Information transmission method, first device, second device, and third device

Abstract

The present application relates to an information transmission method, a first device, a second device, a third device, a chip, a computer-readable storage medium, a computer program product, a computer program, and a communication system. The method comprises: a first device receiving first configuration information from a second device, wherein the first configuration information comprises configuration information of a first resource, configuration information of a second resource, and association configuration information, the configuration information of the first resource and the configuration information of the second resource are used by the first device to acquire a first data set, and the first data set is used for performing training to obtain a first model; the first model is used for obtaining, on the basis of channel information corresponding to the first resource, channel information corresponding to the second resource; the association configuration information comprises configuration information of a third resource and configuration information of a fourth resource; and the first model is further used for obtaining, on the basis of channel information corresponding to the third resource, channel information corresponding to the fourth resource. The embodiments of the present application can reduce the overhead of model training, downloading and switching.

Description

Information transmission method, first device, second device and third device Technical Field

[0001] This application relates to the field of communications, and more specifically, to an information transmission method, a first device, a second device, a third device, a chip, a computer-readable storage medium, a computer program product, a computer program, and a communication system. Background Technology

[0002] Currently, artificial intelligence (AI) and machine learning (ML) technologies can be used to recover channel information for a complete antenna port or bandwidth from channel information from a portion of the antenna port or bandwidth, thereby reducing the overhead of the reference signal. However, due to the diverse configurations of network devices and the varied channels between network devices and terminal devices, using a single model to generalize to support all configurations / channels will result in poor model performance under a specific configuration / channel. Furthermore, if different models are trained for different configuration / channel scenarios, the terminal device needs to collect training data for each model separately, and frequently monitor and switch model performance, significantly increasing overhead. Summary of the Invention

[0003] This application provides an information transmission method, a first device, a second device, a third device, a chip, a computer-readable storage medium, a computer program product, a computer program, and a communication system, which can reduce the overhead of model training, downloading, and switching.

[0004] This application provides an information transmission method, including:

[0005] The first device receives first configuration information from the second device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0006] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0007] The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0008] This application provides an information transmission method, including:

[0009] The second device sends first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0010] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0011] The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0012] This application provides an information transmission method, including:

[0013] The third device receives dataset information from the first device; wherein, the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information;

[0014] The third device trains a first model based on the first dataset. The first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are the associated configuration information in the first configuration information.

[0015] This application provides a first device, including:

[0016] A first communication module is configured to receive first configuration information from a second device; wherein the first configuration information includes configuration information of a first resource, configuration information of a second resource, and associated configuration information.

[0017] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0018] The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0019] This application provides a second device, including:

[0020] The second communication module is used to send first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0021] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0022] The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0023] This application provides a third device, including:

[0024] The third communication module is used to receive dataset information from the first device; wherein the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information;

[0025] The first processing module is used to train a first model based on a first dataset. The first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are the associated configuration information in the first configuration information.

[0026] This application provides a first device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to cause the first device to perform the aforementioned information transmission method.

[0027] This application provides a second device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to enable the second device to perform the information transmission method described above.

[0028] This application provides a third device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to enable the third device to perform the aforementioned information transmission method.

[0029] This application provides a chip for implementing the above-described information transmission method.

[0030] Specifically, the chip includes a processor for retrieving and running a computer program from memory, causing a device equipped with the chip to perform the aforementioned information transmission method.

[0031] This application provides a computer-readable storage medium for storing a computer program, which, when run by a device, causes the device to perform the aforementioned information transmission method.

[0032] This application provides a computer program product, including computer program instructions that cause a computer to execute the above-described information transmission method.

[0033] This application provides a computer program that, when run on a computer, causes the computer to perform the information transmission method described above.

[0034] This application provides a communication system, including a first device and a second device for performing the above-described information transmission method.

[0035] According to an embodiment of this application, when the second device configures the first and second resources for training the model on the first device, it also configures the associated third and fourth resources, so that the model obtained by collecting and training a dataset under a set of resource configurations can be extended to other resource configurations. This eliminates the need to train the model separately for multiple resource configurations and to switch the model for multiple resource configurations, thereby reducing the overhead of model training, downloading and switching. Attached Figure Description

[0036] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application.

[0037] Figure 2A is a schematic diagram of the periodic CSI reporting method.

[0038] Figure 2B is a schematic diagram of semi-persistent CSI transmission on PUCCH.

[0039] Figure 2C is a schematic diagram of semi-persistent CSI transmission on the PUSCH.

[0040] Figure 2D is a schematic diagram of the non-periodic CSI reporting method.

[0041] Figure 3 is a schematic flowchart of an information transmission method according to an embodiment of this application.

[0042] Figure 4 is a schematic diagram of the signaling process in an application example of the information transmission method according to an embodiment of this application.

[0043] Figure 5 is a schematic flowchart of an information transmission method according to another embodiment of this application.

[0044] Figure 6 is a schematic flowchart of an information transmission method according to another embodiment of this application.

[0045] Figure 7 is a schematic block diagram of a first device according to an embodiment of the present application.

[0046] Figure 8 is a schematic block diagram of a second device according to an embodiment of the present application.

[0047] Figure 9 is a schematic block diagram of a third device according to an embodiment of this application.

[0048] Figure 10 is a schematic block diagram of a communication device according to an embodiment of this application.

[0049] Figure 11 is a schematic block diagram of a chip according to an embodiment of this application.

[0050] Figure 12 is a schematic block diagram of a communication system according to an embodiment of this application. Detailed Implementation

[0051] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0052] The technical solutions of this application embodiment can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, Non-Terrestrial Networks (NTN) systems, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), 5th Generation (5G) systems, 6th Generation (6G) systems, or other communication systems.

[0053] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0054] In one implementation, the communication system in this application embodiment can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) network deployment scenario.

[0055] In one embodiment, the communication system in this application can be applied to unlicensed spectrum, wherein the unlicensed spectrum can also be considered as shared spectrum; or, the communication system in this application can also be applied to licensed spectrum, wherein the licensed spectrum can also be considered as non-shared spectrum.

[0056] This application describes various embodiments in conjunction with network devices and terminal devices. The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0057] Terminal devices can be stations (STAs) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistant (PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in next-generation communication systems such as NR networks, or terminal devices in future evolved Public Land Mobile Network (PLMN) networks, etc.

[0058] In the embodiments of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (such as airplanes, balloons and satellites).

[0059] In the embodiments of this application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0060] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0061] In the embodiments of this application, the network device can be a device for communicating with mobile devices, such as an access point (AP) in a WLAN, an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a vehicle-mounted device, a wearable device, a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or an NTN network, etc.

[0062] By way of example and not limitation, in this embodiment, the network device may have mobility characteristics; for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station located on land, water, or other similar locations.

[0063] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0064] Figure 1 illustrates an exemplary communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and the coverage area of ​​each network device 110 may include other numbers of terminal devices 120; this embodiment does not limit the scope of the present application.

[0065] In one embodiment, the communication system 100 may also include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which are not limited in this application.

[0066] Network equipment can be further divided into access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks used to communicate with the access network equipment. Access network equipment can be evolved Node Bs (eNBs or e-NodeBs) in Long-Term Evolution (LTE), Next-Generation Radio (NR) (mobile communication system), or Authorized Auxiliary Access Long-Term Evolution (LAA-LTE) systems, such as macro base stations, micro base stations (also called "small base stations"), pico base stations, access points (APs), transmission points (TPs), or new generation Node Bs (gNodeBs).

[0067] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the communication system shown in Figure 1 as an example, the communication device may include network devices and terminal devices with communication functions. The network devices and terminal devices can be specific devices in this application embodiment, which will not be described in detail here. The communication device may also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities. This application embodiment does not limit this.

[0068] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0069] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0070] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0071] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0072] (I) Wireless Communication and Artificial Intelligence

[0073] In recent years, AI and ML technologies, relying on the development of different types of neural networks and machine learning algorithms, have been widely applied in various fields such as image, speech, and video processing. Typical neural network architectures include fully connected networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformer structures with self-attention mechanisms, which can accomplish different task objectives.

[0074] The rapid development of AI / ML technologies and the integration of artificial intelligence with wireless communication technologies have attracted widespread interest from both academia and industry. Extensive research, evaluation, and standardization efforts have been undertaken in AI / ML-based Channel State Information (CSI) feedback and prediction, beam management, and positioning technologies. Furthermore, looking towards future wireless communication system development, the integration of AI / ML technologies may lead to more use cases, such as AI / ML-based channel estimation methods, AI / ML-based modulation and demodulation techniques, and AI / ML-based integrated receiver designs, all demonstrating performance gains compared to traditional non-AI / ML algorithms. Therefore, the design of future 6G wireless communication systems may incorporate more AI / ML modules to enhance overall system performance.

[0075] (II) Downlink CSI Feedback

[0076] To enable network devices to perform reasonable scheduling, terminals need to report downlink Channel State Information (CSI) so that the base station can determine the terminal's scheduling information, such as the transmission layer number, precoding matrix, transmit beam, and modulation / coding scheme. Specifically, the terminal's CSI reporting is based on the CSI reporting configuration indicated by the network device and the Channel State Information-Reference Signal (CSI-RS) signal sent by the network device. The uplink resources used by the terminal for CSI reporting and the CSI-RS signal used for CSI measurement are both indicated by the CSI reporting configuration. Each CSI reporting configuration corresponds to one CSI report, and each CSI report can contain different information such as CRI, RI, PMI, and CQI. This information is obtained based on the CSI-RS signal configured and sent by the network device. Specifically, the content / information included in the CSI is determined by the report quantity information in the CSI reporting configuration. The report quantity information can indicate one or more of the following report quantities:

[0077] CRI is used to determine the CSI-RS resource currently used for channel measurements and the IMR currently used for interference measurements from multiple CSI-RS resources.

[0078] RI is used to report the recommended transport layer number;

[0079] PMI is used to determine the recommended precoding matrix from a predefined codebook;

[0080] CQI is used to report the current channel quality.

[0081] RSRP is used to report the RSRP of the SSB or CSI-RS corresponding to the returned index, so that the network side can determine the beam used for downlink transmission.

[0082] LI is used to report the transport layer index associated with PTRS.

[0083] RI / PMI / CQI can be determined based on the SINR estimated by the terminal. The channel portion of SINR is determined based on the non-zero power CSI-RS configured for channel measurement in the network configuration, while the interference portion is determined based on the CSI-IM or non-zero power CSI-RS configured for interference measurement in the network configuration. The CSI-RS resources used for channel measurement can include multiple antenna ports to measure the complete downlink channel and thus calculate the CSI.

[0084] Terminals can report CSI in three ways: periodic CSI, semi-persistent CSI, and aperiodic CSI.

[0085] Figure 2A is a schematic diagram of the periodic CSI reporting method. The periodic CSI is transmitted on the Physical Uplink Control Channel (PUCCH). Its CSI reporting configuration is configured by Radio Resource Control (RRC) signaling. After receiving the corresponding RRC configuration, the terminal periodically reports the CSI.

[0086] Semi-persistent CSI can be transmitted on the PUCCH or the Physical Uplink Shared Channel (PUSCH). Figure 2B is a schematic diagram of semi-persistent CSI transmission on the PUCCH. The CSI reporting configuration corresponding to the CSI transmitted on the PUCCH is pre-configured by RRC signaling and activated or deactivated by Media Access Control (MAC) layer signaling, such as the MAC Control Element (MAC CE). Figure 2C is a schematic diagram of semi-persistent CSI transmission on the PUSCH. The CSI reporting configuration corresponding to the CSI transmitted on the PUSCH is dynamically indicated (activated or deactivated) by Downlink Control Information (DCI). After receiving the activation or indication signaling from the network configuration, the terminal periodically transmits CSI on the PUCCH or PUSCH until it receives the deactivation signaling and stops reporting.

[0087] Figure 2D is a schematic diagram of the non-periodic CSI reporting method. The CSI reporting configuration for non-periodic CSI reporting is pre-configured via RRC signaling. Part of this configuration can be activated via MAC layer signaling, and then the CSI trigger signaling in the DCI indicates the CSI reporting configuration used for CSI reporting. After receiving the CSI trigger signaling, the terminal reports the corresponding CSI on the scheduled PUSCH in one go according to the indicated CSI reporting configuration.

[0088] In related technologies, to obtain a complete uplink or downlink CSI, the transmitting end needs to send a reference signal corresponding to the complete antenna port (usually corresponding to the number of antennas at the transmitting end) and the complete bandwidth so that the receiving end can measure the complete channel information, thereby obtaining the uplink or downlink CSI and indicating it to the transmitting end. When the transmitting end has many antennas and a large number of antenna ports (e.g., 128 / 256 ports for downlink, 16 ports for uplink), the CSI measurement bandwidth is large. Frequently sending reference signals for the complete antenna port or complete bandwidth requires a large amount of reference signal resources, which will affect the uplink and downlink data transmission rates.

[0089] Currently, AI / ML technologies can be used to recover the CSI (Channel Information Sequence) of a complete antenna port or bandwidth from channel information of a partial antenna port or bandwidth, thereby reducing the overhead of the reference signal. However, due to the diverse antenna configurations of network devices and the varied channels between network devices and terminal devices, using a single AI model to generalize and support all configurations / channels will result in poor recovery performance under a specific configuration / channel. Furthermore, if different AI models are trained for different antenna configurations / channel scenarios, the terminal device needs to frequently monitor and switch model performance, significantly increasing the complexity of the terminal and the uplink and downlink signaling overhead.

[0090] Therefore, this application proposes an information transmission method that allows the model to adapt to resource configurations of different scales through a relatively simple scalability principle. This reduces the overhead of model switching training, downloading, and switching.

[0091] Figure 3 is a schematic flowchart of an information transmission method according to an embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes:

[0092] S310, the first device receives first configuration information from the second device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information.

[0093] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource; the associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0094] Optionally, the configuration information of the first resource is used to configure the first resource, which is the transmission resource of the first reference signal. The channel information corresponding to the first resource can be determined by measuring the first reference signal. The channel information can be used to characterize the channel state and can be understood as CSI. For example, the first reference signal may include CSI-RS, demodulation reference signal (DMRS), or phase-tracking reference signal (PTRS), etc.

[0095] Optionally, the configuration information of the second resource is used to configure the second resource, which is the transmission resource of the second reference signal. Channel information on the second resource can be determined by measuring the second reference signal. For example, the second reference signal may include CSI-RS, DMRS, or PTRS, etc.

[0096] Optionally, the first reference signal and the second reference signal can be the same type of reference signal transmitted on different transmission resources. For example, both the first reference signal and the second reference signal can be CSI-RS, or both can be DMRS. Here, the difference in transmission resources can refer to the difference in the number of resources and / or the difference in the pattern configuration of the resources.

[0097] In this embodiment, the configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset. An exemplary implementation is that the first device can determine the first resource based on the configuration information of the first resource, determine the second resource based on the configuration information of the second resource, determine the channel information corresponding to the first resource and the channel information corresponding to the second resource based on the reference signals received on the first resource and the second resource respectively, and construct the first dataset using the channel information corresponding to the first resource and the channel information corresponding to the second resource.

[0098] In this embodiment, a first dataset is used to train a first model, which can be used to obtain channel information corresponding to a second resource based on the channel information corresponding to the first resource. An exemplary implementation is that the first dataset includes channel information corresponding to the first resource and channel information corresponding to the second resource, enabling the model to learn the complex nonlinear relationship between the channel information corresponding to these two resources (the first resource and the second resource), thereby allowing the first model to obtain the channel information of the second resource based on the channel information corresponding to the first resource.

[0099] For example, the first resource and the second resource refer to resources corresponding to a specific time range and having a sequential relationship in the time domain. For instance, the first resource is the resource at time X, and the second resource is the resource at time Y, with the second resource occurring after the first resource in the time domain. That is, the first model can be used to infer channel information for later resources based on channel information from earlier resources. For example, it can be used to predict resources at future times Y based on resources at the current time X, where X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

[0100] For example, the first resource and the second resource refer to resources with a specific pattern configuration, or the first resource and the second resource contain a specific number of resources in each resource dimension. For example, the first resource is a relatively sparse resource, and the second resource is a relatively dense resource. That is, the first model can be used to infer channel information on the relatively sparse resources to obtain channel information on the relatively dense resources, thereby helping to reduce the resource overhead required for channel estimation.

[0101] Optionally, the configuration information of the first resource can be used to indicate the pattern configuration of the first resource, or the configuration information of the first resource can include the number of resources in each resource dimension. For example, the configuration information of the first resource can include the pattern index number of the first resource. As another example, if the first resource includes N1 first-dimensional resources, N2 second-dimensional resources, and N3 third-dimensional resources, the configuration information of the first resource can be indicated in the form (N1, N2, N3).

[0102] Optionally, the configuration information of the second resource can be used to indicate the pattern configuration of the second resource, or the configuration information of the second resource can include the number of resources in each resource dimension. For example, the configuration information of the second resource includes the pattern index number of the second resource. As another example, if the second resource includes M1 first-dimensional resources, M2 second-dimensional resources, and M3 third-dimensional resources, the configuration information of the second resource can be indicated in the form (M1, M2, M3).

[0103] Optionally, the first configuration information may include configuration information for multiple first resources. When the first configuration information includes configuration information for multiple first resources, a first dataset can be determined based on the configuration information of a single first resource and the configuration information of a second resource, and then a first model can be trained, that is, a different first model can be trained for the configuration information of each first resource. Alternatively, a general first model can be trained for the configuration information of multiple sets of first resources.

[0104] In this embodiment, the first configuration information includes not only the configuration information of the first resource and the configuration information of the second resource, but also associated configuration information, which includes the configuration information of the third resource and the configuration information of the fourth resource. The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. That is, the first model trained based on the first resource and the second resource can be extended to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0105] Optionally, the third and fourth resources refer to resources with specific pattern configurations, wherein the third and fourth resources may have different pattern configurations.

[0106] Optionally, the third and fourth resources contain a specific number of resources in each resource dimension, wherein the third and fourth resources may have different numbers of resources. For example, the fourth resource may contain more resources than the third resource, or the resource density of the fourth resource in each resource dimension may be greater than the resource density of the third resource in each resource dimension.

[0107] Optionally, the third and fourth resources refer to resources corresponding to a specific time range and have a sequential relationship in the time domain.

[0108] Optionally, the first configuration information may include one or more sets of associated configuration information, each set including configuration information for one or more third resources and configuration information for one or more fourth resources. Optionally, at least one of the third and fourth resources configured in different sets of associated configuration information may be different; for example, the third resources configured in different sets of associated configuration information may be different, or the fourth resources configured in different sets of associated configuration information may be different. When the first configuration information includes multiple sets of associated configuration information, the first model can be extended to various different resource scenarios.

[0109] Specifically, the indication format of the k-th group of associated configuration information can be one of the following, for example:

[0110] This includes configuration information for a set of third resources and configuration information for at least Q sets of fourth resources, indicated in the form of configuration information (N1_k, N2_k, N3_k, M1_k1, M2_k1, M3_k1, ..., M1_kQ, M2_kQ, M3_kQ), where N1_k, N2_k, and N3_k are the number of third resources in the three resource dimensions; M1_ki, M2_ki, and M3_ki (i = 1, 2, ..., Q) are the number of the i-th fourth resource in the three resource dimensions. Alternatively, it can be indicated in the form of pattern indices, such as (ID1_k, ID2_k1, ..., ID2_kQ), where ID1_k is the pattern index of the third resource, and ID2_ki is the pattern index of the i-th fourth resource.

[0111] This includes configuration information for a set of fourth resources and configuration information for at least one set (denoted as P sets) of third resources, indicated in the form of configuration information (N1_k1, N2_k1, N3_k1, ..., N1_kP, N2_kP, N3_kP, M1_k, M2_k, M3_k), where N1_ki, N2_ki, and N3_ki (i = 1, 2, ..., P) are the number of resources of the i-th third resource across the three resource dimensions, and M1_k, M2_k, and M3_k are the number of resources of the fourth resource across the three resource dimensions. Alternatively, it can be indicated in the form of pattern indexes, such as (ID1_k1, ..., ID1_kP, ID2_k), where ID1_ki is the pattern index of the i-th third resource, and ID2_k is the pattern index of the fourth resource.

[0112] Optionally, in the above-mentioned indication form of the associated configuration information, the number of resources on one or more resource dimensions can be defaulted. For example, only the first dimension is indicated, or only the second dimension is indicated, or only the first and second dimensions are indicated. In this case, it can be considered that on the dimension not indicated by the first configuration information: the number of resources of the third resource is the same as the number of resources of the first resource, the number of resources of the fourth resource is the same as the number of resources of the second resource, and the first model does not have scalability on this dimension.

[0113] According to the above method, when the second device configures the first and second resources for training the model on the first device, it also configures associated third and fourth resources. This allows a model trained on a dataset using one set of resource configurations to be extended to other resource configurations, eliminating the need to train models separately for different resource configurations or switch between different resource configurations, thus reducing the overhead of model training, downloading, and switching. Furthermore, since the second device actively configures the associated third and fourth resources, it does not need to expose the specific configurations supported by the second device, thereby avoiding the exposure of implementation details on the second device side and preventing privacy leaks.

[0114] It should be noted that the first device and the second device in the embodiments of this application are communication devices. Specifically, the first device can be a terminal device or a network device, and the second device can also be a terminal device or a network device. For example, the embodiments of this application can be applied to one of the following scenarios:

[0115] The first device is a terminal device, the second device is a network device, and the resources configured in the first configuration information are used for the transmission of downlink reference signals;

[0116] The first device is a network device, the second device is a terminal device, and the resources configured in the first configuration information are used for the transmission of uplink reference signals;

[0117] The first device is a first terminal device, the second device is a second terminal device, and the resources configured in the first configuration information are used for the transmission of side link reference signals.

[0118] The following examples illustrate the technical effects of the first model obtaining the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and the technical effects of the first model obtaining the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0119] Specifically, the first resource and the second resource each contain a specific number of resources in each resource dimension. Each resource dimension includes the first dimension, the second dimension, and the third dimension. The first resource includes N1 first-dimensional resources, N2 second-dimensional resources, and N3 third-dimensional resources; the second resource includes M1 first-dimensional resources, M2 second-dimensional resources, and M3 third-dimensional resources.

[0120] Wherein, the first dimension is the antenna port. Further, the first configuration information may further indicate the number of horizontal antenna ports N1_H in the first resource, the number of horizontal antenna ports M1_H in the second resource, the number of vertical antenna ports N1_V in the first resource, and the number of vertical antenna ports M1_V in the second resource; or, it may further indicate the number of first polarization ports N1_p1 in the first resource, the number of first polarization ports M1_p1 in the second resource, the number of second polarization ports N1_p2 in the first resource, and the number of second polarization ports M1_p2 in the second resource.

[0121] The second dimension is frequency domain resources, which can be RE granularity, RB granularity, or sub-band granularity. That is, a frequency domain resource can refer to an RE, an RB, or a sub-band without limitation.

[0122] The third dimension is time-domain resources, such as time-domain symbol resources.

[0123] Generally, the following constraints exist: 1≤N1≤M1, 1≤N2≤M2, 1≤N3≤M3, and N1, N2, N3, M1, M2, and M3 are all positive integers. To save on reference signal overhead, the x-th dimension of the first resource can be much smaller than the x-th dimension of the second resource, where x = 1, 2, or 3. For example, for the first dimension, a typical configuration is N2 = 32 and N1 = 8. That is, for downlink scenarios, the terminal device can measure CSI-RS on only 8 downlink antenna ports, predict the CSI of 32 downlink ports using the first model, and feed it back to the network device. Using this method, a significant amount of downlink reference signal resource overhead can be saved.

[0124] Generally, when the x-th dimension of the resource corresponding to the channel information to be processed changes, it is necessary to switch to a different model. In this embodiment, the first model can obtain channel information on M1 first-dimensional resources, M2 second-dimensional resources, and M3 third-dimensional resources based on channel information on N1 first-dimensional resources, N2 second-dimensional resources, and N3 third-dimensional resources. When configuring the first and second resources, the second device also provides associated configuration information, instructing the first device to extend the first model to be applied to the channel information on the third resources (including Q1 first-dimensional resources, Q2 second-dimensional resources, and Q3 third-dimensional resources) to obtain channel information on the fourth resources (including P1 first-dimensional resources, P2 second-dimensional resources, and P3 third-dimensional resources), thereby saving the overhead of model training, downloading, and switching.

[0125] In some embodiments, the first resource is associated with the third resource.

[0126] For example, the number of resources in the first resource and the third resource are related in at least one resource dimension, such as at least one of the number of antenna ports, frequency domain resources, and time domain resources in the first resource and the third resource being multiples of each other. For example, N1 = 8, Q1 = 16.

[0127] In some embodiments, the second resource is associated with the fourth resource.

[0128] For example, the second resource and the fourth resource are related in terms of the number of resources in at least one resource dimension, such as at least one of the number of antenna ports, the number of frequency domain resources, and the number of time domain resources in the second resource and the fourth resource being multiples of each other. For example, M1 = 32, Q1 = 64.

[0129] By configuring the relevant first and third resources, and / or the relevant second and fourth resources, the terminal device can be made to extend its use of the first model.

[0130] Taking the correlation between the number of antenna ports of the first and third resources and the correlation between the number of antenna ports of the second and fourth resources as an example, the first configuration information indicates that the first resource N1 = 8 and the second resource M1 = 32, and the first device trains the first model based on this configuration; the associated configuration information indicates that the third resource Q1 = 16 and the fourth resource P1 = 64, which is used to indicate that the first model can additionally perform inference under the configurations of Q1 = 16 and P1 = 64. One possible implementation is that the first device measures the first channel information on the 16 ports of the associated configuration of the third resource, and evenly divides it into two parts (8 ports in each part), and uses the first model to infer the second channel information on 32 ports respectively, and then combines them to obtain the second channel information on 64 ports corresponding to the fourth resource; another possible implementation is that the first device measures the first channel information on the 16 ports of the associated configuration of the third resource, and evenly divides it into two parts (odd and even), and uses the first model to infer the second channel information on 32 ports respectively, and then combines them to obtain the second channel information on 64 ports corresponding to the fourth resource. It should be noted that how the first device applies the first model to the associated configuration, performs inference, and extends it is an implementation issue on the first device side, and can be transparent to the second device.

[0131] In some embodiments, the first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for associated configuration information.

[0132] Optionally, upon receiving an activation instruction for the associated configuration information, the first device obtains the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource using the first model.

[0133] Optionally, the first device does not extend the configuration of the first model application if it does not receive an activation instruction for the associated configuration information.

[0134] In some embodiments, the activation indication is carried via MAC CE or DCI.

[0135] In some embodiments, the first configuration information is carried out via RRC signaling.

[0136] Optionally, the configuration information of the first resource and the configuration information of the second resource in the first configuration information can be indicated by RRC signaling, MAC CE or DCI; the associated configuration information can be configured by RRC signaling and activated and deactivated by MAC CE or DCI.

[0137] In some embodiments, the above information transmission method may further include: a first device receiving a second reference signal based on configuration information of a second resource; wherein the second reference signal is used to determine a first dataset.

[0138] Optionally, the first device receives a second reference signal based on the configuration information of the second resource, and determines the channel information corresponding to the second resource based on the measurement of the second reference signal. The first device determines a first dataset based on the channel information corresponding to the second resource.

[0139] In one implementation, the second resource includes the first resource. For example, the first resource includes a portion of the antenna port or a portion of the bandwidth, and the second resource includes the complete antenna port or the complete bandwidth. That is, the first model can be used to obtain the channel information on the complete antenna port or the complete bandwidth based on the channel information of the portion of the antenna port or the portion of the bandwidth. In this case, the second reference signal includes the first reference signal on the first resource. That is, the first device can determine the first reference signal on the first resource from the received second reference signal, thereby determining the channel information corresponding to the first resource. The first device determines the first dataset based on the channel information corresponding to the first resource and the channel information corresponding to the second resource.

[0140] In one implementation, the first device further receives a first reference signal based on the configuration information of the first resource, and determines the channel information corresponding to the first resource based on the measurement of the first reference signal. The first device then determines a first dataset based on the channel information corresponding to the first resource and the channel information corresponding to the second resource.

[0141] In some embodiments, the above information transmission method may further include: the first device training a first model based on a first dataset.

[0142] In some embodiments, the information transmission method may further include: a first device sending dataset information to a third device; wherein the dataset information includes a first dataset, which is used by the third device to train a first model. The third device may include communication devices such as other terminal devices or network devices, or other types of computing entities used for model training. For example, the third device may include a user-side training unit, i.e., a user-side terminal, server, computing unit, or entity used for model training. According to this embodiment, by forwarding the first dataset to the third device for model training, the terminal device can reduce the computing power requirements of the terminal device and improve model training efficiency.

[0143] In some embodiments, the dataset information further includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset. That is, when the first device forwards the first dataset to the third device, it also indicates the resource configuration associated with the dataset to the third device, so that the third device can perform model training to obtain the first model, and at the same time associate the first model with the first resource and the second resource.

[0144] In some embodiments, the above information transmission method may further include: a first device receiving second configuration information from a second device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain channel information corresponding to the sixth resource based on the channel information corresponding to the fifth resource.

[0145] Optionally, the second configuration information is used to instruct the first device to use the model for inference. In practical applications, the second configuration information includes the configuration information of the fifth resource and the configuration information of the sixth resource. By indicating the configuration information of a pair of resources, the first device is instructed to use the model corresponding to the pair of resources for inference, that is, the first device is instructed to use the model corresponding to the fifth resource and the sixth resource to infer the channel information corresponding to the fifth resource.

[0146] Optionally, the fifth and sixth resources refer to resources with specific drawing configurations, wherein the fifth and sixth resources may have different drawing configurations. Optionally, the configuration information of the fifth and sixth resources may include drawing configurations, such as drawing index numbers.

[0147] Optionally, the fifth and sixth resources each contain a specific number of resources across each resource dimension, wherein the fifth and sixth resources may have different numbers of resources. For example, the sixth resource may contain more resources than the fifth resource, or the resource density of the sixth resource across each resource dimension may be greater than the resource density of the fifth resource across each resource dimension. Optionally, the configuration information of the fifth resource may include the number of resources in each resource dimension; the configuration information of the sixth resource may include the number of resources in each resource dimension.

[0148] Optionally, the fifth and sixth resources refer to resources corresponding to a specific time range and have a sequential relationship in the time domain.

[0149] In some embodiments, the information transmission method described above may further include: the first device determining, based on the fifth resource and the sixth resource, a model associated with the configuration information of the fifth resource and the sixth resource from among a plurality of stored models. For example, if the first device trains the model itself, the first device may directly call the corresponding model based on the second configuration information.

[0150] In some embodiments, the information transmission method described above may further include: a first device sending third configuration information to a third device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource. For example, when the model is trained by the third device, the first device may send the third configuration information to the third device to obtain the model associated with the configuration information of the fifth resource and the configuration information of the sixth resource from the third device.

[0151] In some embodiments, where the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

[0152] For example, if the fifth resource configured in the second configuration information is the first resource used for model training, and the sixth resource configured in the second configuration information is the second resource used for model training, then the third configuration information includes the same content as the second configuration information, that is, it also includes the configuration information of the fifth resource (i.e. the first resource) and the configuration information of the sixth resource (i.e. the second resource). In this way, the third device can determine the first model associated with the first resource and the second resource from the multiple models stored in itself according to the configuration indication information obtained when acquiring the dataset, and return the model to the first device.

[0153] In some embodiments, where the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

[0154] For example, if the fifth resource configured in the second configuration information is the third resource of the model extension application, and the sixth resource configured in the second configuration information is the fourth resource of the model extension application, then the third configuration information includes the configuration information of the first resource related to the third and fourth resources, as well as the configuration information of the second resource. In this way, the third device can determine the first model associated with the first and second resources from among its stored models based on the configuration indication information obtained when acquiring the dataset, and return that model to the first device.

[0155] According to the above embodiments, the first device does not need to expose the resource configuration corresponding to the model it needs to the third device. It only needs to send the resource configuration information associated with the model to obtain the required model, thereby protecting the privacy of the first device from being leaked.

[0156] In some embodiments, the above information transmission method further includes: a first device receiving model information from a third device; wherein the model information is used by the first device to deploy a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource, and to obtain the channel information corresponding to the sixth resource based on the channel information corresponding to the fifth resource using the associated model.

[0157] In some embodiments, the configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

[0158] In other words, the first configuration information can indicate a first resource and a second resource corresponding to a specific time range, and the first resource and the second resource have a sequential relationship in the time domain. Based on this, a first model that can predict information for future times can be trained based on the first dataset corresponding to the first resource and the second resource.

[0159] Optionally, X time points may include X consecutive time points. Y time points may include Y consecutive time points.

[0160] Optionally, the aforementioned moments can be understood as time units / time domain units. For example, the aforementioned moments can be time slots.

[0161] For example, the first model can be used to predict the channel information corresponding to the second resource over Y consecutive time slots based on the channel information corresponding to the first resource over X consecutive time slots. The first model can also be used to predict the channel information corresponding to the fourth resource over Y consecutive time slots based on the channel information corresponding to the third resource over X consecutive time slots.

[0162] In some embodiments, the first configuration information is also used to indicate X and Y.

[0163] Optionally, if the first configuration information includes configuration information of multiple first resources and / or multiple sets of associated configuration information, the multiple first resources and / or multiple sets of associated configuration information correspond to the same X, that is, the configuration information of different first resources corresponds to the same number of measurement time slots. The number of measurement time slots of the third resource in the multiple sets of associated configuration information is X by default and no further configuration is required. In this way, the implementation complexity can be reduced.

[0164] In some embodiments, the first dataset includes first channel information and second channel information, wherein the first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

[0165] In some embodiments, the information transmission method further includes: when the first configuration information indicates configuration information for a plurality of first resources, the first device receives a first reference signal on the union of the plurality of first resources at X time points or on a second resource at X time points.

[0166] It is understood that when the first configuration information indicates the configuration information of multiple first resources, it is necessary to obtain the first reference signal on each first resource to obtain the first channel information corresponding to each first resource. In the embodiments of this application, the first channel information corresponding to each resource can be obtained in the following way:

[0167] 1. A first reference signal is transmitted on the union of multiple first resources at X time points. Since the union contains the first reference signal on each first resource, the first device can extract the measurement result of the corresponding first reference signal for each first resource based on the first reference signal on the union, thereby obtaining the first channel information corresponding to each first resource.

[0168] 2. Transmitting a first reference signal on the second resource. This method is applicable when the second resource includes the first resource. For example, the second resource is a resource containing a complete antenna port or a complete bandwidth, and the first resource is a resource containing a partial antenna port or a partial bandwidth. By transmitting the first reference signal on the second resource, the first device can extract the measurement results of the corresponding first reference signal for each first resource, thereby obtaining the first channel information corresponding to each first resource.

[0169] According to the above method, it is not necessary to transmit the first reference signal separately for each first resource to obtain the first channel information corresponding to each first resource, thereby saving resource overhead.

[0170] In some embodiments, the first configuration information further includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

[0171] According to the above embodiments, the first association information in the first configuration information can indicate the association relationship between reference signals and / or the association relationship between resources, thereby making the first channel information and the second channel information have temporal domain correlation. When the first device receives the first association information, it can use the measured first channel information containing X time points as model input, use the second channel information containing Y time points as model output, and associate them into a set of training samples for training the first model.

[0172] Optionally, the first association information can be used by the first configuration information to indicate a second resource when configuring the first resource; that is, the configuration information of the first resource in the first configuration information indicates the association relationship with the second resource. Alternatively, the first association information can be used by the first configuration information to indicate a first resource when configuring the second resource; that is, the configuration information of the second resource in the first configuration information indicates the association relationship with the first resource. Alternatively, the first association information can be indicated separately, for example, by using an additional set of time information to indicate the start time of the first and second reference signals, or by using an additional set of resource information to indicate the resource IDs of the first and second resources.

[0173] To facilitate understanding of the above embodiments, two specific application examples are provided below. In the following application examples, the first device is a terminal device (hereinafter referred to as the user), and the second device is a network device, which will be used as examples for illustration. At this time, each resource is the channel resource of the downlink reference signal. It can be understood that the technical solution of the embodiments of this application is not limited to this, and can also be extended to uplink scenarios, sidelink scenarios, or other scenarios.

[0174] Application Example 1

[0175] Figure 4 is a schematic diagram of the signaling process in Application Example 1. In this application example, the information transmission methods include:

[0176] Step 1: The network device sends first configuration information to the user and a second reference signal. The second reference signal is sent on the second resource corresponding to the second channel information. The second reference signal can be periodic, aperiodic, or semi-persistent.

[0177] The first configuration information includes the dimension configuration corresponding to the second resource, such as the number of resources M1, M2 and M3 in different dimensions, or the pattern configuration, such as a pattern index number ID2, which is used to instruct the user to receive the second reference signal on the second resource indicated by the above-mentioned dimension or pattern, and to perform channel estimation and data collection.

[0178] Simultaneously, the first configuration information includes the dimension configuration or pattern configuration corresponding to the first resources in groups T ≥ 0. For example, when the first configuration information indicates dimension configuration, the dimension configuration of the t-th group in the T groups of first resources is (N1_t, N2_t, N3_t). This configuration information is associated with a pattern of a first resource, used to instruct the user to use the channel information measured on the first resource as input for training the first model. When the first configuration information indicates pattern configuration, the pattern configuration of the t-th group includes a pattern index number, such as ID1_t, used to instruct the user to select the pattern with index number ID1_t and use the channel information measured on the first resource indicated on the pattern as input for training the first model.

[0179] When T=0, the first configuration information does not additionally indicate the configuration corresponding to the first channel information. At this time, the user assumes that the first resource and the second resource are the same and does not train the first model under this configuration. When T≥1, the configuration information of a set of second resources and the second reference signal are associated with at least one set of configuration information of first resources. At this time, the user can train different first models for each set of configuration information of the associated first resources, or train a general first model for multiple sets of configuration information of first resources.

[0180] Additionally, the first configuration information may contain K sets of associated configuration information, where K ≥ 0. When there is at least one set of associated configuration information, the first configuration information indicates that the first model trained by the user under the first resource and second resource configurations can be extended and inferred under the configuration indicated by the associated configuration information. Taking the first dimension as an example, in the first configuration information, the first resource N1 = 8 and the second resource M1 = 32. The user trains the first model based on this configuration. In the associated configuration information, the third resource Q1 = 16 and the fourth resource P1 = 64, indicating that the first model can additionally perform inference under configurations of Q1 = 16 and P1 = 64. One possible implementation is that the user measures the first channel information on the 16 ports of the associated configuration's first resource, evenly divides it into two parts, uses the first model to infer the second channel information on 32 ports respectively, and then combines them to obtain the second channel information on 64 ports. Alternatively, another possible implementation is that the user measures the first channel information on the 16 ports of the associated configuration's first resource, evenly divides it into odd and even parts, uses the first model to infer the second channel information on 32 ports respectively, and then combines them to obtain the second channel information on 64 ports. It should be noted that how the user applies the first model to the associated configuration for inference and extension is a user-side implementation issue and is transparent to the network device.

[0181] Specifically, the indication format of the k-th group of associated configuration information can be one of the following, for example:

[0182] The configuration includes a set of first resources and at least one set (denoted as Q group) of second resources, indicated in the form of configuration information (N1_k, N2_k, N3_k, M1_k1, M2_k1, M3_k1, ..., M1_kQ, M2_kQ, M3_kQ), or indicated in the form of pattern index, such as (ID1_k, ID2_k1, ..., ID2_kQ).

[0183] The configuration of a set of second resources and at least one set (denoted as P groups) of first resources is indicated in the form of configuration information (N1_k1, N2_k1, N3_k1, ..., N1_kP, N2_kP, N3_kP, M1_k, M2_k, M3_k) or in the form of pattern indexes, such as (ID1_k1, ..., ID1_kP, ID2_k).

[0184] The x-th dimension of the third and / or fourth resources in the associated configuration information can be defaulted. For example, only the first dimension, or only the second dimension, or only the first and second dimensions can be indicated. In this case, the dimension that the user does not indicate by default is the same as the x-th dimension of the first and / or second resources and does not have additional extensibility.

[0185] The configuration information for the first and second resources in the first configuration information can be indicated via RRC, MAC CE, or DCI; the associated configuration information in the first configuration information can be configured via RRC and activated / deactivated via MAC CE or DCI. If the user receives the activation instruction for the associated configuration information, the user can extend the application configuration of the first model according to the associated configuration information instruction; otherwise, the user cannot.

[0186] Step 2: The user collects the first dataset based on the second reference signal and forwards the first dataset, along with the configuration indication information corresponding to the first and second resources in the first configuration information, to the user-side training unit. The user-side training unit is the user-side terminal used for AI / ML model training, or a server from a chip manufacturer, or a computing unit and entity.

[0187] Step 3: The user-side training unit trains the model to obtain the first model, and at the same time associates the configuration indication information corresponding to the first and second resources with the first model.

[0188] Step 4: The network device sends second configuration information and a third reference signal to the user. The second configuration information indicates the configuration information of a set of fifth and sixth resources, for example, it can be indicated in the form of (N1, N2, N3, M1, M2, M3), or it can indicate the pattern indices (ID1, ID2) corresponding to a set of fifth and sixth resources. The third reference signal is transmitted on the fifth resource, received by the user on the fifth resource, and used for channel estimation to obtain the channel information corresponding to the fifth resource. The second configuration information is indicated via RRC, MAC CE, or DCI. The third reference signal can be periodic, aperiodic, or semi-persistent. The third reference signal can be a reference signal of the same type as the first reference signal on the first resource.

[0189] Step 5: The user initiates a model download request to the user-side training unit and simultaneously sends the third configuration information. When the configuration information or pattern index of the fifth and sixth resources in the second configuration information is included by the configuration information or pattern index of the first and second resources in the first configuration information, the third configuration information can be the same as the second configuration information; when the configuration information or pattern index of the fifth and sixth resources in the second configuration information is included by the associated configuration information in the first configuration information, the third configuration information selects the first and second resource configurations associated with that associated configuration information and forwards them to the user-side training unit.

[0190] Step 6: The user-side training unit selects the first model that matches the third configuration information and downloads it to the user side.

[0191] Step 7: Deploy the model on the user side and perform inference.

[0192] Based on this application example, a model trained on a dataset under one resource configuration can be extended to other resource configurations and used for inference, reducing the overhead of model training, downloading, and switching. At the same time, the design of associated configuration information does not expose the implementation details on the network side, thus avoiding privacy leaks on the network side.

[0193] Application Example 2

[0194] Building upon Application Example 1, this application example further applies the information transmission method to a channel prediction scenario. In channel prediction, the first channel information contains measurement results of resources over X consecutive time slots, and the second channel information contains prediction results of resources over Y consecutive future time slots. Based on the signaling flow shown in Figure 4, the following supplementary explanations are provided:

[0195] In step 1, when configuring the first and second resources in the first configuration information, X and Y need to be specified. For configuration information corresponding to T ≥ 0 first resources, the same X is used, that is, different configuration information of the first resources or pattern index numbers correspond to the same measurement time slot X. At this time, the number of measurement time slots of the third resource in the K groups of associated configurations in the associated configuration information is X by default, and no further configuration is required.

[0196] The second reference signal is transmitted on the second resource at Y prediction times, used by the user to obtain second channel information as training labels for the first model; simultaneously, the first channel information needs to be obtained at X measurement times as training input for the first model. To save measurement resource overhead, the following design is adopted:

[0197] When T=1, the first reference signal is sent on the first resource at the X measurement times;

[0198] When T>1, a first reference signal is sent on the union of T first resources at X measurement times, or on second resources at X+Y times.

[0199] The first reference signal and the second reference signal can be periodic, aperiodic, or semi-continuous.

[0200] The first reference signal and the second reference signal can be configured in the same reference signal configuration, that is, the RRC can be configured to the same transmission mode: for example, both can be configured as periodic and use the same period; for another example, both can be configured as aperiodic and scheduled and triggered by the same DCI; for yet another example, both can be configured as the same semi-persistent and activated and deactivated by the same MAC CE or DCI.

[0201] The first reference signal and the second reference signal can also be configured in different reference signal configurations, that is, the RRC can be configured to different transmission modes: for example, the first reference signal can be configured as periodic and the second reference signal can be configured as aperiodic; or for example, the first reference signal can be configured as semi-continuous and the second reference signal can be configured as aperiodic.

[0202] To ensure temporal correlation between the first channel information and the second channel information, additionally, in the first configuration information, the network device needs to provide first association information to associate the first reference signal at the X measurement times with the second reference signal at the Y prediction times, or to associate the first resource at the X measurement times or the union of the first resources with the second resource at the Y prediction times. The user receives the first association information, uses the measured first channel information containing the X measurement times as model input, uses the second channel information containing the Y times as model output, and associates them into a set of training samples for training the first model.

[0203] Steps 2 and 3 are the same as in Application Example 1.

[0204] In step 4, the network device sends second configuration information and a first reference signal to the user. The second configuration information is simply the same as the one in application example 1, with additional configurations for X and Y. The first reference signal is transmitted on the first resource in the X time slots at the measurement time.

[0205] Steps 5 through 7 are the same as in Application Example 1.

[0206] The solution presented in this application example can be further extended to use cases involving channel prediction.

[0207] The method described in the application embodiments enables a model trained on a dataset under one resource configuration to be extended to other resource configurations for inference, reducing the overhead of model training, downloading, and switching, while also lowering the overhead of reference signal resources. Furthermore, by designing associated configuration information, the implementation details of the second device side can be avoided, preventing privacy leaks on the second device side.

[0208] Figure 5 is a schematic flowchart of an information transmission method according to another embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto; the method includes:

[0209] S510, the second device sends first configuration information to the first device; wherein, the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0210] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource; the associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0211] Specific examples of the method executed by the second device in this application embodiment can be found in the description of the second device, such as the network device in the application example, in the foregoing embodiments. For the sake of brevity, they will not be repeated here.

[0212] In some embodiments, the first resource is associated with the third resource.

[0213] In some embodiments, the second resource is associated with the fourth resource.

[0214] In some embodiments, the first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for associated configuration information.

[0215] In some embodiments, the activation indication is carried via MAC CE or DCI.

[0216] In some embodiments, the first configuration information is carried by Radio Resource Control (RRC) signaling.

[0217] In some embodiments, the information transmission method may further include: a second device sending a second reference signal based on configuration information of a second resource; wherein the second reference signal is used to determine a first dataset.

[0218] In some embodiments, the information transmission method may further include: a second device sending second configuration information to a first device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource using a first model.

[0219] In some embodiments, the configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

[0220] In some embodiments, the first configuration information is also used to indicate X and Y.

[0221] In some embodiments, the first dataset includes first channel information and second channel information, wherein the first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

[0222] In some embodiments, the information transmission method may further include: when the first configuration information indicates configuration information for a plurality of first resources, the second device transmits a first reference signal on the union of the plurality of first resources at X time points or on the second resources at X time points.

[0223] In some embodiments, the first configuration information further includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

[0224] The specific implementation methods and examples of each technical feature in the above embodiments can be referred to the relevant descriptions in the foregoing embodiments, and have the same technical effects. For the sake of brevity, they will not be repeated here.

[0225] Figure 6 is a schematic flowchart of an information transmission method according to an embodiment of this application. This method can optionally be applied to a third device. The third device may include communication devices such as terminal devices or network devices, and may also include other types of computing entities used for model training. For example, the third device may include a user-side training unit, i.e., a user-side terminal, server, computing unit, or entity used for model training.

[0226] The method includes:

[0227] S610, the third device receives dataset information from the first device; wherein, the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information;

[0228] S620 and the third device train a first model based on the first dataset. The first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are the associated configuration information in the first configuration information.

[0229] Specific examples of the method executed by the third device in this application embodiment can be found in the description of the user-side training unit in the foregoing embodiments regarding the third device, such as in the application example. For the sake of brevity, these descriptions will not be repeated here.

[0230] In some embodiments, the dataset information further includes configuration indication information, which is used to indicate the configuration information of a first resource and a second resource associated with the first dataset.

[0231] In some embodiments, the information transmission method may further include:

[0232] The third device receives third configuration information from the first device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

[0233] In some embodiments, where the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

[0234] In some embodiments, where the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

[0235] The specific implementation methods and examples of each technical feature in the above embodiments can be referred to the relevant descriptions in the foregoing embodiments, and have the same technical effects. For the sake of brevity, they will not be repeated here.

[0236] Figure 7 is a schematic block diagram of a first device 700 according to an embodiment of the present application. The first device 700 may include:

[0237] The first communication module 710 is used to receive first configuration information from the second device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0238] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0239] The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0240] In one implementation, the first resource is associated with the third resource.

[0241] In one implementation, the second resource is associated with the fourth resource.

[0242] In one implementation, the first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

[0243] In one implementation, the activation indication is carried via MAC CE or DCI.

[0244] In one implementation, the first configuration information is carried by Radio Resource Control (RRC) signaling.

[0245] In one embodiment, the first communication module 710 is further configured to: receive a second reference signal based on the configuration information of the second resource; wherein the second reference signal is used to determine the first dataset.

[0246] In one embodiment, the first communication module 710 is further configured to: send dataset information to a third device; wherein the dataset information includes a first dataset, which is used by the third device to train a first model.

[0247] In one implementation, the dataset information further includes configuration indication information, which indicates the configuration information of a first resource and a second resource associated with the first dataset.

[0248] In one embodiment, the first communication module 710 is further configured to: receive second configuration information from the second device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain channel information corresponding to the sixth resource based on the channel information corresponding to the fifth resource.

[0249] In one embodiment, the first communication module 710 is further configured to: send third configuration information to a third device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

[0250] In one implementation, when the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

[0251] In one implementation, when the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

[0252] In one implementation, the configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

[0253] In one implementation, the first configuration information is also used to indicate X and Y.

[0254] In one implementation, the first dataset includes first channel information and second channel information, wherein the first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

[0255] In one embodiment, the first communication module 710 is further configured to: receive a first reference signal on the union of the multiple first resources at X time points or on the second resources at X time points when the first configuration information indicates the configuration information of multiple first resources.

[0256] In one embodiment, the first configuration information further includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

[0257] The first device 700 in this application embodiment can implement the corresponding functions of the first device in the foregoing method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first device 700 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the first device 700 of this application embodiment can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0258] Figure 8 is a schematic block diagram of a second device 800 according to an embodiment of the present application. The second device 800 may include:

[0259] The second communication module 810 is used to send first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information;

[0260] The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain the first dataset, and the first dataset is used to train the first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource.

[0261] The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0262] In one implementation, the first resource is associated with the third resource.

[0263] In one implementation, the second resource is associated with the fourth resource.

[0264] In one implementation, the first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

[0265] In one implementation, the activation indication is carried via MAC CE or DCI.

[0266] In one implementation, the first configuration information is carried via RRC signaling.

[0267] In one embodiment, the second communication module 810 is further configured to: send a second reference signal based on the configuration information of the second resource; wherein the second reference signal is used to determine the first dataset.

[0268] In one embodiment, the second communication module 810 is further configured to: send second configuration information to the first device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource using a first model.

[0269] In one implementation, the configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

[0270] In one implementation, the first configuration information is also used to indicate X and Y.

[0271] In one implementation, the first dataset includes first channel information and second channel information, wherein the first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

[0272] In one embodiment, the second communication module 810 is further configured to: transmit a first reference signal on the union of the multiple first resources at X time points or on the second resources at X time points when the first configuration information indicates the configuration information of multiple first resources.

[0273] In one embodiment, the first configuration information further includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

[0274] The second device 800 in this application embodiment can implement the corresponding functions of the second device in the foregoing method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the second device 800 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the second device 800 of this application embodiment can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0275] Figure 9 is a schematic block diagram of a third device 900 according to an embodiment of the present application. The third device 900 may include:

[0276] The third communication module 910 is used to receive dataset information from the first device; wherein the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information;

[0277] The first processing module 920 is used to train a first model based on a first dataset. The first model is used to obtain channel information corresponding to a second resource based on channel information corresponding to a first resource, and to obtain channel information corresponding to a fourth resource based on channel information corresponding to a third resource. The configuration information of the third resource and the configuration information of the fourth resource are associated configuration information in the first configuration information.

[0278] In one implementation, the dataset information further includes configuration indication information, which indicates the configuration information of a first resource and a second resource associated with the first dataset.

[0279] In one embodiment, the third communication module 910 is further configured to: receive third configuration information from the first device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

[0280] In one implementation, when the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

[0281] In one implementation, when the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

[0282] The third device 900 in this application embodiment can implement the corresponding functions of the third device in the foregoing method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the third device 900 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the third device 900 of the application embodiment can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0283] Figure 10 is a schematic structural diagram of a communication device 1000 according to an embodiment of this application. The communication device 1000 includes a processor 1010, which can call and run computer programs from memory to enable the communication device 1000 to implement the methods in the embodiments of this application.

[0284] In one embodiment, the communication device 1000 may further include a memory 1020. The processor 1010 can retrieve and run computer programs from the memory 1020 to enable the communication device 1000 to implement the methods described in the embodiments of this application.

[0285] The memory 1020 can be a separate device independent of the processor 1010, or it can be integrated into the processor 1010.

[0286] In one embodiment, the communication device 1000 may further include a transceiver 1030, and the processor 1010 may control the transceiver 1030 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0287] The transceiver 1030 may include a transmitter and a receiver. The transceiver 1030 may further include an antenna, and the number of antennas may be one or more.

[0288] In one embodiment, the communication device 1000 may be the first device in the embodiments of this application, and the communication device 1000 may implement the corresponding processes implemented by the first device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0289] In one embodiment, the communication device 1000 may be the second device in the embodiments of this application, and the communication device 1000 may implement the corresponding processes implemented by the second device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0290] In one embodiment, the communication device 1000 may be a third device in the embodiments of this application, and the communication device 1000 may implement the corresponding processes implemented by the third device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0291] Figure 11 is a schematic structural diagram of a chip 1100 according to an embodiment of this application. The chip 1100 includes a processor 1110, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0292] In one embodiment, chip 1100 may further include memory 1120. Processor 1110 can retrieve and run computer programs from memory 1120 to implement the methods executed by the first device, second device, or third device in this embodiment.

[0293] The memory 1120 can be a separate device independent of the processor 1110, or it can be integrated into the processor 1110.

[0294] In one embodiment, the chip 1100 may further include an input interface 1130. The processor 1110 can control the input interface 1130 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0295] In one embodiment, the chip 1100 may further include an output interface 1140. The processor 1110 can control the output interface 1140 to communicate with other devices or chips; specifically, it can output information or data to other devices or chips.

[0296] In one implementation, the chip can be applied to the first device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the first device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0297] In one implementation, the chip can be applied to the second device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the second device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0298] In one implementation, the chip can be applied to a third device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the third device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0299] The chips used in the first device, the second device, and the third device can be the same chip or different chips.

[0300] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0301] The processors mentioned above can be general-purpose processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processors mentioned above can be microprocessors or any conventional processor.

[0302] The aforementioned memory can be volatile memory or non-volatile memory, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM).

[0303] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0304] Figure 12 is a schematic block diagram of a communication system 1200 according to an embodiment of this application. The communication system 1200 includes a first device 1210 and a second device 1220. The second device 1220 is used to send first configuration information to the first device 1210. The first device 1210 is used to receive the first configuration information from the second device 1220. The first configuration information includes configuration information of a first resource, configuration information of a second resource, and associated configuration information; wherein the configuration information of the first and second resources is used by the first device 1210 to obtain a first dataset, the first dataset being used to train a first model; the first model is used to obtain channel information corresponding to the second resource based on the channel information corresponding to the first resource; the associated configuration information includes configuration information of a third resource and configuration information of a fourth resource; the first model is also used to obtain channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

[0305] The first device 1210 can be used to implement the corresponding functions implemented by the first device in the above method, and the second device 1220 can be used to implement the corresponding functions implemented by the second device in the above method. For the sake of brevity, further details are omitted here.

[0306] Optionally, the communication system 1200 may also include a third device, which can be used to implement the corresponding functions implemented by the third device in the above method. For the sake of brevity, further details are omitted here.

[0307] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. 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 via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0308] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0309] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0310] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An information transmission method, comprising: The first device receives first configuration information from the second device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information; The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

2. The method according to claim 1, wherein, The first resource is related to the third resource.

3. The method according to claim 1 or 2, wherein, The second resource is related to the fourth resource.

4. The method according to any one of claims 1-3, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

5. The method according to claim 4, wherein, The activation indication is carried by the Media Access Control Unit (MAC CE) or Downlink Dynamic Information (DCI).

6. The method according to any one of claims 1-5, wherein, The first configuration information is carried by Radio Resource Control (RRC) signaling.

7. The method according to any one of claims 1-6, wherein, The method further includes: The first device receives a second reference signal based on the configuration information of the second resource; wherein the second reference signal is used to determine the first dataset.

8. The method according to any one of claims 1-7, wherein, The method further includes: The first device sends dataset information to the third device; wherein, the dataset information includes the first dataset, which is used by the third device to train the first model.

9. The method according to claim 8, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

10. The method according to any one of claims 1-9, further comprising: The first device receives second configuration information from the second device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource.

11. The method according to claim 10, wherein, The method further includes: The first device sends third configuration information to the third device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

12. The method according to claim 11, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

13. The method according to claim 11 or 12, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

14. The method according to any one of claims 1-13, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

15. The method according to claim 14, wherein, The first configuration information is also used to indicate X and Y.

16. The method according to claim 14 or 15, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

17. The method according to claim 16, wherein, The method further includes: When the first configuration information indicates configuration information for multiple first resources, the first device receives the first reference signal on the union of the multiple first resources at X time points or on the second resources at X time points.

18. The method according to any one of claims 14-17, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

19. An information transmission method, comprising: The second device sends first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information; The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

20. The method according to claim 19, wherein, The first resource is related to the third resource.

21. The method according to claim 19 or 20, wherein, The second resource is related to the fourth resource.

22. The method according to any one of claims 19-21, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

23. The method according to claim 22, wherein, The activation indication is carried via MAC CE or DCI.

24. The method according to any one of claims 19-23, wherein, The first configuration information is carried by Radio Resource Control (RRC) signaling.

25. The method according to any one of claims 19-24, wherein, The method further includes: The second device sends a second reference signal based on the configuration information of the second resource; wherein the second reference signal is used to determine the first dataset.

26. The method according to any one of claims 19-25, further comprising: The second device sends second configuration information to the first device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource and using the first model.

27. The method according to any one of claims 19-26, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

28. The method according to claim 27, wherein, The first configuration information is also used to indicate X and Y.

29. The method according to claim 27 or 28, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

30. The method according to claim 29, wherein, The method further includes: When the first configuration information indicates configuration information for multiple first resources, the second device transmits the first reference signal on the union of the multiple first resources at X time points or on the second resources at X time points.

31. The method according to any one of claims 27-30, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

32. An information transmission method, comprising: The third device receives dataset information from the first device; wherein the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information; The third device trains a first model based on the first dataset. The first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are the associated configuration information in the first configuration information.

33. The method according to claim 32, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

34. The method according to claim 32 or 33, wherein, The method further includes: The third device receives third configuration information from the first device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

35. The method according to claim 34, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

36. The method according to claim 34 or 35, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

37. A first device, comprising: A first communication module is configured to receive first configuration information from a second device; wherein the first configuration information includes configuration information of a first resource, configuration information of a second resource, and associated configuration information. The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

38. The first device according to claim 37, wherein, The first resource is related to the third resource.

39. The first device according to claim 37 or 38, wherein, The second resource is related to the fourth resource.

40. The first device according to any one of claims 37-39, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

41. The first device according to claim 40, wherein, The activation indication is carried via MAC CE or DCI.

42. The first device according to any one of claims 37-41, wherein, The first configuration information is carried via RRC signaling.

43. The first device according to any one of claims 37-41, wherein, The first communication module is further configured to: Based on the configuration information of the second resource, a second reference signal is received; wherein the second reference signal is used to determine the first dataset.

44. The first device according to any one of claims 37-43, wherein, The first communication module is further configured to: Send dataset information to a third device; wherein the dataset information includes the first dataset, which is used by the third device to train the first model.

45. The first device according to claim 44, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

46. ​​The first device according to any one of claims 37-45, wherein, The first communication module is further configured to: The first device receives second configuration information from the second device; wherein the second configuration information includes configuration information for a fifth resource and configuration information for a sixth resource; the second configuration information is used to instruct the first device to obtain channel information corresponding to the sixth resource based on the channel information corresponding to the fifth resource.

47. The first device according to claim 46, wherein, The first communication module is further configured to: Send third configuration information to a third device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

48. The first device according to claim 47, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

49. The first device according to claim 47 or 48, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

50. The first device according to any one of claims 37-49, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

51. The first device according to claim 50, wherein, The first configuration information is also used to indicate X and Y.

52. The first device according to claim 50 or 51, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

53. The first device according to claim 52, wherein, The first communication module is further configured to: When the first configuration information indicates the configuration information of multiple first resources, the first reference signal is received on the union of the multiple first resources at X time points or on the second resources at X time points.

54. The first device according to any one of claims 50-53, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

55. A second device, comprising: The second communication module is used to send first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information; The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

56. The second device according to claim 55, wherein, The first resource is related to the third resource.

57. The second device according to claim 55 or 56, wherein, The second resource is related to the fourth resource.

58. The second device according to any one of claims 55-57, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

59. The second device according to claim 58, wherein, The activation indication is carried via MAC CE or DCI.

60. The second device according to any one of claims 55-59, wherein, The first configuration information is carried via RRC signaling.

61. The second device according to any one of claims 55-60, wherein, The second communication module is also used for: Based on the configuration information of the second resource, a second reference signal is sent; wherein the second reference signal is used to determine the first dataset.

62. The second device according to any one of claims 55-61, wherein, The second communication module is also used for: Send second configuration information to the first device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource and using the first model.

63. The second device according to any one of claims 55-62, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

64. The second device according to claim 63, wherein, The first configuration information is also used to indicate X and Y.

65. The second device according to claim 63 or 64, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

66. The second device according to claim 65, wherein, The second communication module is also used for: When the first configuration information indicates the configuration information of multiple first resources, the first reference signal is transmitted on the union of the multiple first resources at X time points or on the second resources at X time points.

67. The second device according to any one of claims 63-66, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

68. A third device, comprising: The third communication module is used to receive dataset information from the first device; wherein the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of the first resource and the configuration information of the second resource in the first configuration information; A first processing module is used to train a first model based on the first dataset. The first model is used to obtain channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are associated configuration information in the first configuration information.

69. The third device according to claim 68, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

70. The third device according to claim 68 or 69, wherein, The third communication module is also used for: Receive third configuration information from the first device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

71. The third device according to claim 70, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

72. The third device according to claim 70 or 71, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

73. A first device, comprising: The transceiver, processor, and memory, wherein the memory stores a computer program, the transceiver is used to communicate with other devices, and the processor invokes and runs the computer program stored in the memory to cause the first device to perform: Receive first configuration information from the second device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information; The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information includes the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

74. The first device according to claim 73, wherein, The first resource is related to the third resource.

75. The first device according to claim 73 or 74, wherein, The second resource is related to the fourth resource.

76. The first device according to any one of claims 73-75, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

77. The first device according to claim 76, wherein, The activation indication is carried via MAC CE or DCI.

78. The first device according to any one of claims 73-77, wherein, The first configuration information is carried by Radio Resource Control (RRC) signaling.

79. The first device according to any one of claims 73-78, wherein, The processor is also configured to cause the first device to perform: Based on the configuration information of the second resource, a second reference signal is received; wherein the second reference signal is used to determine the first dataset.

80. The first device according to any one of claims 73-79, wherein, The processor is also configured to cause the first device to perform: Send dataset information to a third device; wherein the dataset information includes the first dataset, which is used by the third device to train the first model.

81. The first device according to claim 80, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

82. The first device according to any one of claims 73-81, wherein, The processor is also configured to cause the first device to perform: The first device receives second configuration information from the second device; wherein the second configuration information includes configuration information for a fifth resource and configuration information for a sixth resource; the second configuration information is used to instruct the first device to obtain channel information corresponding to the sixth resource based on the channel information corresponding to the fifth resource.

83. The first device according to claim 82, wherein, The processor is also configured to cause the first device to perform: Send third configuration information to a third device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

84. The first device according to claim 83, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

85. The first device according to claim 82 or 84, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

86. The first device according to any one of claims 73-85, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

87. The first device according to claim 86, wherein, The first configuration information is also used to indicate X and Y.

88. The first device according to claim 86 or 87, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

89. The first device according to claim 88, wherein, The processor is also configured to cause the first device to perform: When the first configuration information indicates the configuration information of multiple first resources, the first reference signal is received on the union of the multiple first resources at X time points or on the second resources at X time points.

90. The first device according to any one of claims 86-89, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

91. A second device, comprising: The transceiver, processor, and memory, wherein the memory stores a computer program, the transceiver is used to communicate with other devices, and the processor invokes and runs the computer program stored in the memory to cause the second device to perform: Send first configuration information to the first device; wherein the first configuration information includes configuration information of the first resource, configuration information of the second resource, and associated configuration information; The configuration information of the first resource and the configuration information of the second resource are used by the first device to obtain a first dataset, and the first dataset is used to train a first model; the first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource. The associated configuration information is used by the first device to determine the configuration information of the third resource and the configuration information of the fourth resource; the first model is also used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource.

92. The second device according to claim 91, wherein, The first resource is related to the third resource.

93. The second device according to claim 91 or 92, wherein, The second resource is related to the fourth resource.

94. The second device according to any one of claims 91-93, wherein, The first model is used to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource when the first device receives an activation instruction for the associated configuration information.

95. The second device according to claim 94, wherein, The activation indication is carried via MAC CE or DCI.

96. The second device according to any one of claims 91-95, wherein, The first configuration information is carried via RRC signaling.

97. The second device according to any one of claims 91-96, wherein, The processor is also configured to cause the second device to perform: Based on the configuration information of the second resource, a second reference signal is sent; wherein the second reference signal is used to determine the first dataset.

98. The second device according to any one of claims 91-97, wherein, The processor is also configured to cause the second device to perform: Send second configuration information to the first device; wherein the second configuration information includes configuration information of a fifth resource and configuration information of a sixth resource; the second configuration information is used to instruct the first device to obtain the channel information corresponding to the configuration information of the sixth resource based on the channel information corresponding to the configuration information of the fifth resource and using the first model.

99. The second device according to any one of claims 91-98, wherein, The configuration information of the first resource is used to determine the first resource at X time points; the configuration information of the second resource is used to determine the second resource at Y time points; the Y time points are after the X time points; X is an integer greater than or equal to 1, and Y is an integer greater than or equal to 1.

100. The second device according to claim 99, wherein, The first configuration information is also used to indicate X and Y.

101. The second device according to claim 99 or 100, wherein, The first dataset includes first channel information and second channel information. The first channel information is determined based on a first reference signal received on a first resource at X time points, and the second channel information is determined based on a second reference signal received on a second resource at Y time points.

102. The second device according to claim 101, wherein, The processor is also configured to cause the second device to perform: When the first configuration information indicates the configuration information of multiple first resources, the first reference signal is transmitted on the union of the multiple first resources at X time points or on the second resources at X time points.

103. The second device according to any one of claims 99-102, wherein, The first configuration information also includes first association information, which is used to indicate the association relationship between the first reference signal at X times and the second reference signal at Y times, and / or the association relationship between the first resource or multiple first resources at X times and the second resource at Y times.

104. A third device, comprising: The transceiver, processor, and memory, wherein the memory stores a computer program, the transceiver is used to communicate with other devices, and the processor invokes and runs the computer program stored in the memory to cause the third device to perform: Receive dataset information from a first device; wherein the dataset information includes a first dataset, which is obtained by the first device based on the configuration information of a first resource and the configuration information of a second resource in the first configuration information; Based on the first dataset, a first model is trained. The first model is used to obtain the channel information corresponding to the second resource based on the channel information corresponding to the first resource, and to obtain the channel information corresponding to the fourth resource based on the channel information corresponding to the third resource. The configuration information of the third resource and the configuration information of the fourth resource are the associated configuration information in the first configuration information.

105. The third device according to claim 104, wherein, The dataset information also includes configuration indication information, which is used to indicate the configuration information of the first resource and the configuration information of the second resource associated with the first dataset.

106. The third device according to claim 104 or 105, wherein, The processor is also configured to cause the third device to perform: Receive third configuration information from the first device; wherein the third configuration information is used to obtain a model associated with the configuration information of the fifth resource and the configuration information of the sixth resource.

107. The third device according to claim 106, wherein, When the configuration information of the fifth resource includes the configuration information of the first resource and the configuration information of the sixth resource includes the configuration information of the second resource, the third configuration information is used to indicate the configuration information of the fifth resource and the configuration information of the sixth resource.

108. The third device according to claim 106 or 107, wherein, When the configuration information of the fifth resource includes the configuration information of the third resource and the configuration information of the sixth resource includes the configuration information of the fourth resource, the third configuration information is used to indicate the configuration information of the first resource and the configuration information of the second resource.

109. A chip, comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1 to 18.

110. A chip, comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 20 to 33.

111. A chip, comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 34 to 38.

112. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as claimed in any one of claims 1 to 18.

113. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as described in any one of claims 19 to 31.

114. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as described in any one of claims 32 to 36.

115. A computer program product comprising computer program instructions that cause a computer to perform the method as claimed in any one of claims 1 to 18.

116. A computer program product comprising computer program instructions that cause a computer to perform the method as described in any one of claims 19 to 31.

117. A computer program product comprising computer program instructions that cause a computer to perform the method as described in any one of claims 32 to 36.

118. A computer program that causes a computer to perform the method as claimed in any one of claims 1 to 18.

119. A computer program that causes a computer to perform the method as described in any one of claims 19 to 31.

120. A computer program that causes a computer to perform the method as described in any one of claims 32 to 36.

121. A communication system, comprising: A first device for performing the method as described in any one of claims 1 to 18; A second device for performing the method as described in any one of claims 19 to 31.

Images