Information synchronization method and apparatus, device, and storage medium

Abstract

An information synchronization method and apparatus, a device, and a storage medium, relating to the technical field of communications. The method comprises: synchronizing first information between a terminal device and a network device, the first information being used for associating a condition for the network device to transmit a reference signal and / or a condition for the terminal device to receive the reference signal, wherein a measurement result for the reference signal by the terminal device is used as training data or inference data of a prediction model, and the prediction model is configured to predict channel state information between the terminal device and the network device (310). In the present application, consistency of a network-side condition and / or a terminal-side condition is maintained during training and inference phases of a model.

Description

Information synchronization method and device, equipment and storage medium TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communication technology, in particular to an information synchronization method, device, equipment and storage medium. BACKGROUND

[0002] In view of the great success of AI (Artificial Intelligence) technology, especially deep learning in computer vision, natural language processing and other aspects, the communication field begins to try to use deep learning to solve technical problems that traditional communication methods cannot solve.

[0003] The related technology proposes model-based CSI (Channel State Information) prediction. The purpose of CSI prediction is to solve the problem of outdated CSI due to dynamic changes in the wireless environment. The traditional CSI feedback method needs to report the current channel state frequently, which will generate a large overhead in the high mobility scenario. By predicting the future CSI state, the system can still maintain effective control over the channel state without the need for frequent reporting.

[0004] However, how to improve the prediction effect of the model based on the model-based CSI prediction technology still needs further research.

[0005] SUMMARY

[0006] Embodiments of the present application provide an information synchronization method, device, equipment and storage medium. The technical solutions provided by the embodiments of the present application are as follows:

[0007] According to an aspect of the embodiments of the present application, an information synchronization method is provided, the method is executed by a terminal device, and the method comprises:

[0008] Synchronizing first information with a network device, the first information being used to associate a condition of the network device sending a reference signal and / or a condition of the terminal device receiving the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, and the prediction model is used to predict channel state information between the terminal device and the network device.

[0009] According to an aspect of the embodiments of the present application, an information synchronization method is provided, the method is executed by a network device, and the method comprises:

[0010] synchronize first information with a terminal device, the first information being used to associate a condition of transmitting a reference signal by the network device and / or a condition of receiving the reference signal by the terminal device, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

[0011] According to an aspect of embodiments of the present application, there is provided an information synchronization apparatus, comprising:

[0012] a transceiver configured to synchronize first information with a network device, the first information being used to associate a condition of transmitting a reference signal by the network device and / or a condition of receiving the reference signal by the terminal device, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

[0013] According to an aspect of embodiments of the present application, there is provided an information synchronization apparatus, comprising:

[0014] a transceiver configured to synchronize first information with a terminal device, the first information being used to associate a condition of transmitting a reference signal by the network device and / or a condition of receiving the reference signal by the terminal device, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

[0015] According to an aspect of embodiments of the present application, there is provided a terminal device, comprising a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the information synchronization method performed by the terminal device.

[0016] According to an aspect of embodiments of the present application, there is provided a network device, comprising a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement the information synchronization method performed by the network device.

[0017] According to an aspect of embodiments of the present application, there is provided a computer readable storage medium, the storage medium storing a computer program, the computer program being configured to be executed by a processor to implement the information synchronization method performed by the terminal device or the information synchronization method performed by the network device.

[0018] According to an aspect of the embodiments of the present application, a chip is provided, which includes programmable logic circuit and / or program instructions, and when the chip is running, is used to implement the information synchronization method performed by the terminal device or implement the information synchronization method performed by the network device.

[0019] According to an aspect of the embodiments of the present application, a computer program product is provided, which includes computer instructions stored in a computer readable storage medium, and a processor reads and executes the computer instructions from the computer readable storage medium to implement the information synchronization method performed by the terminal device or implement the information synchronization method performed by the network device.

[0020] The technical solutions provided by the embodiments of the present application can include the following beneficial effects:

[0021] By synchronizing the first information between the terminal device and the network device, since the first information is associated with the network side condition and / or the terminal side condition, by synchronizing the first information between the terminal device and the network device in the training stage and / or the inference stage of the prediction model, the network side condition can be told to the terminal device, or the terminal side condition can be told to the network device, so that the consistency of the network side condition and / or the terminal side condition can be maintained in the training stage and the inference stage of the model. BRIEF DESCRIPTION OF DRAWINGS

[0022] FIG. 1 is a schematic diagram of a network architecture provided by an embodiment of the present application;

[0023] FIG. 2 is a time domain schematic diagram of CSI prediction provided by an embodiment of the present application;

[0024] FIG. 3 is a flowchart of an information synchronization method provided by an embodiment of the present application;

[0025] FIG. 4 is a block diagram of an information synchronization apparatus provided by an embodiment of the present application;

[0026] FIG. 5 is a block diagram of an information synchronization apparatus provided by another embodiment of the present application;

[0027] FIG. 6 is a structural schematic diagram of a communication device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0029] The network architecture and service scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0030] Please refer to FIG. 1, which shows a schematic diagram of a network architecture 100 provided by an embodiment of the present application. The network architecture 100 can include a terminal device 10, an access network device 20 and a core network element 30.

[0031] The terminal device 10 can refer to a UE (User Equipment), a STA (Station), an access terminal, a subscriber unit, a subscriber station, a mobile station, a mobile, a remote station, a remote terminal, a mobile device, a wireless communication device, a user agent or a user equipment. In some embodiments, the terminal device 10 can also be a cellular phone, a cordless phone, a SIP (Session Initiation Protocol) phone, a WLL (Wireless Local Loop) station, a PDA (Personal Digital Assistant), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a 5GS (5th Generation System) or a terminal device in a future evolved PLMN (Public Land Mobile Network), etc., and the embodiments of the present application are not limited thereto. For the convenience of description, the above-mentioned devices are collectively referred to as terminal devices. The number of terminal devices 10 is usually multiple, and one or more terminal devices 10 can be distributed in a cell managed by each access network device 20. The terminal device can also be referred to as a terminal or a UE, and those skilled in the art can understand its meaning.

[0032] The access network device 20 is a device deployed in an access network to provide wireless communication functions for the terminal device 10. The access network device 20 can include various forms of macro base stations, micro base stations, relay stations, APs (Access Points), and the like. In systems using different wireless access technologies, the names of devices with access network device functions can be different, for example, in a 5G NR (New Radio) system, it is called gNodeB or gNB (Next Generation Node B). With the evolution of communication technology, the name of the "access network device" can change. For ease of description, in the embodiments of the present application, the above-mentioned devices that provide wireless communication functions for the terminal device 10 are collectively referred to as access network devices. In some embodiments, through the access network device 20, a communication relationship can be established between the terminal device 10 and the core network element 30. Illustratively, in the LTE (Long Term Evolution) system, the access network device 20 can be an EUTRAN (Evolved Universal Terrestrial Radio Access Network) or one or more eNodeBs in the EUTRAN; in the 5G NR system, the access network device 20 can be a RAN (Radio Access Network) or one or more gNBs in the RAN. In the embodiments of the present application, the "network device" refers to the access network device 20, such as a base station, unless otherwise specified.

[0033] The core network element 30 is a network element deployed in the core network, and the main functions of the core network element 30 are to provide user connection, manage users, and complete bearer for services, and provide an interface to external networks as a bearer network. For example, the core network element in the 5G NR system can include AMF (Access and Mobility Management Function) entities, UPF (User Plane Function) entities, and SMF (Session Management Function) entities.

[0034] In some embodiments, the access network device 20 and the core network element 30 communicate with each other through some air interface technology, such as the NG interface in the 5G NR system. The access network device 20 and the terminal device 10 communicate with each other through some air interface technology, such as the Uu interface.

[0035] The "5G NR system" in the embodiments of the present application can also be referred to as a 5G system or an NR system, but those skilled in the art can understand its meaning. The technical solutions described in the embodiments of the present application can be applicable to the LTE system, and can also be applicable to the 5G NR system, and can also be applicable to the subsequent evolution system (such as the B5G (Beyound 5G) system, the 6G system (6th Generation System, the sixth generation mobile communication system)) of the 5G NR system, and can also be applicable to other communication systems such as the NB-IoT (Narrow Band Internet of Things, Narrow Band Internet of Things) system, and the like, and the present application does not limit this.

[0036] In the embodiments of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resource (for example, frequency domain resource, or spectrum resource) on the carrier used by the cell. The cell can be a cell corresponding to the network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell (Small cell). The small cell can include a metro cell, a micro cell, a pico cell, a femto cell, and the like. These small cells have the characteristics of small coverage and low transmit power, and are suitable for providing high-speed data transmission services.

[0037] Before introducing the technical solutions of the present application, some related technical knowledge involved in the present application will be introduced and explained. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0038] I. Wireless communication and artificial intelligence

[0039] In recent years, artificial intelligence (AI) and machine learning (ML) technologies have relied on the development of different types of neural networks and machine learning algorithms, and have achieved wide application in different fields such as image, voice and video processing. Typical neural network architectures include fully connected networks, convolutional neural networks (CNN), recurrent neural networks (RNN), and Transformer structures with self-attention mechanisms, which can complete different task objectives.

[0040] With the rapid development of AI / ML technology, the combination of artificial intelligence and wireless communication technology has attracted widespread interest from both academia and industry. AI / ML-based CSI (Channel State Information) feedback, beam management, and positioning technology have been extensively researched, evaluated, and standardized. Further, in the development of future wireless communication systems, AI / ML technology may generate more wireless AI / ML use cases, such as AI / ML-based channel estimation methods, AI / ML-based modulation and demodulation techniques, and AI / ML-based integrated receiver design, all of which exhibit performance gains over traditional non-AI / ML algorithms. Therefore, future wireless communication systems such as 6G may incorporate more AI / ML modules to enhance overall system performance.

[0041] II. CSI prediction in NR

[0042] The purpose of CSI prediction is to address the problem of outdated CSI due to dynamic changes in the wireless environment. Traditional CSI feedback methods require frequent reporting of current channel state, which can result in significant overhead in high-mobility scenarios. By predicting future CSI states, the system can maintain effective control over channel state without the need for frequent reporting.

[0043] The model type can be a commonly used deep learning model, including RNN (Recurrent Neural Network), LSTM (Long-Short Term Memory), GRU (Gated Recurrent Unit), etc. These models are suitable for processing time series data and can predict future CSI states based on historical CSI measurements. In addition, some research has shown that CNN (Convolutional Neural Network) can also effectively capture the correlation between time, space, and frequency domains, thereby improving prediction performance.

[0044] 3GPP (3rd Generation Partnership Project) emphasizes the use of single-sided models on the UE side for CSI prediction.

[0045] The input of the model is the historical CSI measurement. The model input is usually a series of past CSI measurements, which reflect the changes in channel state over time. Specifically, as shown in FIG. 2, the input can be the CSI data at multiple (4 in this figure) historical measurement times. The CSI measurement value mentioned here can be the H matrix of the equivalent channel, or the singular value vector / eigenvector after singular value / eigenvalue decomposition of the channel matrix.

[0046] The output of the model is the predicted value of the future CSI. The model output is the predicted value of the CSI at one or more future time instances. Similarly, the CSI measurement value referred to herein can be the H matrix of the equivalent channel, or the singular value vector / eigenvector after singular value / eigenvalue decomposition of the channel matrix.

[0047] Please refer to FIG. 3, which shows a flowchart of the information synchronization method provided by an embodiment of the present application. The method can be applied to the network architecture shown in FIG. 1. The method can include the following step 310.

[0048] In step 310, the terminal device and the network device synchronize first information, and the first information is used to associate a condition for the network device to send a reference signal and / or a condition for the terminal device to receive the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, and the prediction model is used to predict channel state information between the terminal device and the network device.

[0049] In some embodiments, the condition for the network device to send the reference signal refers to a state or configuration of the network device to send the reference signal. In some embodiments, the condition for the network device to send the reference signal includes, but is not limited to, at least one of the following: an antenna port virtualization manner (such as CSI-RS virtualization) of the reference signal, a phase coherent time of a transmitter of the network device (such as gNB transmitter’s phase coherent time), an antenna layout, an antenna element to TxRU (Transceiver Unit) mapping, a digital / analog beamforming, and time domain configuration information (such as an interval of measurement time instances, an interval of prediction time instances, etc.). In the following, for ease of description, the condition for the network device to send the reference signal can also be referred to as “network side condition”.

[0050] In some embodiments, the condition for the terminal device to receive the reference signal refers to a state or configuration of the terminal device to receive the reference signal. In some embodiments, the condition for the terminal device to receive the reference signal includes, but is not limited to, at least one of the following: a number of receive ports (Number of Rx), and Rx beamforming. In the following, for ease of description, the condition for the terminal device to receive the reference signal can also be referred to as “terminal side condition”.

[0051] In some embodiments, the reference signal is a downlink reference signal, i.e., a reference signal sent by the network device to the terminal device. In some embodiments, the reference signal is a CSI-RS (Channel State Information-Reference Signal). A reference signal (RS for short) is a known signal provided by the transmitting end to the receiving end for channel estimation or channel sounding. In the embodiments of the present application, the reference signal is mainly taken as the CSI-RS for example, and the present application is not limited to other forms of reference signals.

[0052] In some embodiments, the prediction model is an AI / ML model for predicting channel state information between the terminal device and the network device. Channel state information (CSI for short) refers to the channel properties of a communication link. It describes the attenuation factors of a signal on each transmission path, i.e., the value of each element in the channel gain matrix H, such as signal scattering (Scattering), environmental attenuation (fading, multipath fading or shadowing fading), distance attenuation (power decay of distance), etc. CSI can enable the communication system to adapt to the current channel conditions and provide high reliability and high rate communication in multi-antenna systems. In the embodiments of the present application, the model type of the prediction model is not limited, such as the CNN, RNN, LSTM, GRU, etc. introduced above.

[0053] In some embodiments, in the training phase of the prediction model, the terminal device measures the reference signal transmitted by the network device to obtain corresponding measurement results. In the training phase, the measurement results of the reference signal are used as training data for the prediction model. Specifically, based on the measurement results of the reference signal, a data set for training the prediction model is constructed. The prediction model is trained using the data set. Illustratively, the data set includes a plurality of training samples, each training sample can include measurement values obtained by the terminal device at one or more measurement times, each training sample has corresponding label data, the label data includes measurement values obtained at one or more measurement times, and the measurement values included in the training sample correspond to measurement times earlier than the measurement times corresponding to the measurement values included in the label data. Based on the above method of generating training samples, a prediction model can be trained to predict channel state information at future times based on channel state information at historical times. Taking the reference signal as an example, in the training phase of the prediction model, the terminal device measures the downlink CSI-RS transmitted by the network device. Part of it is used as input for the model, i.e., historical CSI; another part is used as a label for the model, i.e., predicted CSI. For CSI-RS transmission in the training data, it is affected by network side conditions and / or terminal side conditions.

[0054] In some embodiments, in the inference phase of the prediction model, the terminal device also measures the reference signal transmitted by the network device to obtain corresponding measurement results. In the inference phase, the measurement results of the reference signal are used as inference data for the prediction model. Specifically, the measurement results of the reference signal are input into the prediction model, and the prediction model outputs the predicted channel state information, thereby realizing prediction of channel state information at future times based on channel state information at historical times. Taking the reference signal as an example, in the inference phase of the prediction model, the terminal device only measures part of the CSI-RS transmitted by the network device as input for the model. Through the input, the model infers the CSI at one or more future times. Similarly, in the inference phase, the result of the CSI prediction is also affected by the network side conditions and / or the terminal side conditions.

[0055] It can be understood that the network side condition and / or the terminal side condition in the training phase of the prediction model and the network side condition and / or the terminal side condition in the inference phase should be as consistent as possible, and if not consistent, the prediction performance of the CSI prediction model will be greatly affected. In the embodiments of the present application, the first information is synchronized between the terminal device and the network device, used to maintain the consistency of the condition of the network device sending the reference signal and / or the consistency of the condition of the terminal device receiving the reference signal in the training phase and the inference phase of the prediction model. Since the first information is associated with the network side condition and / or the terminal side condition, by synchronizing the first information between the terminal device and the network device in the training phase and / or the inference phase of the prediction model, the network side condition can be told to the terminal device, or the terminal side condition can be told to the network device, thereby maintaining the consistency of the network side condition and / or the terminal side condition in the training phase and the inference phase of the model.

[0056] In the following, the content included in the first information is described.

[0057] In some embodiments, the first information includes identification information, different identification information is associated with different conditions of the network device sending the reference signal, and / or different identification information is associated with different conditions of the terminal device receiving the reference signal.

[0058] The identification information can be an ID (Identifier). Exemplarily, the following several different identification information is included: ID 1, ID 2, ID 3, wherein ID 1 is associated with network side condition 1 and / or terminal side condition 1, ID 2 is associated with network side condition 2 and / or terminal side condition 2, and ID 3 is associated with network side condition 3 and / or terminal side condition 3. The above network side condition 1, network side condition 2 and network side condition 3 are three different network side conditions, such as the values of one or more parameters included in the network side conditions listed above are different. The above terminal side condition 1, terminal side condition 2 and terminal side condition 3 are three different terminal side conditions, such as the values of one or more parameters included in the terminal side conditions listed above are different.

[0059] In some embodiments, the identification information includes but is not limited to at least one of the following: associated ID (associated ID), dataset ID (dataset ID), model ID (model ID).

[0060] In some embodiments, the identification information can also be represented by an index value. Taking the network side condition as an example, assume that there are 16 different network side conditions in total, and the IDs of the 16 different network side conditions are 0-15 respectively. If the network side condition is directly indicated by the ID, 4 bits are needed to effectively distinguish the 16 different network side conditions. Therefore, the index value form can be considered for indication to save bit overhead to some extent. For example, among the above-mentioned 16 different network side conditions, the IDs of the available / candidate network side conditions are 1, 5, 9, and 16 respectively, and the above-mentioned 4 network side conditions can be assigned index values 0, 1, 2, and 3 respectively, so that the network side condition can be indicated by 2-bit index value.

[0061] In some embodiments, the identification information associated with the prediction model is the same as the identification information associated with the data set used for training the prediction model. The data set used for training the prediction model can be collected and generated by the terminal device or collected and generated by the network device. When the data set used for training the prediction model is collected and generated by the terminal device, in the training phase of the model, the terminal device measures the reference signal sent by the network device, and generates the data set based on the measurement result. When the data set used for training the prediction model is collected and generated by the network device, in the training phase of the model, the terminal device measures the reference signal sent by the network device, and reports the measurement result to the network device, and the network device generates the data set based on the measurement result. Since the identification information is associated with the network side condition and / or the terminal side condition, and the identification information is also associated with the data set, the data set also has an association relationship with the network side condition and / or the terminal side condition. It can be understood that for the data set, the network side condition and / or the terminal side condition having an association relationship, it represents a data set collected and generated based on the measurement result of the reference signal transmitted and received using the network side condition and / or the terminal side condition. For example, in the training phase of the model, under the network side condition 1, the network device sends a reference signal, the terminal device receives and measures the reference signal using the terminal side condition 1, and generates a data set 1 based on the measurement result, and assuming that the network side condition 1 is associated with ID 1, the following association relationship is obtained: ID 1, network side condition 1, terminal side condition 1, data set 1. For another example, in the training phase of the model, under the network side condition 2, the network device sends a reference signal, the terminal device receives and measures the reference signal using the terminal side condition 2, and generates a data set 2 based on the measurement result, and assuming that the network side condition 2 is associated with ID 2, the following association relationship is obtained: ID 2, network side condition 2, terminal side condition 2, data set 2.

[0062] In some embodiments, the prediction model is trained based on a mixed dataset, the mixed dataset comprising a plurality of datasets, each dataset being associated with a set of conditions for the network device to transmit the reference signal and / or a set of conditions for the terminal device to receive the reference signal, and different datasets being associated with different conditions for the network device to transmit the reference signal and / or different conditions for the terminal device to receive the reference signal. The collection and generation of the datasets are as described above. For example, the terminal device collects and generates the datasets. During the data collection, the terminal device collects a large amount of data. As the terminal device moves, the terminal device collects a plurality of datasets under different network side conditions and / or terminal side conditions, thereby forming a mixed dataset. For another example, the network device collects a plurality of datasets from a plurality of terminal devices, each terminal device having experienced at least one network side condition and / or terminal side condition, and the plurality of datasets form a mixed dataset. The prediction model trained based on the mixed dataset has the technical advantage of strong generalization, i.e., only acceptable performance loss for each network side condition and / or terminal side condition, and is applicable to each network side condition and / or terminal side condition corresponding to each dataset in the mixed dataset.

[0063] In some embodiments, when the prediction model is trained based on the mixed dataset, the identification information associated with the prediction model is newly allocated identification information, and the newly allocated identification information is different from the identification information associated with each of the plurality of datasets in the mixed dataset. For example, the mixed dataset comprises dataset 1 and dataset 2. Assume that the identification information associated with dataset 1 is ID 1, and the identification information associated with dataset 2 is ID 2. When the prediction model is trained based on the mixed dataset, the identification information associated with the prediction model can be a newly allocated identification information, such as ID 3. The prediction model corresponding to ID 3 can be applicable to the network side condition and / or terminal side condition corresponding to ID 1 and the network side condition and / or terminal side condition corresponding to ID 2 in the inference stage, which is the generalization described above.

[0064] In some embodiments, when the prediction model is trained based on the mixed dataset, the identification information associated with the prediction model comprises the identification information associated with each of the plurality of datasets in the mixed dataset. For example, the mixed dataset comprises dataset 1 and dataset 2. Assume that the identification information associated with dataset 1 is ID 1, and the identification information associated with dataset 2 is ID 2. When the prediction model is trained based on the mixed dataset, the identification information associated with the prediction model can be ID 1 and ID 2. In the inference stage, the prediction model can be applicable to the network side condition and / or terminal side condition corresponding to ID 1 and the network side condition and / or terminal side condition corresponding to ID 2, which is the generalization described above.

[0065] The following describes the first information between the terminal device and the network device.

[0066] Case 1

[0067] In some embodiments, the first information between the terminal device and the network device is synchronized, including: the network device sends the first information to the terminal device, and the terminal device receives the first information sent by the network device, and the first information is used to associate the conditions of the network device sending the reference signal.

[0068] In case 1, the network device sends the first information to the terminal device, and tells the terminal device the network side conditions. In case 1, the terminal device is the subject of collecting and generating the data set. Taking the CSI-RS as an example, the terminal device measures the CSI-RS resource in the periodic or semi-persistent or non-periodic CSI-RS resource set, and obtains the downlink channel CSI between the terminal device and the network device according to the traditional CSI feedback method. As described above, the CSI can be an equivalent channel matrix H, or a predefined singular value vector / eigen vector, i.e. PMI (Precoding Matrix Indicator), obtained by eigenvalue decomposition / singular value decomposition of the channel matrix H. From the perspective of the terminal device, the network side conditions are implicitly represented for the measured CSI-RS resource. However, the 3GPP protocol often cannot directly expose the NW side implementation, but uses an implicit way to ensure the consistency of the network side conditions in the training and inference stages. The network device identifies a complete set of network side conditions through the first information (including identification information, such as association ID).

[0069] In some embodiments, in the training stage of the prediction model, the network device sends the first information to the terminal device, and the terminal device receives the first information sent by the network device; and / or, in the inference stage of the prediction model, the network device sends the first information to the terminal device, and the terminal device receives the first information sent by the network device. In the training stage and the inference stage of the model, the network device can tell the terminal device the network side conditions used by the network device through the first information (including identification information).

[0070] In some embodiments, the first information is carried in RRC (Radio Resource Control) signaling.

[0071] In some embodiments, the RRC signaling is also used to carry resource configuration information of the reference signal, i.e., the first information is transmitted by the RRC signaling used to carry the resource configuration information of the reference signal. When the network device sends the RRC signaling to configure the resource configuration information of the reference signal, the network device can further carry the first information in the RRC signaling to inform the terminal device of the network-side condition adopted by the network device. The resource configuration information of the reference signal is used to configure the transmission resource of the reference signal. For example, the first information can be carried in the following IE (information element): CSI-ResourceConfig, NZP-CSI-RS-ResourceSet.

[0072] In some embodiments, the RRC signaling is also used to carry reporting configuration information of the measurement result of the reference signal, i.e., the first information is transmitted by the RRC signaling used to carry the reporting configuration information of the measurement result of the reference signal. When the network device sends the RRC signaling to configure the reporting configuration information of the measurement result of the reference signal, the network device can further carry the first information in the RRC signaling to inform the terminal device of the network-side condition adopted by the network device. The reporting configuration information of the measurement result of the reference signal is used to configure the transmission resource of the measurement result of the reference signal. For example, the first information can be carried in the following IE: CSI-ReportConfig, CSI-AssociatedReportConfigInfo.

[0073] In some embodiments, the first information is carried in a MAC CE (Media Access Control Control Element), which helps to reduce the delay compared with carrying the first information by using the RRC signaling.

[0074] In some embodiments, the method further includes: the terminal device sends second information to the network device, and the network device receives the second information sent by the terminal device, the second information being used to determine one or more prediction models supported or applicable by the terminal device. After the terminal device completes the collection and generation of the data set, the terminal device can train the prediction model by using the data set, and after the model training is completed, the terminal device can report the supported or applicable prediction model to the network device. By reporting the second information, the network device can perform subsequent LCM (Life Cycle Management) operations on the prediction model, such as activating the prediction model to make the prediction model on the terminal device side enter an inference stage.

[0075] In some embodiments, the second information comprises identification information associated with one or more prediction models supported or available by the terminal device. The identification information associated with the prediction model can be obtained by using the method introduced above, regardless of whether the prediction model is trained by using a single data set or a mixed data set. When reporting the prediction models supported or available by the terminal device to the network device, the terminal device can report the identification information associated with the prediction models supported or available by the terminal device to the network device.

[0076] It should be understood that, in case 1, the network device sends the first information to the terminal device, and tells the terminal device about the network-side condition. For the terminal-side condition, the terminal device naturally knows / understands the terminal-side condition when collecting the training data. Specifically, in the training phase, for different network-side conditions associated with different identification information, the terminal device has the corresponding terminal-side condition. In the inference phase, the network device instructs the terminal device about the identification information to instruct the corresponding prediction model, and the terminal device naturally should also use the identification information to collect the corresponding terminal-side condition when collecting the data. Here, no additional signaling is needed to support, but should be left to the implementation of the terminal device to complete.

[0077] Case 2

[0078] In some embodiments, the terminal device and the network device synchronize the first information, comprising: the terminal device sends the first information to the network device, and the network device receives the first information sent by the terminal device, and the first information is used to associate the condition in which the terminal device receives the reference signal.

[0079] In case 2, the terminal device sends the first information to the network device, and tells the network device about the terminal-side condition. In case 2, the network device is the main body of collecting and generating the data set. Taking the CSI-RS as an example, the terminal device measures the CSI-RS resource in the periodic or semi-persistent or non-periodic CSI-RS resource set, and obtains the downlink channel CSI between the terminal device and the network device according to the traditional CSI feedback method. As described above, the CSI can be an equivalent channel matrix H, or a predefined singular value vector / eigen vector, i.e., PMI, obtained by eigenvalue decomposition / singular value decomposition of the channel matrix H. The terminal device needs to feed back the time-domain CSI to the network device as a data set, which contains the historical measurement CSI as the input of the model, and the CSI at the future time as the label of the model.

[0080] In the data collection process, the terminal device inevitably uses terminal-side conditions. For a complete set of samples collected under terminal-side conditions, the terminal device labels them by means of first information (including identification information such as association ID). And in the process of reporting the data set, the above-mentioned identification information is reported to the network device. So that the network device can distinguish the data set corresponding to different terminal-side conditions, so as to combine the data set of the same terminal-side condition or mix the data set of different terminal-side conditions in the subsequent model training process.

[0081] In some embodiments, in the training phase of the prediction model, the terminal device sends first information to the network device, and the network device receives the first information sent by the terminal device; and / or, in the inference phase of the prediction model, the terminal device sends first information to the network device, and the network device receives the first information sent by the terminal device. In the training phase and the inference phase of the model, the terminal device can tell the network device the terminal-side conditions used by the terminal device through the first information (including identification information).

[0082] In some embodiments, the first information and the measurement result of the reference signal are in the same signaling, thereby helping to save signaling overhead. In some embodiments, the first information and the measurement result of the reference signal are in different signaling, so that the information reporting flexibility is higher.

[0083] In some embodiments, the method further comprises: the network device sending third information to the terminal device, and the terminal device receiving the third information sent by the network device, the third information being used to determine one or more prediction models provided by the network device to the terminal device. After training one or more prediction models, the network device can provide the trained prediction model to the terminal device by means of model transmission / distribution.

[0084] In some embodiments, the third information includes identification information associated with one or more prediction models provided by the network device to the terminal device. Whether the prediction model is trained by a single data set or a mixed data set, the identification information associated with the prediction model can be obtained by the method introduced above. When the network device provides the prediction model to the terminal device, the identification information associated with the prediction model can be provided to the terminal device. In order to identify the terminal-side condition and / or network-side condition corresponding to a specific prediction model, the identification information (such as association ID) is used to mark. After receiving the prediction model and the corresponding identification information, the terminal device uses the terminal-side condition corresponding to the identification information. For the same identification information in the training phase and the inference phase, the network device considers that the terminal-side condition is consistent in the model training phase and the inference phase.

[0085] It should be understood that in case 2, the terminal device sends the first information to the network device, and tells the network device the terminal side condition. For the network side condition, when the network device collects the training data, the network device naturally knows / understands the network side condition. Specifically, in the training phase, the network device configures the terminal device to measure the reference signal (characterizing the network side condition) and feeds back the measurement result (i.e., CSI) to the network device. In this process, the terminal device does not need to know the network side condition, but only assists the network device to complete the collection of training data. Subsequently, the network device completes the training of the model, and delivers / distributes one or more prediction models to the terminal device. In the process of delivering / distributing the model, in order to mark the model, the network device can configure an identification information for each prediction model for model management. In the inference phase, since the activation / deactivation and other operations of the model are dominated by the network device, it is believed that the network device will select the corresponding model for inference at the terminal side according to the network side condition. Therefore, no additional signaling support is required.

[0086] Next, a method for maintaining consistency of the network side condition and / or the terminal side condition between the training phase and the inference phase based on model monitoring is introduced. Considering that the prediction model is deployed at the terminal device side, the terminal device can be used to complete the function of this model monitoring.

[0087] In some embodiments, the terminal device compares the first channel state information and the second channel state information to obtain a comparison result, wherein the first channel state information is the channel state information obtained by the prediction model, and the second channel state information is the channel state information actually measured by the terminal device. In the case where the comparison result meets a condition, the terminal device sends fourth information to the network device, and the fourth information is used to instruct the network device to adjust the condition of sending the reference signal.

[0088] In some embodiments, the comparison result is used to reflect the similarity between the first channel state information and the second channel state information, and the above-mentioned condition includes that the similarity is less than or equal to a threshold value. Exemplarily, the similarity can be measured by indicators such as SGCS (Square Generalized Cosine Similarity), MSE (Mean Square Error), etc. The threshold value can be specified by a standard, or predefined, or configured by the network device, or dependent on the implementation of the terminal device.

[0089] For the consistency judgment of the network side condition, the terminal device can compare the real CSI measurement result with the model predicted CSI result. When the terminal device finds that the similarity index is less than or equal to a certain threshold, it is reasonable to suspect that the consistency of the network side condition is not guaranteed, thereby causing performance degradation. Therefore, the terminal device can send fourth information to the network device, and the network device can adjust the network side condition according to the fourth information. In the above manner, the training phase and the inference phase are maintained based on model monitoring, and the consistency of the network side condition and / or the terminal side condition is maintained.

[0090] In summary, the technical scheme provided by the embodiments of the present application synchronizes the first information between the terminal device and the network device. Since the first information is associated with the network side condition and / or the terminal side condition, by synchronizing the first information between the terminal device and the network device in the training phase and / or the inference phase of the prediction model, the network side condition can be told to the terminal device, or the terminal side condition can be told to the network device, thereby maintaining the consistency of the network side condition and / or the terminal side condition in the training phase and the inference phase of the model.

[0091] It should be noted that the steps performed by the terminal device in the above method embodiments can be implemented separately as a terminal device side information synchronization method, and the steps performed by the network device can be implemented separately as a network device side information synchronization method.

[0092] The following is a device embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0093] Please refer to FIG. 4, which shows a block diagram of an information synchronization device according to an embodiment of the present application. The device has the functions of implementing the method examples performed by the terminal device described above, which can be implemented by hardware or by executing corresponding software by hardware. The device can be the terminal device introduced above, or can be arranged in the terminal device. As shown in FIG. 4, the device 400 can include a transceiver module 410.

[0094] The transceiver module 410 is configured to synchronize first information with a network device, the first information being used to associate a condition of transmitting a reference signal by the network device and / or a condition of receiving the reference signal by a terminal device, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, and the prediction model is used to predict channel state information between the terminal device and the network device.

[0095] In some embodiments, the first information comprises identification information, different identification information being associated with different conditions for the network device to transmit the reference signal, and / or different identification information being associated with different conditions for the terminal device to receive the reference signal.

[0096] In some embodiments, the identification information associated with the prediction model is the same as the identification information associated with the dataset used to train the prediction model.

[0097] In some embodiments, the prediction model is trained based on a mixed dataset, the mixed dataset comprising a plurality of datasets, each dataset being associated with a set of conditions for the network device to transmit the reference signal and / or a set of conditions for the terminal device to receive the reference signal, different datasets being associated with different conditions for the network device to transmit the reference signal and / or different conditions for the terminal device to receive the reference signal. The identification information associated with the prediction model is newly assigned identification information, and the newly assigned identification information is different from the identification information associated with each of the plurality of datasets; or the identification information associated with the prediction model comprises the identification information associated with each of the plurality of datasets.

[0098] In some embodiments, the identification information comprises at least one of: an association ID, a dataset ID, a model ID.

[0099] In some embodiments, the transceiver 410 is configured to receive the first information transmitted by the network device, the first information being used to associate conditions for the network device to transmit the reference signal.

[0100] In some embodiments, the transceiver 410 is configured to receive the first information transmitted by the network device in a training phase of the prediction model, and / or receive the first information transmitted by the network device in an inference phase of the prediction model.

[0101] In some embodiments, the first information is carried in RRC signaling or MAC CE.

[0102] In some embodiments, the RRC signaling is further used to carry resource configuration information of the reference signal, or the RRC signaling is further used to carry reporting configuration information of measurement results of the reference signal.

[0103] In some embodiments, the transceiver 410 is further configured to transmit second information to the network device, the second information being used to determine one or more prediction models supported or available to the terminal device.

[0104] In some embodiments, the second information comprises identification information associated with one or more prediction models supported or available to the terminal device.

[0105] In some embodiments, the transceiver 410 is configured to send, to the network device, the first information, where the first information is used to associate a condition under which the terminal device receives a reference signal.

[0106] In some embodiments, the transceiver 410 is configured to send, to the network device, the first information in a training phase of the prediction model, and / or send, to the network device, the first information in an inference phase of the prediction model.

[0107] In some embodiments, the first information and the measurement result of the reference signal are in a same signaling, or the first information and the measurement result of the reference signal are in different signaling.

[0108] In some embodiments, the transceiver 410 is further configured to receive third information sent by the network device, where the third information is used to determine one or more prediction models provided by the network device to the terminal device.

[0109] In some embodiments, the third information includes identification information respectively associated with the one or more prediction models provided by the network device to the terminal device.

[0110] In some embodiments, the first information is synchronized between the terminal device and the network device, so as to maintain consistency of a condition under which the network device sends a reference signal in the training phase and the inference phase of the prediction model, and / or maintain consistency of a condition under which the terminal device receives a reference signal.

[0111] In some embodiments, as shown in FIG. 4, the apparatus 400 further includes a processing module 420 configured to compare first channel state information and second channel state information to obtain a comparison result, where the first channel state information is channel state information obtained by the prediction model, and the second channel state information is channel state information actually measured by the terminal device.

[0112] The transceiver 410 is further configured to send, to the network device, fourth information in a case where the comparison result satisfies a condition, where the fourth information is used to instruct the network device to adjust a condition under which the network device sends a reference signal.

[0113] In some embodiments, the comparison result is used to reflect a similarity between the first channel state information and the second channel state information, and the condition includes that the similarity is less than or equal to a threshold.

[0114] Please refer to FIG. 5, which shows a block diagram of an information synchronization apparatus according to another embodiment of the present application. The apparatus has the functions of the method examples performed by the network device described above, which can be implemented by hardware or by corresponding software executed by hardware. The apparatus can be the network device described above or can be arranged in the network device. As shown in FIG. 5, the apparatus 500 can include a transceiver module 510.

[0115] The transceiver module 510 is configured to synchronize first information with a terminal device, the first information being used to associate a condition for a network device to transmit a reference signal and / or a condition for the terminal device to receive the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, and the prediction model is used to predict channel state information between the terminal device and the network device.

[0116] In some embodiments, the first information includes identification information, different identification information being associated with different conditions for the network device to transmit the reference signal, and / or different identification information being associated with different conditions for the terminal device to receive the reference signal.

[0117] In some embodiments, the identification information associated with the prediction model is the same as the identification information associated with a data set used to train the prediction model.

[0118] In some embodiments, the prediction model is trained based on a mixed data set, the mixed data set including a plurality of data sets, each data set being associated with a group of conditions for the network device to transmit the reference signal and a group of conditions for the terminal device to receive the reference signal, different data sets being associated with different conditions for the network device to transmit the reference signal and / or different conditions for the terminal device to receive the reference signal. The identification information associated with the prediction model is newly assigned identification information, and the newly assigned identification information is different from the identification information associated with each of the plurality of data sets; or the identification information associated with the prediction model includes the identification information associated with each of the plurality of data sets.

[0119] In some embodiments, the identification information includes at least one of an association ID, a data set ID, and a model ID.

[0120] In some embodiments, the transceiver module 510 is configured to send the first information to the terminal device, the first information being used to associate the condition for the network device to transmit the reference signal.

[0121] In some embodiments, the transceiver module 510 is configured to send the first information to the terminal device in a training phase of the prediction model, and / or to send the first information to the terminal device in an inference phase of the prediction model.

[0122] In some embodiments, the first information is carried in RRC signaling or a MAC CE.

[0123] In some embodiments, the RRC signaling is further used to carry resource configuration information of the reference signal, or the RRC signaling is further used to carry reporting configuration information of the measurement result of the reference signal.

[0124] In some embodiments, the transceiver 510 is further configured to receive second information sent by the terminal device, the second information being used to determine one or more prediction models supported or available to the terminal device.

[0125] In some embodiments, the second information includes identification information respectively associated with the one or more prediction models supported or available to the terminal device.

[0126] In some embodiments, the transceiver 510 is configured to receive the first information sent by the terminal device, the first information being used to associate a condition for the terminal device to receive a reference signal.

[0127] In some embodiments, the transceiver 510 is configured to receive the first information sent by the terminal device in a training phase of the prediction model, and / or receive the first information sent by the terminal device in an inference phase of the prediction model.

[0128] In some embodiments, the first information and the measurement result of the reference signal are in the same signaling, or the first information and the measurement result of the reference signal are in different signaling.

[0129] In some embodiments, the transceiver 510 is further configured to send third information to the terminal device, the third information being used to determine one or more prediction models provided by the network device to the terminal device.

[0130] In some embodiments, the third information includes identification information respectively associated with the one or more prediction models provided by the network device to the terminal device.

[0131] In some embodiments, the terminal device and the network device synchronize the first information, so as to maintain consistency of a condition for the network device to send a reference signal in a training phase and an inference phase of the prediction model, and / or maintain consistency of a condition for the terminal device to receive a reference signal.

[0132] In some embodiments, the transceiver module 510 is further configured to receive fourth information sent by the terminal device, the fourth information being used to indicate a condition for the network device to adjust a reference signal transmission. The fourth information is sent in a case where a comparison result of first channel state information and second channel state information meets a condition, the first channel state information being channel state information obtained by the prediction model, and the second channel state information being channel state information actually measured by the terminal device.

[0133] In some embodiments, the comparison result is used to reflect a similarity between the first channel state information and the second channel state information, and the condition includes that the similarity is less than or equal to a threshold.

[0134] It should be noted that the apparatus provided by the above embodiments is only used as an example to divide the above various functional modules in achieving its functions. In actual applications, the above functions can be completed by different functional modules according to actual needs, that is, the content structure of the device is divided into different functional modules to complete all or part of the above described functions.

[0135] As to the apparatus in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and will not be described here in detail.

[0136] Please refer to FIG. 6, which shows a structural schematic diagram of a communication device provided by an embodiment of the present application. The communication device can be the terminal device or the network device introduced above. The communication device 600 can include a processor 601, a transceiver 602, and a memory 603. The transceiver 602 is configured to implement a sending or receiving function, such as the function of the transceiver module described above, and the processor 601 can be configured to implement other processing functions or control the sending and / or receiving, such as the function of the processing module described above.

[0137] The processor 601 includes one or more than one processing core. The processor 601 performs various functional applications and information processing by running software programs and modules.

[0138] The transceiver 602 can include a receiver and a transmitter, which can be implemented as the same wireless communication component, and the wireless communication component can include a wireless communication chip and a radio frequency antenna.

[0139] The memory 603 can be connected to the processor 601 and the transceiver 602.

[0140] The memory 603 can be used to store a computer program executed by the processor, and the processor 601 is configured to execute the computer program to implement various steps in the above method embodiments.

[0141] In some embodiments, in a case that the communication device 600 is a terminal device, the transceiver 620 is configured to synchronize, with a network device, first information used for associating a condition of transmitting, by the network device, a reference signal and / or a condition of receiving, by the terminal device, the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model used for predicting channel state information between the terminal device and the network device.

[0142] In some embodiments, in a case that the communication device 600 is a network device, the transceiver 620 is configured to synchronize, with a terminal device, first information used for associating a condition of transmitting, by the network device, a reference signal and / or a condition of receiving, by the terminal device, the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model used for predicting channel state information between the terminal device and the network device.

[0143] For details not specifically described in the present embodiment, reference can be made to the above embodiments, which will not be repeated here.

[0144] In addition, the memory can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, including but not limited to: magnetic or optical disks, electrically erasable programmable read-only memories, erasable programmable read-only memories, static random access memories, read-only memories, magnetic memories, flash memories, programmable read-only memories.

[0145] The embodiments of the present application also provide a computer readable storage medium, wherein the storage medium stores a computer program. The computer program is used for being executed by a processor to implement the above-mentioned information synchronization method on the terminal device side or the above-mentioned information synchronization method on the network device side. In some embodiments, the computer readable storage medium can include: a ROM (Read-Only Memory), a RAM (Random-Access Memory), a SSD (Solid State Drives) or an optical disc, etc. Wherein, the random access memory can include a ReRAM (Resistance Random Access Memory) and a DRAM (Dynamic Random Access Memory).

[0146] The embodiment of the present application further provides a chip, which comprises a programmable logic circuit and / or program instructions, and when the chip is running, is used for realizing the information synchronization method on the terminal device side or realizing the information synchronization method on the network device side.

[0147] The embodiment of the present application further provides a computer program product, which comprises a computer program stored in a computer readable storage medium, and a processor reads and executes the computer program from the computer readable storage medium, and is used for realizing the information synchronization method on the terminal device side or realizing the information synchronization method on the network device side.

[0148] It should be understood that the "indication" mentioned in the embodiments of the present application can be direct indication, or indirect indication, or can be an indication of an associated relationship. For example, A indicates B, which can mean that B can be obtained directly through A; or it can mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; or it can mean that A and B have an associated relationship.

[0149] In the description of the embodiments of the present application, the term "corresponding" can mean a direct or indirect corresponding relationship between the two, or an associated relationship between the two, or an indication and being indicated, configuration and being configured, etc.

[0150] In some embodiments of the present application, "predefined" can be realized by pre-saving corresponding codes, tables or other means for indicating related information in devices (for example, including terminal devices and APs), and the specific implementation manner of the present application is not limited. For example, pre-defined can mean defined in a protocol.

[0151] In some embodiments of the present application, the "protocol" can refer to a standard protocol in the communication field, which can include LTE protocol, NR protocol and related protocols applied to future communication systems, and the present application is not limited thereto.

[0152] "Multiple" mentioned in the present text refers to two or more than two. "And / or" describes the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after it are in an "or" relationship.

[0153] "Greater than or equal to" mentioned in the present text can mean greater than or equal to, and "less than or equal to" can mean less than or equal to.

[0154] In addition, the step numbers described herein only exemplarily show a possible execution sequence between steps, and in some other embodiments, the above steps can also be executed in a sequence different from the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in a sequence opposite to the illustration, which is not limited in the embodiments of the present application.

[0155] Those skilled in the art can realize that, in one or more examples described above, the functions described in the embodiments of the present application can be implemented in hardware, software, firmware or any combination thereof. When implemented in software, the functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on a computer readable medium. The computer readable medium includes computer storage medium and communication medium, and the communication medium includes any medium that facilitates the transfer of computer programs from one place to another. The storage medium can be any available medium accessible by a general or special purpose computer.

[0156] The above only describes exemplary embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An information synchronization method, characterized by, The method is performed by a terminal device, and the method comprises: synchronizing first information with a network device, the first information being used to associate a condition of the network device sending a reference signal and / or a condition of the terminal device receiving the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

2. The method of claim 1, wherein, The first information comprises identification information, different identification information being associated with different conditions of the network device sending the reference signal, and / or different identification information being associated with different conditions of the terminal device receiving the reference signal.

3. The method of claim 2, wherein, The identification information associated with the prediction model is the same as the identification information associated with a data set used to train the prediction model.

4. The method of claim 2, wherein, The prediction model is trained based on a mixed data set, the mixed data set comprising a plurality of data sets, each data set being associated with a group of conditions of the network device sending the reference signal and / or a group of conditions of the terminal device receiving the reference signal, different data sets being associated with different conditions of the network device sending the reference signal and / or different conditions of the terminal device receiving the reference signal. The identification information associated with the prediction model is newly allocated identification information, and the newly allocated identification information is different from the identification information associated with each of the plurality of data sets. Or, The identification information associated with the prediction model comprises the identification information associated with each of the plurality of data sets.

5. The method according to any one of claims 2 to 4, characterized in that, The identification information comprises at least one of an association identifier (ID), a data set ID, and a model ID.

6. The method according to any one of claims 1 to 5, characterized in that, The synchronizing of the first information with the network device comprises: receiving the first information sent by the network device, the first information being used to associate the condition of the network device sending the reference signal.

7. The method of claim 6, wherein, The receiving of the first information sent by the network device comprises: in a training phase of the prediction model, receiving the first information sent by the network device; and / or in an inference phase of the prediction model, receiving the first information sent by the network device. The first information is carried in radio resource control (RRC) signaling or a medium access layer control element (MAC CE).

8. The method according to claim 6 or 7, characterized in that, The RRC signaling is further used to carry resource configuration information of the reference signal, or the RRC signaling is further used to carry reporting configuration information of a measurement result for the reference signal.

9. The method of claim 8, wherein, The method further comprises:

10. The method according to any one of claims 6 to 9, characterized in that, sending second information to the network device, the second information being used to determine one or more prediction models supported or available to the terminal device. The second information comprises identification information associated with each of the one or more prediction models supported or available to the terminal device.

11. The method of claim 10, wherein, The synchronizing of the first information with the network device comprises:

12. The method according to any one of claims 1 to 5, characterized in that, sending the first information to the network device, the first information being used to associate the condition of the terminal device receiving the reference signal. The sending of the first information to the network device comprises:

13. The method of claim 12, wherein, in the training phase of the prediction model, sending the first information to the network device; and / or in the inference phase of the prediction model, sending the first information to the network device. ​ ​ 14. The method of claim 12 or 13, wherein the first information and the measurement result of the reference signal are in a same signaling; or, the first information and the measurement result of the reference signal are in different signalings. The method comprises: receiving third information sent by the network device, the third information being used to determine one or more prediction models provided by the network device to the terminal device.

15. The method according to any one of claims 12 to 14, characterized in that, The third information comprises identification information respectively associated with the one or more prediction models provided by the network device to the terminal device. The first information is synchronized between the terminal device and the network device, used to maintain consistency of conditions of sending reference signals by the network device and / or consistency of conditions of receiving reference signals by the terminal device in a training phase and an inference phase of the prediction model.

16. The method of claim 15, wherein, The method further comprises:

17. The method according to any one of claims 1 to 16, characterized in that, comparing first channel state information and second channel state information to obtain a comparison result, wherein the first channel state information is channel state information obtained by the prediction model, and the second channel state information is channel state information actually measured by the terminal device; 18. The method according to any one of claims 1 to 17, characterized in that, in a case where the comparison result satisfies a condition, sending fourth information to the network device, the fourth information being used to instruct the network device to adjust the conditions of sending reference signals. The comparison result is used to reflect a similarity between the first channel state information and the second channel state information, and the condition comprises that the similarity is less than or equal to a threshold. The method is performed by a network device, and the method comprises:

19. The method of claim 18, wherein, synchronizing first information between the terminal device, the first information being used to associate conditions of sending reference signals by the network device and / or conditions of receiving reference signals by the terminal device, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, and the prediction model is used to predict channel state information between the terminal device and the network device.

20. An information synchronization method, characterized by, The first information comprises identification information, different identification information is associated with different conditions of sending reference signals by the network device and / or different identification information is associated with different conditions of receiving reference signals by the terminal device. The identification information associated with the prediction model is the same as identification information associated with a data set used to train the prediction model.

21. The method of claim 20, wherein, The prediction model is trained based on a mixed data set, the mixed data set comprises a plurality of data sets, each data set is associated with a group of conditions of sending reference signals by the network device and a group of conditions of receiving reference signals by the terminal device, and different data sets are associated with different conditions of sending reference signals by the network device and / or different conditions of receiving reference signals by the terminal device.

22. The method of claim 21, wherein, The identification information associated with the prediction model is newly allocated identification information, and the newly allocated identification information is different from identification information respectively associated with the plurality of data sets.

23. The method of claim 21, wherein, Or, The identification information associated with the prediction model comprises identification information respectively associated with the plurality of data sets. The identification information comprises at least one of the following: an association identifier (ID), a data set ID, and a model ID. ​ 24. The method according to any one of claims 21 to 23, characterized in that, ​ 25. The method according to any one of claims 20 to 24, characterized in that, The first information synchronized with the terminal device comprises: The network device sends the first information to the terminal device, and the first information is used to associate a condition of the network device sending a reference signal.

26. The method of claim 25, wherein, The network device sends the first information to the terminal device, and the first information is used to associate a condition of the network device sending a reference signal. In the training phase of the prediction model, the network device sends the first information to the terminal device. In the inference phase of the prediction model, the network device sends the first information to the terminal device. The first information is carried in radio resource control (RRC) signaling or a medium access control (MAC) control element.

27. The method of claim 25 or 26, wherein, The RRC signaling is also used to carry resource configuration information of the reference signal, or the RRC signaling is also used to carry reporting configuration information of a measurement result of the reference signal.

28. The method of claim 27, wherein, The method further comprises:

29. The method according to any one of claims 25 to 28, characterized in that, The network device receives second information sent by the terminal device, and the second information is used to determine one or more prediction models supported or available for the terminal device. The second information comprises identification information associated with the one or more prediction models supported or available for the terminal device.

30. The method of claim 29, wherein, The first information synchronized with the terminal device comprises:

31. The method of any one of claims 20 to 24, wherein, The network device receives the first information sent by the terminal device, and the first information is used to associate a condition of the terminal device receiving a reference signal. The network device receives the first information sent by the terminal device, and the first information is used to associate a condition of the terminal device receiving a reference signal.

32. The method of claim 31, wherein, In the training phase of the prediction model, the network device receives the first information sent by the terminal device. In the inference phase of the prediction model, the network device receives the first information sent by the terminal device.

33. The method of claim 31 or 32, wherein: The first information and the measurement result of the reference signal are in the same signaling; or The first information and the measurement result of the reference signal are in different signaling. The method comprises: The network device sends third information to the terminal device, and the third information is used to determine one or more prediction models provided by the network device to the terminal device.

34. The method of any one of claims 31 to 33, wherein, The third information comprises identification information associated with the one or more prediction models provided by the network device to the terminal device. The first information synchronized between the terminal device and the network device is used to maintain consistency of a condition of the network device sending a reference signal in the training phase and the inference phase of the prediction model, and / or maintain consistency of a condition of the terminal device receiving a reference signal.

35. The method of claim 34, wherein, The method further comprises:

36. The method of any one of claims 20 to 35, wherein, The network device receives fourth information sent by the terminal device, and the fourth information is used to indicate that the network device adjusts a condition of sending a reference signal.

37. The method of any one of claims 20 to 36, wherein, The fourth information is sent in a case where a comparison result of first channel state information and second channel state information meets a condition, the first channel state information is channel state information obtained by the prediction model, and the second channel state information is channel state information actually measured by the terminal device. The comparison result is used to reflect a similarity between the first channel state information and the second channel state information, and the condition comprises that the similarity is less than or equal to a threshold value. The apparatus comprises:

38. The method of claim 37, wherein, ​ 39. An information synchronization apparatus, characterized by comprising: ​ The transceiver module is configured to synchronize first information with a network device, the first information being used to associate a condition for the network device to transmit a reference signal and / or a condition for a terminal device to receive the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

40. An information synchronization apparatus, comprising: The apparatus comprises: The transceiver module is configured to synchronize first information with a terminal device, the first information being used to associate a condition for a network device to transmit a reference signal and / or a condition for the terminal device to receive the reference signal, wherein a measurement result of the terminal device for the reference signal is used as training data or inference data of a prediction model, the prediction model being used to predict channel state information between the terminal device and the network device.

41. A terminal device, comprising: The terminal device comprises a processor and a memory, the memory storing a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 19.

42. A network device, comprising: The network device comprises a processor and a memory, the memory storing a computer program, and the processor executes the computer program to implement the method according to any one of claims 20 to 38.

43. A computer-readable storage medium, comprising: The storage medium stores a computer program, and the computer program is configured to be executed by a processor to implement the method according to any one of claims 1 to 19, or implement the method according to any one of claims 20 to 38.

44. A chip, comprising: The chip comprises programmable logic circuitry and / or program instructions, and when the chip is running, the programmable logic circuitry and / or program instructions are configured to implement the method according to any one of claims 1 to 19, or implement the method according to any one of claims 20 to 38.

45. A computer program product, characterised in that, The computer program product comprises computer instructions stored in a computer readable storage medium, and a processor reads and executes the computer instructions from the computer readable storage medium to implement the method according to any one of claims 1 to 19, or implement the method according to any one of claims 20 to 38.

Images