node may also be deployed separately. For example, it may be deployed at a position outside any of the above devices, such as in the host of an over the top (OTT) system or a cloud server. The AI node can communicate with other devices in the communication system, and the other devices may be, for example, one or more of the following: a network device, a terminal device, or a network element of the core network.

[0120] It can be understood that the number of AI nodes in the embodiments of the present application is not limited. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes being responsible for different functions.

[0121] It can also be understood that an AI node can be an independent device, can also be integrated into the same device to implement different functions, can also be a network element in a hardware device, can also be a software function running on dedicated hardware, or a virtualized function instantiated on a platform (such as a cloud platform). The present application does not limit the specific form of the AI node. Among them, the AI node can be an AI network element or an AI module.

[0122] Figure 1 is a schematic diagram of an application framework 100 applicable to the embodiments of the present application. As Figure 1 shown, the devices are connected through interfaces (such as NG, Xn), or the air interface. One or more AI modules are provided in one or more of these device nodes, such as: core network devices, access network nodes (RAN nodes), terminals, or operation administration and maintenance (OAM) devices. For clarity, Figure 1 only 1 is shown in the figure. The access network node can be a separate RAN node, or can include multiple RAN nodes. For example, it includes a CU and a DU. One or more AI modules can also be provided in the CU and / or the DU. Optionally, the CU can also be split into a CU-CP and a CU-UP. One or more AI models are provided in the CU-CP and / or the CU-UP.

[0123] The AI module is used to implement the corresponding AI function. The AI modules deployed in different devices can be the same or different. According to different parameter configurations of the model of the AI module, the AI module can implement different functions. The model of the AI module can be configured based on one or more of the following parameters: structural parameters (such as at least one of the number of neural network layers, the width of the neural network, the connection relationship between layers, the weights of neurons, the activation function of neurons, or the bias in the activation function), input parameters (such as the type and / or dimension of the input parameters), or output parameters (such as the type and / or dimension of the output parameters). The bias in the activation function can also be referred to as the bias of the neural network.

[0124] An AI module can have one or more models. One model can infer an output, and the output includes one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0125] Figure 2 It is a schematic diagram of the application framework 200 applicable to the embodiments of the present application. As Figure 2 shown, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be Figure 1 the AI modules 117, 118 shown in, for implementing AI-related functions. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The non-real time RIC mainly processes non-real time information, such as data that is not sensitive to latency, and the latency of this data can be in seconds. The real time RIC mainly processes near-real time information, such as data that is relatively sensitive to latency, and the latency of this data is in tens of milliseconds.

[0126] The near-real time RIC is used for model training and inference. For example, for training an AI model and using this AI model for inference. The near-real time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data.

[0127] Optionally, the near-real time RIC can submit the inference result to the RAN node and / or the terminal.

[0128] Optionally, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near-real time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0129] The non-real time RIC is also used for model training and inference. For example, for training an AI model and using this model for inference. The non-real time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference result can be submitted to the RAN node and / or the terminal.

[0130] Optionally, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real time RIC submits the inference result to the DU, and the DU sends it to the RU.

[0131] The near-real-time RIC and the non-real-time RIC can also be separately set as a device. Optionally, the near-real-time RIC and the non-real-time RIC can also be part of other devices. For example, the near-real-time RIC is set in the RAN node (e.g., CU, DU), and the non-real-time RIC is set in the OAM, cloud server, core network device, or other network devices.

[0132] Figure 3 is a schematic diagram of a communication system 300 to which the embodiments of the present application are applicable. As Figure 3 shown, the communication system 300 may include at least one network device, for example, the network device 110; the communication system 100 may also include at least one terminal device, for example, the terminal device 120 and the terminal device 130. The network device 110 and the terminal devices (such as the terminal device 120 and the terminal device 130) can communicate through a wireless link. Among the communication devices in this communication system, for example, between the network device 110 and the terminal device 120, communication can be carried out through multi-antenna technology.

[0133] Figure 4 is a schematic diagram of a communication system 400 to which the embodiments of the present application are applicable. Compared with the communication system 300, the communication system 400 further includes an AI device 140. The AI device 140 is used to perform AI-related operations, such as constructing a training data set or training an AI model, etc.

[0134] In a possible implementation, the network device 110 sends data related to the training of the AI model to the AI device 140, and the AI device 140 constructs a training data set and trains the AI model. For example, the data related to the training of the AI model may include the data reported by the terminal device. The AI device 140 sends the results of the operations related to the AI model to the network device 110, and forwards them to the terminal device through the network device 110. For example, the results of the operations related to the AI model include at least one of the following: the trained AI model, the evaluation result or test result of the model, etc. Exemplarily, a part of the trained AI model is deployed on the network device 110, and another part is deployed on the terminal device. Alternatively, the trained AI model is deployed on the network device 110. Or, the trained AI model is deployed on the terminal device.

[0135] It should be understood that Figure 4 only taking the example that the AI device 140 is directly connected to the network device 110 for illustration. In other scenarios, the AI device 140 can also be connected to the terminal device; the AI device 140 can also be connected to both the network device 110 and the terminal device at the same time; the AI device 140 can also be connected to the network device 110 through a third-party device, etc. Therefore, the present application does not limit the connection relationship between the AI device and other devices.

[0136] The AI device 140 can also be set as a module in the network device and / or the terminal device. For example, it can be set in Figure 3 the network device 110 or the terminal device shown in the figure.

[0137] It should be noted that Figure 3 and Figure 4 are simplified schematic diagrams shown only for easy understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, etc., Figure 3 and Figure 4 which are not drawn in the figure. In practical applications, the communication system may include multiple network devices (such as network device 110 and network device 150 ( Figure 3 not shown)), and may also include multiple terminal devices. Therefore, the present application does not limit the number of network devices and terminal devices included in the communication system.

[0138] Next, a brief description of some technical concepts involved in the present application will be given.

[0139] Machine learning (ML): ML is an important technical approach to realizing AI. ML can be divided into supervised learning, unsupervised learning, and reinforcement learning.

[0140] Supervised learning is based on the collected sample values and sample labels, uses the ML algorithm to learn the mapping relationship from the sample values to the sample labels, and uses the ML model to represent the learned mapping relationship. The process of training the ML model is the process of learning this mapping relationship. For example, in signal detection, the received signal with noise is the sample, and the true constellation point corresponding to this signal is the label. ML expects to learn the mapping relationship between the sample and the label through training, that is, to make the ML model learn a signal detector. During training, the model parameters are optimized by calculating the error between the predicted value of the model and the true label. Once the mapping relationship is learned, the learned mapping can be used to predict the sample label of each new sample. The mapping relationship learned by supervised learning can include linear mapping and non-linear mapping. According to the type of label, the learning tasks can be divided into classification tasks and regression tasks.

[0141] In supervised learning, there is a type of task that uses ML algorithms to learn how to assign labels to examples. For example, classifying emails as "spam" or "non-spam". In ML, classification refers to a predictive modeling problem of predicting the class label for a given example in the input data. For example: Given an example, classify it as spam or non-spam. Given a handwritten character, classify it as a known character. Based on the recent user behavior, classify it as a churned user or a non-churned user. From a modeling perspective, classification requires a training dataset that contains many input and output examples for learning. The model will use the training dataset and calculate how to map the input data to the most appropriate specific class label. Therefore, the training dataset must be representative, and there should be many samples for each class. Class labels are usually strings, such as "spam", "non-spam". They must be mapped to numerical values before being used in the modeling algorithm. This process is usually called label encoding, which assigns a unique integer to each class label, for example, "spam" = 0, "non-spam" = 1. There are many different types of classification algorithms available for modeling classification predictive modeling problems.

[0142] The more common classification tasks are:

[0143] 1. Binary classification problem:

[0144] Binary classification tasks are usually modeled using a model that predicts the Bernoulli probability distribution of each sample. The Bernoulli distribution is a discrete probability distribution that contains the binary outcomes of an event, that is, either 1 or 0. For classification problems, such a model will predict the probability that a sample belongs to the class of "1", or the probability of the abnormal class. Common algorithms that can be used for binary classification include: 1) Logistic regression 2) k-nearest neighbor algorithm 3) Decision tree 4) Support vector machine 5) Naive Bayes.

[0145] 2. Multi-class classification problem:

[0146] Multi-class classification refers to a classification task with more than two class labels. For example: face recognition, plant species recognition, optical character recognition. Different from binary classification, there is no concept of normal and abnormal results in multi-class classification. Instead, samples are classified as belonging to one of a series of known classes. In some problems, the number of class labels may be very large. For example, a model can predict that a photo belongs to one of thousands of faces in a face recognition system. Problems involving predicting a sequence of words, such as a text translation model, can also be regarded as a special type of multi-class classification. Each word in the sequence of words to be predicted involves a multi-class classification, and the size of the vocabulary defines the number of classes that can be predicted, which may be thousands of words. Usually, a multinomial probability distribution model is used to model multi-class classification tasks. The multinomial distribution is a discrete probability distribution that contains events with definite classification results, such as K in {1, 2, 3, …, K}. For such a classification task, this means that the model can predict the probability that a sample belongs to each class label. Many binary classification algorithms can also be used for multi-class classification.

[0147] 3. Multi-label classification:

[0148] Multi-label classification refers to a classification task with two or more classification labels, where each sample can be predicted as one or more classes. Consider the example of photo classification, where a given photo may have multiple objects in the scene, and the model can predict the presence of multiple known objects in the photo, such as "bicycle", "apple", "person", etc. This is different from binary classification and multi-class classification, in which the prediction of each sample contains only a single classification label. Usually, a model that predicts multiple outputs is used to model multi-label classification tasks, and each output is predicted as a Bernoulli probability distribution. Essentially, this is a model that makes multiple binary classification predictions for each sample. Classification algorithms used for binary classification or multi-class classification cannot be directly used for multi-label classification. Special versions of standard classification algorithms, namely the so-called multi-label versions of the algorithms, can be used, including: 1) multi-label decision tree 2) multi-label random forest 3) multi-label gradient boosting.

[0149] 4. Impact of imbalanced samples on the classification task model:

[0150] In general classification learning methods, there is an assumption that the number of training samples in different classes is relatively balanced. Taking binary classification as an example, for instance, there are about 1000 positive and negative examples each. If the ratio is 1200:800, it is also acceptable. If it is 1900:100, some measures are needed to solve the imbalance problem. Otherwise, the final training result is very likely to ignore the negative examples and classify all samples as positive. If it is three-class classification, assuming the sample ratio of the three classes is 1000:800:600, this is acceptable; if it is 1000:300:100, it is unbalanced. The result is that the classifier is overfitted to the samples of the first class and underfitted to the samples of the other two classes, and the test effect must be very poor.

[0151] Unsupervised learning only relies on the collected sample values and uses algorithms to discover the inherent patterns of the samples by itself. In unsupervised learning, there is a type of algorithm that uses the samples themselves as the supervision signal, that is, the model learns the mapping relationship from samples to samples, which is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the predicted value of the model and the sample itself. Self-supervised learning can be used in applications such as signal compression and decompression recovery. Common algorithms include autoencoders and adversarial generative networks, etc.

[0152] Reinforcement learning is different from supervised learning. It is a type of algorithm that learns strategies to solve problems by interacting with the environment. Different from supervised and unsupervised learning, there is no clear "correct" action label data in reinforcement learning problems. The algorithm needs to interact with the environment to obtain the reward signal feedback from the environment, and then adjust the decision-making actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user according to the total system throughput rate feedback by the wireless network, and then expects to obtain a higher system throughput rate. The goal of reinforcement learning is also to learn the mapping relationship between the environmental state and the optimal decision-making action. However, because the "correct action" label cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action". The training of reinforcement learning is achieved through iterative interaction with the environment.

[0153] Deep neural network (DNN) is a specific implementation form of ML. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, so that the neural network has the ability to learn any mapping. Traditional communication systems need to rely on rich expert knowledge to design communication modules, while deep learning communication systems based on DNN can automatically discover the implicit pattern structures from a large amount of data sets, establish the mapping relationship between data, and obtain better performance than traditional modeling methods.

[0154] According to the construction method of the network, DNN can be divided into feedforward neural network (FNN), convolutional neural networks (CNN), and recurrent neural network (RNN).

[0155] CNN is a neural network specifically designed to process data with a similar grid structure. For example, time series data (discrete sampling on the time axis) and image data (two-dimensional discrete sampling) can both be considered data with a similar grid structure. Instead of using all the input information for calculation at once, CNN uses a fixed-size window to intercept part of the information for convolution operations, which greatly reduces the computational amount of model parameters. Additionally, according to the different types of information intercepted by the window (such as people and objects in the same picture being different types of information), each window can use different convolution kernels for operations, enabling CNN to better extract the features of the input data.

[0156] RNN is a type of DNN network that utilizes feedback time series information. Its input includes the new input value at the current moment and its own output value at the previous moment. RNN is suitable for obtaining sequence features that are relevant in time and is particularly applicable to applications such as speech recognition and channel coding and decoding.

[0157] The above-mentioned FNN, CNN, and RNN are common neural network structures, and these network structures are all constructed based on neurons. As introduced above, each neuron performs a weighted summation operation on its input value, and the weighted summation result passes through a non-linear function to generate an output. Then, we call the weights of the weighted summation operation of the neurons in the neural network and the non-linear function the parameters of the neural network. Taking the neuron with the non-linear function max{0, x} as an example, the parameters of the neuron performing the 0 , …, w n weighted summation bias is b, and the non-linear function is max{0, x}. The parameters of all neurons in a neural network constitute the parameters of this neural network.

[0158] AI model: An AI model is an algorithm or computer program that can implement AI functions, and the AI model represents the mapping relationship between the input and output of the model. The types of AI models can be neural networks, linear regression models, decision tree models, support vector machine (SVM), Bayesian networks, Q-learning models, or other ML models.

[0159] AI model application or inference: Using a trained AI model to solve practical problems.

[0160] It is understandable that the implementation of the AI model can be a hardware circuit, software, or a combination of software and hardware, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0161] Beam management: used for a network device and a terminal device to establish and maintain a suitable beam pair. For example, for downlink transmission, the network device needs to select a suitable transmit beam, and the terminal device needs to select a suitable receive beam. The transmit beam and the receive beam form a set of beam pairs to maintain a good wireless connection between the network device and the terminal device.

[0162] For further description of beam management, reference can be made to Figure 5 .

[0163] Figure 5 is a schematic diagram of beam management 500. As Figure 5 shown, the network device sends a synchronization signal block 1 (i.e., synchronization signal and PBCH block, SSB) (corresponding to beam 1) in the direction of beam 1, sends SSB2 (corresponding to beam 2) in the direction of beam 2, and sends SSB3 (corresponding to beam 3) in the direction of beam 3. The receiving end receives the three SSBs, namely SSB1, SSB2, and SSB3, measures the three SSBs, obtains the measurement results of the three SSBs, and reports the measurement results of the three SSBs to the network device. The network device determines that the measurement result of SSB2 is better than the measurement results of SSB1 and SSB3 based on the measurement results of the three SSBs reported by the terminal device.

[0164] The network device further divides beam 2 to obtain three sub - beams, namely: beam a1, beam a2, and beam a3, and respectively transmits channel state information - reference signal (CSI - RS) a1 (corresponding to beam a1), CSI - RS a2 (corresponding to beam a2), and CSI - RS a3 (corresponding to beam a3). The terminal device receives the three CSI - RSs, namely CSI - RS a1, CSI - RS a2, and CSI - RS a3, measures these three CSI - RSs to obtain the measurement results of these three CSI - RSs, and reports the measurement results of these three CSI - RSs to the network device. The network device determines that the measurement result of CSI - RS a2 is better than the measurement results of CSI - RS a1 and CSI - RS a3 according to the measurement results of the three CSI - RSs reported by the terminal device. The network device can determine that the sub - beam corresponding to CSI - RS a2 is the optimal transmission beam.

[0165] The terminal device can also determine a suitable receiving beam based on the above process.

[0166] Optionally, the terminal device can only report the measurement result of the optimal SSB to the network device, and the network device determines the beam corresponding to the SSB as the optimal wide beam according to the measurement result of the optimal SSB. Further, the terminal device can only report the measurement result of the optimal CSI - RS to the network device, and the network device determines the beam corresponding to the optimal CSI - RS as the optimal narrow beam.

[0167] It should be noted that the selection of beams is mainly completed through reference signals and corresponding beam measurements. The reference signals mainly include SSB and CSI-RS. SSB is a cell broadcast signal, which includes a primary synchronization signal (PSS), a secondary synchronization signal (SSS), a physical broadcast channel (PBCH), and a de-modulation reference signal (DMRS). SSB can be transmitted periodically according to cell configuration, and its functions can be used not only for beam management, but also for initial access, time-frequency synchronization, etc. Generally, the SSB signal can be considered as a wide beam signal. The CSI-RS signal is a user-level signal, and the network side configures one or more groups of CSI-RS resources for the user according to the actual situation. The CSI-RS signal can also be used not only for beam management, but also for channel quality measurement, etc. The CSI-RS signal can be simply understood as a narrow beam signal.

[0168] To solve the technical problems mentioned in the background art section, the present application provides a method for information transmission and a communication device, aiming to support improving the accuracy of the AI model.

[0169] The following describes the method for information transmission and the communication device according to the embodiments of the present application with reference to the accompanying drawings.

[0170] For the convenience of understanding and description, the following describes the method for information transmission according to the embodiments of the present application by taking the interaction between the first device and the second device as an example, but this should not impose any limitation on the execution entity of the method for information transmission according to the embodiments of the present application. For example, the method executed by the first device can also be executed by a module of the first device (such as a circuit, a chip, or a chip system, etc.), and can also be implemented by a logical node, a logical module, or software that can implement all or part of the functions of the first device. The method executed by the second device can be executed by a module of the second device (such as a circuit, a chip, or a chip system, etc.), and can also be implemented by a logical node, a logical module, or software that can implement all or part of the functions of the second device.

[0171] The above device can be a communication device or equipment, or a component or chip system in the equipment. For example, the first device is the first equipment, or the first component, or the first chip, etc.; for example, the second device is the second equipment, or the second component, or the second chip, etc.

[0172] In a possible implementation, the first device can be a terminal device or a network device, and the second device can be a terminal device. For example, the first device is a terminal device and the second device is a terminal device; for example, the first device is a network device and the second device is a terminal device.

[0173] When both the first device and the second device are terminal devices, the communication between the first device and the second device is sidelink communication; when the first device is a network device and the second device is a terminal device, the communication between the first device and the second device is air interface communication or Uu interface communication.

[0174] The second device can represent one or more devices (taking a terminal device as an example). For example, the second device represents one terminal device, or the second device represents multiple terminal devices. For the convenience of description, the following takes the second device representing one terminal device as an example for description, but does not limit the scenario where the second device can represent multiple terminal devices.

[0175] It should be noted that the following description takes the first device having the AI model training function as an example. The first device can also be a device without the AI model training function. When the first device is a device with the AI model training function, it can perform AI model training according to the obtained samples. When the first device is a device without the AI model training function, it can send the obtained samples to a device with the AI model training function, and the device with the model training function performs AI model training according to the samples.

[0176] Figure 6 It is a schematic diagram of the interaction process of the information transmission method 600 according to the embodiments of the present application. As Figure 6 shown, the method includes:

[0177] Optionally, in S601a, the second device sends at least one sample to the first device.

[0178] Correspondingly, the first device receives at least one sample from the second device.

[0179] Optionally, in S601b, the first device receives multiple samples. The above-mentioned multiple samples include the at least one sample, that is, the at least one sample sent by the second device belongs to the multiple samples.

[0180] By receiving multiple samples, the first device can detect the distribution of these multiple samples and determine the samples that need to be reported by one or more second devices (for the convenience of description, the following takes one second device as an example for description). As an example, the above-mentioned multiple samples can be referred to as a sample set.

[0181] For example, the first device receives (or obtains) a set of samples, which includes a plurality of samples (the plurality of samples can come from multiple devices or one device, and this is not limited). For example, the first device can obtain a plurality of samples from multiple terminal devices (such as the second device and the third device).

[0182] Exemplarily, the first device obtains Sample 1 and Sample 2 from Terminal Device 1 (e.g., the second device), and the first device obtains Sample 1 and Sample 3 from Terminal Device 2 (e.g., the third device).

[0183] For another example, the first device can obtain a plurality of samples from Terminal Device #M (“#M” is used to represent a certain terminal device).

[0184] Exemplarily, Terminal Device 1 sends Sample 1 and Sample 2 to Terminal Device #M, Terminal Device 2 sends Sample 1 and Sample 3 to Terminal Device #M, and Terminal Device #M (which can be the second device) sends two Sample 1s, one Sample 2, and one Sample 3 to the first device. The description of the plurality of samples can be seen in Table 1. The content shown in Table 1 is only for example and not for final limitation.

[0185] Table 1

[0186] Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 2 Sample 2 Sample 2 Sample 2 Sample 3 Sample 3 Sample 4 Sample 5

[0187] As shown in Table 1, the first device receives a total of 16 samples, which are: 8 Sample 1s, 4 Sample 2s, 3 Sample 3s, 1 Sample 4, and 1 Sample 5. The quantity ratio of Sample 1 - Sample 2 - Sample 3 - Sample 4 - Sample 5 in the plurality of samples is: 8:4:2:1:1.

[0188] In a possible implementation, the samples to be reported include the identification information of the beam or the measurement report of the beam. The measurement report of the beam includes at least one of the measurement result of the beam and the resource identifier (the measurement result of the beam can be characterized by one or more of the reference signal received power (RSRP), complex received signal, or phase information). The resource identifier and the identification information of the beam can have a configured or indicated or predefined corresponding relationship, or the resource identifier and the identification information of the beam are the same identifier, that is, the resource identifier is the identification information of the beam.

[0189] For example, the samples to be reported include the identification information of the beam;

[0190] For example, the samples to be reported include the measurement report of the beam (the beam is the same beam as the beam indicated by the identification information of the beam);

[0191] For example, the samples to be reported include the identification information of the beam and the measurement report of the beam.

[0192] Taking the samples to be reported including the identification information of the beam as an example, for instance, the first device receives the identification information of 8 beams 1, the first device receives the identification information of 4 beams 2, the first device receives the identification information of 2 beams 3, the first device receives the identification information of 1 beam 4, and the first device receives the identification information of 1 beam 5.

[0193] In a possible implementation, the identification information of the beam can be the identification of the beam or the relevant information used to identify the beam, such as an index, etc., which is not limited.

[0194] Taking the samples to be reported including the measurement report of the beam as an example, for instance, the first device receives the measurement reports of 8 beams 1, the first device receives the measurement reports of 4 beams 2, the first device receives the measurement reports of 2 beams 3, the first device receives the measurement report of 1 beam 4, and the first device receives the measurement report of 1 beam 5.

[0195] It should be noted that the measurement report of the beam includes the measurement result of the beam and the resource identification (the resource identification is similar to information such as the identification of the beam). The resource identification is used to indicate the resource corresponding to the measurement result of the beam. This resource is associated with the beam. The first device can determine the beam corresponding to the measurement result of the beam based on the association between the resource and the beam (this association relationship can be indicated by the first device to the second device, or can be predefined, and the second device can also obtain this association relationship and can accordingly determine the measurement report of the beam to be reported) and the measurement result of the beam. Among them, there may be numerical differences between multiple measurement results corresponding to the same beam (for example, measuring the same beam at different times or locations to obtain multiple different measurement results), but multiple measurement results corresponding to the same beam can be considered to correspond to the same beam. For example, the first device sends a reference signal 1 through resource 1, and the reference signal 1 corresponds to beam 1 (or the reference signal 1 is used to measure the channel quality of beam 1). The second device measures the reference signal 1, obtains the measurement result of the reference signal 1, and reports the measurement result of the reference signal 1 and the identification of resource 1 to the second device (which can form the measurement report of beam 1). The second device can accordingly determine that the measurement result of the reference signal 1 corresponds to the reference signal 1, and thus can determine the measurement result of beam 1.

[0196] Taking the example that the samples to be reported include the identification information of the beam and the measurement report of the beam. For example, the first device receives the identification information of 8 beams 1 and the measurement report of beam 1, the first device receives the identification information of 4 beams 2 and the measurement report of beam 2, the first device receives the identification information of 2 beams 3 and the measurement report of beam 3, the first device receives the identification information of 1 beam 4 and the measurement report of beam 4, and the first device receives the identification information of 1 beam 5 and the measurement report of beam 5.

[0197] Optionally, when the first device indicates the measurement report of the beam to be reported to the second device, the identification information of the resource may be carried in the indication information, and the identification information of the resource is used to indicate the resource for which beam scanning needs to be performed. The second device determines the corresponding resource according to the identification information of the resource, scans the beam transmitted on the resource, and obtains the measurement report of the beam corresponding to the resource.

[0198] Optionally, the identification information of the resource may also be replaced by the identification information of the measurement report, and the identification information of the measurement report may correspond to the identification information of one or more resources.

[0199] A possible implementation is that the number of samples in the multiple samples is greater than a threshold #1 (i.e., an example of the first threshold). In this way, when the number of samples in the multiple samples does not reach the threshold, the first device does not need to detect the sample distribution of the multiple samples, which can effectively reduce the power consumption of the first device.

[0200] S601. The first device sends an indication message.

[0201] Correspondingly, the second device receives the indication message. The indication message is used to indicate the sample reporting rule, and the sample reporting rule is used for the second device to determine the samples that the second device needs to report.

[0202] After the first device receives multiple samples, it can detect the sample distribution and determine the samples to be reported, so as to construct or form a sample set with a more uniform sample distribution, so that the AI model can learn the characteristics of most or all samples (compared with the existing AI model training, the above solution can support the AI model to learn the characteristics of more samples), and then a more objective inference result can be output.

[0203] A possible implementation is that the samples to be reported do not belong to the multiple samples. For example, after receiving the multiple samples, the first device determines that some samples are lacking in the multiple samples, and these samples are the samples to be reported.

[0204] Taking Table 1 as an example, the first device received multiple samples, namely Sample 1, Sample 2, Sample 3 - Sample 5, but did not receive Sample 6, and Sample 6 is the sample that needs to be reported. In this way, it is possible to support the construction of a sample set with a richer sample composition.

[0205] In a possible implementation, the sample that needs to be reported belongs to the multiple samples. For example, after receiving the multiple samples, the first device determines that the proportion of some samples in the multiple samples is relatively small, and these some samples are the samples that need to be reported. For specific descriptions, please refer to Table 1. In this way, it is possible to support the construction of a sample set with a more uniform sample distribution.

[0206] It should be noted that there may or may not be an intersection between the sample that needs to be reported and at least one sample already reported by the second device. The second device can selectively report samples from the newly obtained samples (the newly obtained samples can be different from the at least one already reported sample) according to the indication of the first device, rather than reporting all the newly obtained samples, which can effectively reduce the resource overhead and power consumption of the second device.

[0207] Exemplarily, the second device obtained the first-round samples and reported all the first-round samples to the first device. The first-round samples are the aforementioned at least one sample. When the second device obtains the second-round samples, the second device can selectively report samples according to the indication information sent by the first device, rather than reporting all the obtained samples. Among them, the second-round samples and the first-round samples may be irrelevant.

[0208] It also should be noted that the samples reported by the second device to the first device can be part or all of the samples that need to be reported. For example, if the second device determines that the samples that need to be reported according to the sample reporting rule are Sample 3, Sample 4, and Sample 5, the samples actually reported by the second device to the first device can be one or more of Sample 3, Sample 4, or Sample 5.

[0209] In S601, the first device can broadcast the indication information, multicast the indication information, or unicast the indication information.

[0210] When the first device broadcasts the indication information, the devices that receive the indication information can be multiple devices (including the second device), and each of the multiple devices determines the samples that need to be reported based on the sample reporting rule.

[0211] For the description of the first device broadcasting the indication information, please refer to Table 2. The content shown in Table 2 is only for example and not for final limitation.

[0212] Table 2

[0213] Terminal device Samples to be reported Terminal device 1 Sample 3, Sample 4, and Sample 5 Terminal device 2 Sample 3, Sample 4, and Sample 5 Terminal device 3 Sample 3, Sample 4, and Sample 5

[0214] As shown in Table 2:

[0215] For the terminal device 1, the indication information indicates that the samples it needs to report are Sample 3, Sample 4, and Sample 5;

[0216] For the terminal device 2, the indication information indicates that the samples it needs to report are Sample 3, Sample 4, and Sample 5;

[0217] For the terminal device 3, the indication information indicates that the sample it needs to report is Sample 3.

[0218] In this way, the first device can obtain the samples that need to be reported within a relatively short time.

[0219] In the embodiment of this application, when the first device sends the indication information in a broadcast manner, multiple devices that receive the indication information can determine the samples that need to be reported according to the indication information. Further, each device that receives the indication information can report some of the samples that need to be reported according to its corresponding SSB, rather than all the samples. For specific descriptions, please refer to the description of unicast sending of indication information below.

[0220] When the first device multicasts the indication information, multiple devices (including the second device) can receive the indication information. These multiple devices can be grouped into a device group, and each device in the device group determines the samples that need to be reported according to the sample reporting rules.

[0221] For the description of the first device multicasting the indication information, please refer to Table 3. The content shown in Table 3 is only for example and is not the final limitation.

[0222] Table 3

[0223] Terminal device Samples to be reported Terminal device 1 Sample 3, Sample 4, and Sample 5 Terminal device 2 Sample 3, Sample 4, and Sample 5 Terminal device 3 Sample 3

[0224] As shown in Table 3:

[0225] For the terminal device 1, the indication information indicates that the samples it needs to report are Sample 3, Sample 4, and Sample 5;

[0226] For the terminal device 2, the indication information indicates that the samples it needs to report are Sample 3, Sample 4, and Sample 5;

[0227] For the terminal device 3, the indication information indicates that the sample it needs to report is Sample 3.

[0228] Exemplarily, the terminal device 1 and the terminal device 2 belong to the same terminal device group. The first device may send indication information to this terminal device group, and this indication information is used to instruct the terminal device 1 and the terminal device 2 to report sample 3, sample 4, and sample 5. The terminal device 3 belongs to another terminal device group. The first device may send another indication information to this terminal device group, and this indication information is used to instruct the terminal device 3 to report sample 3. In this way, different terminal device groups may report the samples that need to be reported to the first device according to the indication information received by each of them. For example, the terminal device 1 or the terminal device 2 determines that the samples it needs to report are sample 3, sample 4, and sample 5 based on the indication information; the terminal device 3 determines that the sample it needs to report is sample 3 based on the indication information.

[0229] When different terminal devices or terminal device groups report different samples respectively, this may enable the terminal devices in a specific area (which may be within the coverage range of the beam (a wide beam) corresponding to this SSB) to feedback information on the beam (such as one or more narrow beams, and the one or more narrow beams correspond to the wide beam corresponding to this SSB) corresponding to the specific area, without the need to feedback information on the beams that have nothing to do with the specific area (one or more narrow beams that do not correspond to this SSB), which is beneficial to the quality of the samples obtained by the second device, and thus beneficial to the AI model training.

[0230] The above-mentioned terminal device group may be the terminal devices located within the coverage range of the same SSB. For example, the terminal devices within the terminal device group 1 are all located within the coverage range of SSB1. The terminal devices within the terminal device group 1 may determine the samples that need to be reported according to the indication information received. The terminal devices within the terminal device group 2 are all located within the coverage range of SSB2. The terminal devices within the terminal device group 2 may determine the samples that need to be reported according to the indication information received. Among them, the indication information received by the terminal devices within the terminal device group 1 may be different from the indication information received by the terminal devices within the terminal device group 2, or may be the same, and this is not limited.

[0231] When the first device unicasts and sends this indication information, the device that receives the indication information is one (it may also be multiple devices, and these multiple devices are all located within the coverage range of the same SSB) (taking the second device as an example), and this device determines the samples that need to be reported according to the sample reporting rules.

[0232] For the description of the first device unicasting and sending this indication information, refer to Table 4. The content shown in Table 4 is only for example and is not the final limit.

[0233] Table 4

[0234] Terminal device Samples to be reported Corresponding SSB Terminal device 1 Sample 3 SSB1 Terminal device 2 Sample 4 SSB2 Terminal device 3 Sample 5 SSB3

[0235] As shown in Table 4:

[0236] For the terminal device 1, the indication information indicates that the sample it needs to report is sample 3, and the SSB corresponding to the terminal device 1 is SSB1;

[0237] For the terminal device 2, the indication information indicates that the sample it needs to report is sample 4, and the SSB corresponding to the terminal device 2 is SSB2;

[0238] For the terminal device 3, the indication information indicates that the sample it needs to report is sample 5, and the SSB corresponding to the terminal device 3 is SSB3.

[0239] For the terminal device:

[0240] The first device sends indication information 1 to the terminal device 1, and the terminal device 1 determines that the sample to be reported is sample 3 according to the indication information 1;

[0241] The first device sends indication information 2 to the terminal device 2, and the terminal device 2 determines that the sample to be reported is sample 4 according to the indication information 2;

[0242] The first device sends indication information 3 to the terminal device 3, and the terminal device 3 determines that the sample to be reported is sample 5 according to the indication information 3.

[0243] In the embodiments of the present application, different terminal devices respectively correspond to different SSBs, which can be seen Figure 7 .

[0244] Figure 7 It is a schematic diagram of the correspondence relationship 700 between the terminal device and the SSB. As Figure 7 shown, different terminal devices respectively correspond to different SSBs. For example, the terminal device 1 is within the coverage range of the beam corresponding to SSB1, and the terminal device 1 corresponds to SSB1; the terminal device 2 is within the coverage range of the beam corresponding to SSB2, and the terminal device 2 corresponds to SSB2; the terminal device 3 is within the coverage range of the beam corresponding to SSB3, and the terminal device 3 corresponds to SSB3.

[0245] When performing beam scanning, the terminal device 1 can send the measurement result of the beam corresponding to SSB1 to the first device, and SSB1 corresponds to the channel state information-reference signal (CSI-RS) 3; the terminal device 2 sends the measurement result of the beam corresponding to SSB2 to the first device, and SSB2 corresponds to CSI-RS 4; the terminal device 3 sends the measurement result of the beam corresponding to SSB3 to the first device, and SSB3 corresponds to CSI-RS5.

[0246] When the terminal device performs beam scanning, it can first obtain the measurement results of the wide beam. For example, the terminal device 1 obtains the measurement results of the wide beam 1 (such as SSB1) and reports the measurement results of the wide beam 1; the terminal device 2 obtains the measurement results of the beam 2 (such as SSB2) and reports the measurement results of the wide beam 2 (such as SSB2); the terminal device 3 obtains the measurement results of the beam 3 (such as SSB3) and reports the measurement results of the wide beam 3. Correspondingly, the first device can record the correspondence between the terminal device and the SSB. For example, the first device determines that the terminal device 1 is associated with SSB1, determines that the terminal device 2 is associated with SSB2, and determines that the terminal device 3 is associated with SSB3.

[0247] In the embodiments of the present application, the beam corresponding to the SSB is a wide beam, and the beam corresponding to the CSI-RS is a narrow beam. One wide beam can include at least one narrow beam. For example, SSB1 corresponds to CSI-RS3 (it can also correspond to multiple CSI-RSs), SSB2 corresponds to CSI-RS4 (it can also correspond to multiple CSI-RSs), and SSB3 corresponds to CSI-RS5 (it can also correspond to multiple CSI-RSs).

[0248] In the embodiments of the present application, the foregoing beam can be a narrow beam, and the identification information of the beam included in the foregoing sample can be the identification information of the narrow beam. For example, it can be the identification information of the CSI-RS.

[0249] After the first device determines the correspondence between the SSB and the CSI-RS, according to the correspondence between the SSB and the CSI-RS, the first device can send corresponding indication information to the corresponding terminal device.

[0250] For example, if it is determined that the terminal device 1 corresponds to SSB1 and SSB1 corresponds to CSI-RS3, then indication information 1 is sent to the terminal device 1. The indication information 1 is used to indicate reporting the information of the beam corresponding to CSI-RS3 (such as identification information and measurement report);

[0251] For example, if it is determined that the terminal device 2 corresponds to SSB2 and SSB2 corresponds to CSI-RS4, then indication information 2 is sent to the terminal device 2. The indication information 2 is used to indicate reporting the information of the beam corresponding to CSI-RS4 (such as identification information and measurement report);

[0252] For example, if it is determined that the terminal device 3 corresponds to SSB3 and SSB3 corresponds to CSI-RS5, then indication information 3 is sent to the terminal device 3. The indication information 3 is used to indicate reporting the information of the beam corresponding to CSI-RS5 (such as identification information and measurement report).

[0253] The first device can determine that the samples to be reported are Sample 3, Sample 4, and Sample 5 according to the sample distribution of multiple samples shown in Table 1. Each sample corresponds to a narrow beam. For example, the sample corresponds to CSI-RS.

[0254] When the first device determines that it needs to report the measurement reports of the beams corresponding to CSI-RS 3, the beams corresponding to CSI-RS 4, and the beams corresponding to CSI-RS 5, the first device can determine, according to the correspondence between CSI-RS and SSB, that the terminal devices within the coverage of the beam corresponding to SSB1 need to report the measurement reports of the beams corresponding to CSI-RS 3, and then can send indication information 1 to terminal device 1; determine that the terminal devices within the coverage of the beam corresponding to SSB2 need to report the measurement reports of the beams corresponding to CSI-RS 4, and then can send indication information 2 to terminal device 2; determine that the terminal devices within the coverage of the beam corresponding to SSB3 need to report the measurement reports of the beams corresponding to CSI-RS 5, and then can send indication information 3 to terminal device 3.

[0255] In this way, the terminal devices in a specific area (which can be within the coverage of the beam corresponding to the SSB (a wide beam)) feedback information on the beam corresponding to the specific area (such as one or more narrow beams, and the one or more narrow beams correspond to the wide beam corresponding to the SSB), and do not need to feedback information on the beams that have nothing to do with the specific area (one or more narrow beams that do not correspond to the SSB). This is beneficial to improving the quality of the samples obtained by the second device, and thus beneficial to AI model training.

[0256] It should be noted that the content shown in Table 4 is described with the number of terminal devices within the coverage of one SSB being 1, and the content shown in Table 4 is also applicable to the scenario where the number of terminal devices within the coverage of one SSB is more than one.

[0257] It should also be noted that when the first device sends indication information to multiple terminal devices in a broadcast manner, the multiple terminal devices that receive the indication information can report some samples according to the correspondence between the SSB and the CSI-RS. For example, the first device broadcasts and sends indication information to terminal device 1, terminal device 2, and terminal device 3, and the indication information is used to indicate that the samples to be reported include sample 1, sample 2, and sample 3. Terminal device 1 determines to report sample 1 to the first device according to the correspondence between the SSB and the CSI-RS, terminal device 2 determines to report sample 2 to the first device according to the correspondence between the SSB and the CSI-RS, and terminal device 3 determines to report sample 3 to the first device according to the correspondence between the SSB and the CSI-RS. In this way, each terminal device can obtain samples with better quality and avoid interference from the channel quality on the beam measurement of the terminal device. Among them, the above correspondence between the SSB and the CSI-RS can be pre-configured in the terminal device or indicated by the first device to the multiple terminal devices, and this is not limited.

[0258] A possible implementation manner is that the rule for sample reporting is used for the terminal device to determine the samples to be reported and may include:

[0259] The terminal device indirectly determines the samples to be reported according to the rule for sample reporting; or,

[0260] The terminal device directly determines the samples to be reported according to the rule for sample reporting.

[0261] Taking the case where the terminal device indirectly determines the samples to be reported according to the rule for sample reporting as an example, for example, the indication information includes the identification information of sample 1, and the terminal device can determine according to the identification information of sample 1 that it does not need to report sample 1, but needs to report sample 2, sample 3, sample 4, and sample 5. Correspondingly, the terminal device reports one or more of sample 2, sample 3, sample 4, and sample 5 to the first device.

[0262] Taking the case where the terminal device directly determines the samples to be reported according to the rule for sample reporting as an example, for example, the indication information includes the identification information of sample 3, and the terminal device can determine according to the identification information of sample 3 that it needs to report sample 3. Correspondingly, the terminal device can report sample 3 to the first device.

[0263] For example, the indication information carries the identification information corresponding to the samples to be reported. Exemplarily, the indication information includes the identification information corresponding to the first sample. The second device determines to report the first sample according to the identification information corresponding to the first sample (the number of the first samples is not limited).

[0264] For another example, the indication information carries identification information corresponding to samples that do not need to be reported. Exemplarily, the indication information includes identification information corresponding to a second sample. The second device determines, based on the identification information corresponding to the second sample, that the second sample does not need to be reported and determines that samples other than the second sample need to be reported, such as a first sample, etc.

[0265] In an embodiment of the present application, in a possible implementation manner, the first sample belongs to the multiple samples, and the first sample satisfies at least one of the following:

[0266] The difference between the proportion of the second sample in the multiple samples and the proportion of the first sample in the multiple samples is greater than or equal to a threshold #2 (i.e., an example of the second threshold), the proportion of the second sample in the multiple samples is higher than the proportion of the first sample in the multiple samples, and the second sample belongs to the multiple samples; or,

[0267] The proportion of the first sample in the multiple samples is less than or equal to a threshold #3 (i.e., an example of the third threshold).

[0268] For the first item, exemplarily, the second sample is sample 1, the first sample is sample 4, the proportion of sample 1 is 8 / 16, the proportion of sample 4 is 1 / 16, the difference in proportion between sample 1 and sample 4 is greater than the threshold #2 (e.g., threshold #2 = 0.4) (which can be flexibly set and is not limited), and the first device determines that sample 4 needs to be reported.

[0269] For the second item, exemplarily, the first sample is sample 4, the proportion of sample 4 is 1 / 16, and it is less than the threshold #3 (e.g., threshold #3 = 0.2) (which can be flexibly set and is not limited), and the first device determines that sample 4 needs to be reported.

[0270] In this way, the first device can determine the samples that need to be reported based on any one of the above.

[0271] When the first sample does not belong to the multiple samples, the proportion of the first sample in the multiple samples is 0 and is less than the threshold #3.

[0272] After the first device receives the samples that need to be reported, it can form a sample set with a more uniform sample distribution based on the samples that need to be reported and the multiple samples that have been obtained, so as to enable the AI model to learn the features of most or all of the samples (compared with the existing AI model training, the above solution can enable the AI model to learn the features of more samples), and thus can output a more objective inference result.

[0273] Optionally, the first sample can also be determined according to the measurement report of the beam, as shown in Table 5. The content shown in Table 5 is only for example and is not the final limit.

[0274] Table 5

[0275] Terminal device 1 RSRP set 1 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6} Terminal device 2 RSRP set 2 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6} Terminal device 3 RSRP set 3 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6} Terminal device 4 RSRP set 4 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6} Terminal device 5 RSRP set 5 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6} Terminal device 6 RSRP set 6 {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6}

[0276] As shown in Table 5:

[0277] Terminal device 1 reports RSRP set 1, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6};

[0278] Terminal device 2 reports RSRP set 2, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6};

[0279] Terminal device 3 reports RSRP set 3, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6};

[0280] Terminal device 4 reports RSRP set 4, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6};

[0281] Terminal device 5 reports RSRP set 5, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6};

[0282] Terminal device 6 reports RSRP set 6, including: {RSRP1, RSRP2, RSRP3, RSRP4, RSRP5, RSRP6}.

[0283] Each terminal device can report to the first device some or all of the measurement reports of multiple beams it has obtained (the resource identifiers in the measurement reports are not shown in Table 5).

[0284] The first device can draw a change curve for the RSRP sets reported by the terminal devices. For example, the first device determines the sum value of the 6 RSRPs reported by terminal device 1, and determines the ratio between each RSRP and this sum value, and draws a curve graph based on these 6 ratios. There will be a highest point on this curve graph (this highest point can be any one of RSRP1 - RSRP6, without limitation).

[0285] As described above, the first device can draw six curves (each curve has a highest point), and can determine the samples to be reported based on these six curves. For example, the highest point in the first curve is RSRP1 (corresponding to RSRP set 1), the highest point in the second curve is RSRP2 (corresponding to RSRP set 2), the highest point in the third curve is RSRP3 (corresponding to RSRP set 3), the highest point in the fourth curve is RSRP4 (corresponding to RSRP set 4), the highest point in the fifth curve is RSRP5 (corresponding to RSRP set 5), and the highest point in the sixth curve is RSRP4 (corresponding to RSRP set 6). The first device can determine that the RSRP set with RSRP6 as the highest value is the sample to be reported. The first device can send indication information for indicating to report the RSRP set with RSRP6 as the highest value to some or all of the terminal devices 1 - terminal devices 6. That is, the measurement report of the resource corresponding to RSRP6 is the optimal beam. Optionally, the indication information sent by the first device to some or all of the terminal devices 1 - terminal devices 6 indicates one or more of the resource identifier or beam identifier information corresponding to RSRP6.

[0286] Optionally, the indication information can be used to indicate to report the RSRP set with RSRP6 as the highest value. After receiving the indication information, the terminal device sends the RSRP set with RSRP6 as the highest value to the first device.

[0287] Optionally, the indication information can indicate to report not only the RSRP set with RSRP6 as the highest value but also the RSRP set where RSRP6 may be the highest value. After receiving the indication information, the terminal device sends the RSRP set with RSRP6 as the highest value to the first device, and sends the RSRP set where RSRP6 may be the highest value. That is, this RSRP set does not include RSRP6, but the beam corresponding to the highest value in this RSRP set is adjacent to the beam corresponding to RSRP6 in the spatial domain. For example, the highest value in this RSRP set is RSRP5. Since this RSRP set does not include the value of RSRP6, and the beam corresponding to RSRP6 and the beam corresponding to RSRP5 are adjacent in the spatial domain, therefore, the value of RSRP6 may be higher than the value of RSRP5.

[0288] When the terminal device obtains the measurement results of a larger number of beams, it can send the measurement results of only some beams to the first device. When the first device draws curves based on the measurement results of these partial beams, it can determine the set of measurement results of the beams to be reported according to the above description of RSRP6. In summary, the embodiments of the present application do not limit the manner in which the first device determines the samples to be reported.

[0289] In a possible implementation, the above indication information is determined according to the sample distribution among the multiple samples.

[0290] In this way, the first device can determine the samples to be reported according to the sample distribution among the multiple samples. The first device can construct a sample set with a more uniform sample distribution based on the samples to be reported, and can perform AI model training based on this sample set.

[0291] Compared with the existing AI models that will regard samples with a relatively small proportion as noise and thus ignore learning the features of these samples, the embodiments of the present application can support the AI model to learn the features of most or all samples (compared with the existing AI model training, the above solution can support the AI model to learn the features of more samples). In this way, this can support improving the accuracy of the AI model.

[0292] The above sample distribution can be understood as: the proportions of different samples. For example, the proportion of sample 1, the proportion of sample 2, the proportion of sample 3, the proportion of sample 4, and the proportion of sample 5, etc.

[0293] The above sample distribution can also be understood as: the differences between the proportions of different samples. For example, the difference between the proportion of sample 1 and the proportion of sample 2, the difference between the proportion of sample 1 and the proportion of sample 3, the difference between the proportion of sample 2 and the proportion of sample 5, etc.

[0294] Taking Table 1 as an example, combined with the foregoing description of the impact of unbalanced samples on the classification task model, when the quantity proportions of sample 1 - sample 2 - sample 3 - sample 4 - sample 5 among the multiple samples are 8:4:2;1:1, this will cause the AI model obtained by training based on the samples shown in Table 1 to be unable to learn the features of sample 3, sample 4, and sample 5. In subsequent applications of the AI model, the AI model will tend to consider the beam corresponding to sample 1 as the best beam and will ignore the possibility that the beam corresponding to sample 4 is the best beam. This may cause the accuracy of the AI model to fail to meet the requirements. For example, the inference result of the AI model indicates that the beam corresponding to sample 1 is the best beam, but in fact, the beam corresponding to sample 4 is the optimal beam.

[0295] S602. The second device sends the first sample to the first device.

[0296] Correspondingly, the first device receives the first sample. The first sample belongs to the samples to be reported.

[0297] Wherein, the first sample may include one or more samples, and the one or more samples belong to the samples to be reported.

[0298] Optionally, the first sample may be part or all of the samples to be reported, and there is no limitation in this regard. The first device may train the AI model according to Table 1 and the samples to be reported, and the trained AI model can be used for beam management.

[0299] For the description of the first device training the AI model according to Table 1 and the samples to be reported, refer to Table 6. The content shown in Table 6 is only for illustrative purposes and is not an ultimate limitation.

[0300] Table 6

[0301] Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 1 Sample 2 Sample 2 Sample 2 Sample 2 Sample 3 Sample 3 Sample 4 Sample 5 Sample 2 Sample 2 Sample 2 Sample 2 Sample 3 Sample 3 Sample 3 Sample 4 Sample 4 Sample 4 Sample 5 Sample 5

[0302] As shown in Table 6, the content shown in the first four rows is the content shown in Table 1, and the content shown in the last three rows is the samples to be reported. When the first device obtains the samples to be reported (it can obtain the samples to be reported from one or more second devices, and there is no limitation in this regard), the ratios between Sample 1 - Sample 5 are: 8:8:5:4:3.

[0303] The first device may train the AI model according to the samples shown in Table 6. Since the proportion distribution of the above samples is relatively uniform, the first device can learn the features of each sample and will not tend to consider the beam corresponding to Sample 1 as the best beam. Therefore, it can more accurately infer the appropriate best beam and thus meet the requirements.

[0304] In summary, the first device sends indication information for indicating the sample reporting rule to the second device. The second device can determine the samples to be reported according to the sample reporting rule and selectively report the samples to be reported, rather than reporting all the samples obtained by the second device to the first device. This can support constructing a sample set with a more uniform sample distribution, and this sample set can be used for AI model training.

[0305] Compared with the existing AI model that will regard some samples with a small proportion as noise and thus ignore learning the features of these samples during the training process, and then will output less objective inference results, the above solution can support the AI model to learn the features of each sample or most or all of the samples during the training process (compared with the existing AI model training, the above solution can support the AI model to learn the features of more samples). This can support improving the accuracy of the AI model and thus output more objective inference results.

[0306] In the embodiments of the present application, the types of samples to be reported are more than or equivalent to the types of samples that the second device can obtain. For example, when the second device performs beam measurement, the samples that can be obtained (the samples satisfy the relevant information of the beam whose signal reception quality is greater than threshold #4 mentioned above) include Sample 1, Sample 2, and Sample 3. The samples to be reported include: Sample 1, Sample 2, Sample 3, Sample 4, and Sample 5. The types of samples to be reported are more than the types of samples that the second device can determine; or, the samples to be reported include Sample 1, Sample 2, and Sample 3. The types of samples to be reported are equivalent to the types of samples that the second device can determine.

[0307] Optionally, multiple devices can jointly report the samples to be reported, which is beneficial to completing the collection of the samples to be reported faster. In this case, the types of samples to be reported can be more than the types of samples that the second device can determine. That is, when the foregoing indication information is sent by broadcast or multicast, the types of samples to be reported indicated by the indication information can be more than the types of samples that each of the multiple devices receiving the indication information can obtain. At this time, each of the multiple devices can report some of the samples to be reported to the first device according to the types of samples that each can obtain.

[0308] Optionally, a single device can report the samples to be reported. This can avoid multiple devices from reporting, save signaling, and reduce the power consumption of terminal devices that do not report. In this case, the first device can send the indication information in a unicast manner.

[0309] In this case, the types of samples that the device receiving the indication information needs to report are all reported based on the indication information for the types of samples to be reported. Optionally, in the case of sending the indication information in a unicast manner, the first device can first determine that the second device to which the indication information is sent has the ability to obtain the types of samples to be reported indicated. For example, the first device determines that the second device has reported the samples to be reported, or has reported samples related to the samples to be reported. For example, if the sample to be reported is Beam 2, the samples related to the sample to be reported can be the adjacent beams of this Beam 2.

[0310] In the embodiments of the present application, the foregoing beam can be a beam whose received signal quality (such as RSRP, or other terms used to characterize channel quality, not limited) is greater than threshold #4 (that is, an example of the fourth threshold).

[0311] Optionally, the foregoing beam can also be the beam with the best received signal quality.

[0312] By feeding back the relevant information of the beam with the highest received signal quality (such as the identifier of the beam and the measurement report of the beam), when the AI model performs inference, it can output the identifiers of one or more beams with better received signal quality, so as to more effectively reduce the beam scanning overhead.

[0313] For example, the terminal device measures multiple beams, obtains the measurement results of each beam, determines the beams whose measurement results are greater than threshold #4, and reports the information of the beam (such as at least one of the identifier information of the beam or the measurement report of the beam) to the first device.

[0314] Exemplarily, the terminal device 1 measures beams 1 - 100, obtains the measurement results of the beams (such as represented by the RSRP value), screens the measurement results of these 100 beams, and determines the beams whose RSRP is greater than threshold #4. For example, if beams 1 - 10 have an RSRP greater than threshold #4, then it reports at least one of the identifier information of each beam in beams 1 - 10 or the measurement report of the beam.

[0315] Exemplarily, the terminal device 2 measures beams 1 - 100, obtains the measurement results of the beams (such as represented by the RSRP value), screens the measurement results of these 100 beams, and determines the beams whose RSRP is greater than threshold #4. For example, if beams 10 - 20 have an RSRP greater than threshold #4, then it reports at least one of the identifier information of each beam in beams 10 - 20 or the measurement report of the beam.

[0316] By feeding back the relevant information of the beam whose received signal quality is greater than the threshold (such as the identifier of the beam and the measurement report of the beam), when the AI model performs inference, it can output the identifiers of one or more beams with better received signal quality, so as to more effectively reduce the beam scanning overhead.

[0317] In the embodiments of the present application, multiple samples with relatively low proportions can also be classified into the same category. As shown in Table 1, samples 3 - 4 and sample 5 are all samples with relatively low proportions. The first device classifies samples 3, 4, and 5 into one category (represented by sample X), and the proportion of sample X is 4 / 16. The distributions of samples 1, 2, and sample X are relatively uniform. The first device trains the AI model based on samples 1, 2, and sample X. When the first device newly obtains multiple samples 3, the first device can also classify samples 4 and 5 into one category (represented by sample XX), and train the AI model based on samples 1, 2, 3, and sample XX. In this way, the existing samples can be fully utilized for AI model training, and waste of samples can be avoided.

[0318] In an embodiment of the present application, in a possible implementation manner, the first device may periodically send indication information to one or more second devices. In this way, the first device can periodically update the sample set for AI model training, which can enable the AI model to learn the features of most or all of the samples, and thus be able to output more objective inference results.

[0319] Finally, the device embodiments of the present application are introduced.

[0320] To implement each function in the method provided by the present application, both the first device and the second device may include a hardware structure and / or a software module, and implement the above functions in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module. Whether a certain function among the above functions is executed in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module depends on the specific application and design constraints of the technical solution.

[0321] Figure 8 It is a schematic block diagram of the communication device 800 according to an embodiment of the present application. The communication device 800 includes a processing circuit 810 and a transceiver circuit 820. The processing circuit 810 and the transceiver circuit 820 may be connected or coupled to each other, for example, connected to each other through a bus 830. The communication device 800 may be the first device or the second device.

[0322] Optionally, the communication device 800 may further include a memory 840. The memory 840 includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a compact disc read-only memory (CD-ROM). The memory 840 is used for relevant instructions and data.

[0323] The processing circuit 810 may be all or part of the processing circuits in one or more processors, or one or more processors. Among them, the processor may be a central processing unit (CPU). When the processing circuit 810 is a CPU, the CPU may be a single-core CPU or a multi-core CPU. Among them, the processing circuit 810 may be a signal processor, a chip, or other integrated circuits that can implement the method of this application, or a partial circuit for processing functions in the foregoing processor, chip, or integrated circuit. In addition, the transceiver circuit 820 may also be a transceiver, or an input / output interface. The input / output interface is used for input or output of signals or data, and may also be referred to as an input / output circuit.

[0324] When the communication device 800 is the first device, for example, the processing circuit 810 is used to perform the following operations: sending indication information; receiving first samples, etc.

[0325] When the communication device 800 is the second device, for example, the processing circuit 810 is used to perform the following operations: receiving indication information; sending first samples, etc.

[0326] The above content is only described as an example. When the communication device 800 is the first device or the second device, it will be responsible for executing the methods or steps related to the first device or the second device in the foregoing method embodiments.

[0327] When the communication device 800 is the first device or the second device, the transceiver circuit 820 may be a transceiver. When the communication device 800 is a chip for the first device or the second device, the transceiver circuit 820 may be an input / output circuit. The above description is only an exemplary description.

[0328] For specific content, reference may be made to the content shown in the foregoing method embodiments. Figure 8 The implementation of each operation in may also correspond to the corresponding description of the method embodiment shown in Figures 6 to 8 the method embodiment shown.

[0329] Figure 9 is a schematic block diagram of the communication device 900 in an embodiment of the present application. The communication device 900 may be the first device or the second device, and is used to implement the method involved in the foregoing embodiment.

[0330] Among them, the communication device 900 includes a transceiver unit 910. The transceiver unit 910 is introduced below by way of example.

[0331] The transceiver unit 910 may include a transmitting unit and a receiving unit. The transmitting unit is used to perform the transmitting actions of the communication device, and the receiving unit is used to perform the receiving actions of the communication device. For ease of description, in the embodiments of this application, the transmitting unit and the receiving unit are combined into one transceiver unit. This is explained uniformly here and will not be elaborated further hereinafter.

[0332] When the communication device 900 is the first device, exemplarily, the transceiver unit 910 is used to transmit indication information; and is also used to receive the first sample, etc.

[0333] Optionally, the communication device 900 may further include a processing unit 920, and the processing unit 920 is used to perform the content related to processing, control, etc. steps of the first device. For example, the processing unit 920 is used to determine the samples to be reported, etc.

[0334] When the communication device 900 is the second device, exemplarily, the transceiver unit 910 is used to receive indication information; and is also used to transmit the first sample, etc.

[0335] Optionally, the communication device 900 may further include a processing unit 920, and the processing unit 920 is used to determine the samples to be reported according to the sample reporting rules. Among them, the processing unit 920 is used to perform the content related to processing, control, etc. steps of the second device.

[0336] When the communication device 900 is the first device or the second device, it will be responsible for performing one or more of the methods or steps related to the first device or the second device in the foregoing method embodiments.

[0337] Optionally, the communication device 900 further includes a storage unit 930, and the storage unit 930 is used to store the programs or codes for executing the foregoing methods.

[0338] It should be noted that Figure 9 the transceiver unit in Figure 8 may correspond to the transceiver circuit in Figure 9 the processing unit in Figure 8 may correspond to the processing circuit in

[0339] Figure 8 and Figure 9 the device embodiments shown are used to implement Figure 6 the content described above. Figure 8 and Figure 9 For the specific execution steps and methods of the devices shown, reference may be made to the content described in the foregoing method embodiments.

[0340] The present application also provides a chip, including a processor, which is configured to call and run instructions stored in a memory, so that a communication device installed with the chip executes the methods in the above examples. The memory may be integrated within the chip or located outside the chip.

[0341] The present application also provides another chip, including: an input interface, an output interface, and a processing circuit. The input interface, the output interface, and the processor are connected through an internal connection path. The processing circuit is configured to execute code in a memory. When the code is executed, the processing circuit is configured to execute the methods in the above examples. Optionally, the chip further includes a memory, which is configured to store a computer program or code. Wherein, the input interface and the output interface may be independent of each other or may be integrated into an input / output interface.

[0342] The processing circuit may be all or part of the processing circuits in one or more processors, or one or more processors.

[0343] The present application also provides a processor, which is configured to be coupled with a memory and execute the methods and functions related to a network device or a terminal device in any one of the above embodiments.

[0344] In another embodiment of the present application, a computer program product including instructions is provided. When the computer program product runs on a computer, the methods in the foregoing embodiments are implemented.

[0345] The present application also provides a computer program. When the computer program runs on a computer, the methods in the foregoing embodiments are implemented.

[0346] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a computer, the methods described in the foregoing embodiments are implemented.

[0347] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0348] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include but not be limited to these and any other suitable types of memory.

[0349] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0350] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0351] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0352] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs that can store program codes.

[0353] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

Claims

1. A method for information transmission, characterized in that, it includes: sending indication information, where the indication information is used to indicate a sample reporting rule, and the sample reporting rule is used for a terminal device to determine samples to be reported, and the samples to be reported include at least one of beam identification information and beam measurement reports; receiving a first sample, where the first sample belongs to the samples to be reported.

2. The method according to claim 1, characterized in that, the indication information includes identification information corresponding to the first sample.

3. The method according to claim 2, characterized in that, before sending the indication information, the method further includes: receiving a plurality of samples.

4. The method according to claim 3, characterized in that, the indication information is determined according to the sample distribution among the plurality of samples.

5. The method according to claim 3 or 4, characterized in that, the number of samples among the plurality of samples is greater than a first threshold.

6. The method according to any one of claims 3 to 5, characterized in that, the first sample belongs to the plurality of samples, and the first sample satisfies at least one of the following: the difference between the proportion of a second sample among the plurality of samples and the proportion of the first sample among the plurality of samples is greater than or equal to a second threshold, the proportion of the second sample among the plurality of samples is higher than the proportion of the first sample among the plurality of samples, and the second sample belongs to the plurality of samples; or, the proportion of the first sample among the plurality of samples is less than or equal to a third threshold.

7. The method according to any one of claims 1 to 6, characterized in that, the beam is a beam with a received signal quality greater than a fourth threshold.

8. The method according to any one of claims 1 to 7, characterized in that, the beam is a beam of a channel state information reference signal, the first sample includes identification information of the channel state information reference signal, and the first sample is associated with a synchronization signal block corresponding to the terminal device.

9. The method according to any one of claims 1 to 8, characterized in that, the types of samples to be reported are more than or equivalent to the types of samples obtained by the terminal device.

10. The method according to any one of claims 1 to 9, characterized in that, the samples to be reported are used for training an artificial intelligence model, and the artificial intelligence model obtained after training is used for beam management.

11. A method for information transmission, characterized in that, it includes: receiving indication information, where the indication information is used to indicate a sample reporting rule, and the sample reporting rule is used for a terminal device to determine samples to be reported, and the samples to be reported include at least one of beam identification information and beam measurement reports; sending a first sample according to the indication information, where the first sample belongs to the samples to be reported.

12. The method according to claim 11, characterized in that, the indication information includes identification information corresponding to the first sample.

13. The method according to claim 12, characterized in that, before receiving the indication information, the method further includes: Send at least one sample.

14. The method according to any one of claims 11 to 13, wherein, the beam is a beam with received signal quality greater than a threshold.

15. The method according to any one of claims 12 to 14, wherein, the beam is a beam of a channel state information reference signal, the first sample includes identification information of the channel state information reference signal, and the first sample is associated with a synchronization signal block corresponding to the terminal device.

16. The method according to any one of claims 11 to 15, wherein, the types of samples to be reported are more than or the same as the types of samples obtained by the terminal device.

17. The method according to any one of claims 11 to 16, wherein, the samples to be reported are used for training an artificial intelligence model, and the artificial intelligence model obtained after training is used for beam management.

18. A communication device, wherein, comprising a processing circuit, the processing circuit is configured to, by executing a computer program or instruction, or by a hardware circuit, cause the communication device to execute the method according to any one of claims 1 to 10; or, cause the communication device to execute the method according to any one of claims 11 to 17.

Images