Data collection method and apparatus

Abstract

The present application relates to the technical field of communications. Provided are a data collection method and apparatus. The method comprises: a second communication device instructing a first communication device to send first information, wherein the first information reflects information of N pieces of first data obtained by means of performing performance monitoring on N inference results of a model. It is equivalent to the first communication device feeding back a model monitoring result to the second communication device, thereby realizing the monitoring of the model by the first communication device and the second communication device.

Description

Data collection method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on March 29, 2024, with application number 202410383617.X and application name "A Data Collection Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a data collection method and device. Background Art

[0004] Models (such as artificial intelligence (AI) or machine learning (ML) models) can be applied to improve communications. For example, a terminal device can use the model to select an appropriate beam to improve communication quality between the terminal device and network equipment. Network equipment can configure the model for the terminal device, meaning the model is deployed within the terminal device. The terminal device can then use the model to improve communication quality with the network device. However, there is currently no solution for monitoring the performance of the model. Summary of the Invention

[0005] The embodiments of the present application provide a data collection method and apparatus for providing a model monitoring mechanism.

[0006] In the first aspect, an embodiment of the present application provides a data collection method. The method is applied to a first communication device, a chip system or other functional modules in the first communication device. Other functional modules may be, for example, software modules (such as programs), hardware modules, or hardware modules running programs, etc., which are not specifically limited. For the sake of ease of description, the following mainly introduces the application to the first communication device as an example. The method includes: receiving first indication information from a second communication device, and sending first information to the second communication device. The first indication information instructs the first communication device to send the first information, and the first information is determined based on N first data, and the N first data are obtained by performance monitoring of N inference results respectively, and N is a positive integer.

[0007] The first indication information indicating the sending of the first information can also be described as the first indication information indicating the reporting of the first information. The first information, for example, indicates (or includes) N first data. Alternatively, the first information indicates statistical information of the N first data. For example, the first information indicates the average value, summation result, variance, maximum value or minimum value of the N first data, etc., which is not specifically limited. The N first data represent the results of monitoring the N inference results of the model, or can be described as the results of monitoring or performance monitoring of the model, so it can be understood that the N first data reflect the monitoring results of the model. One of the first data is, for example, a performance indicator of the model. For example, one of the N first data is determined based on one inference result among the N inference results.

[0008] In an embodiment of the present application, a first communication device can monitor N inference results of a model and obtain N first data. Thus, the first information determined based on the N first data represents the results of model monitoring, providing a mechanism for the first communication device to monitor the performance of the model. Furthermore, under the instruction of the second communication device, the first communication device can feedback the first information determined based on the N first data to the second communication device. In this way, the second communication device can perceive the performance monitoring results of the model and enable the second communication device to monitor the model. Furthermore, when N is greater than 1, it is equivalent to the first communication device feeding back the first information to the second communication device after monitoring the model N times, which helps reduce the number of interactions between the two. Furthermore, because the first information is fed back based on the results of multiple model monitorings, large deviations in the results of a single monitoring are avoided. Therefore, more accurate first information can be fed back, facilitating more accurate monitoring of the model. Furthermore, the value of N can be 1 or greater to meet the needs of different model monitoring scenarios. This means that the method provided in the embodiment of the present application has good applicability.

[0009] In a possible implementation, the method further includes: receiving second indication information from the second communication device. The second indication information indicates the first communication device to generate the first data in a first period, which can be replaced by the description that the second indication information indicates the first communication device to periodically generate the first data. The N inference results are respectively the inference results generated in the N first periods, and the N first periods are the periods for generating the N first data. The N inference results can, for example, be related to the measurement of the reference signal. For example, one of the inference results is determined based on the measurement result of the reference signal and the model, and the N first data are related to the N inference results, then the N first data can be regarded as being related to the measurement of the reference signal.

[0010] In the above embodiment, the first communication device supports the periodic generation of the first data, so that the process of generating the first data can adapt to the scenario of periodic reference signals or supporting semi-periodic reference information, which is beneficial to reducing changes to the first communication device and relatively reducing the resources occupied by the first communication device to generate the first data.

[0011] In one possible implementation, the sum of the durations of N first cycles is less than or equal to the duration of the first monitoring window, wherein the first monitoring window is used to generate M first data, the M first data include N first data, and M is an integer greater than or equal to N.

[0012] In the above embodiment, the first communication device can select N first data from the M first data to generate the first information, thereby increasing the flexibility of the first information. Furthermore, when M is greater than N, some of the M first data may contain data with significant errors. In this case, the first communication device can discard the data with significant errors to obtain N first data. This facilitates the feedback of more accurate first information and improves the accuracy of the monitoring model.

[0013] In one possible implementation, the first information is sent on a first time unit, the first time unit corresponds to a second time unit, the second time unit is a time unit for potentially reporting second data, the second data is the last first data among M first data, and the second time unit is associated with the first period for generating the second data.

[0014] The first time unit and the second time unit may be the same, or the first time unit and the second time unit may satisfy a certain relationship, which is not specifically limited.

[0015] In the above implementation, the first communication device may report the first information after generating the first data within the first monitoring window, so that the first communication device can select more accurate N first data for reporting based on the specific circumstances of the M first data.

[0016] In one possible implementation, the N third time units corresponding to the N reasoning results and / or the N fourth time units corresponding to the N first data are located within the first monitoring window. The N third time units are the time units where the measurement resources corresponding to the N reasoning results are located. Alternatively, the N third time units are the time units where the N reasoning results are generated. Alternatively, the N third time units are the time units where the N reasoning results are potentially reported. The N fourth time units are the time units where the measurement resources corresponding to the N first data are located. Alternatively, the N fourth time units are the time units where the N first data are generated. Alternatively, the N fourth time units are the time units where the N first data are potentially reported.

[0017] The potential reporting time unit can be understood as a time unit that may be used for reporting, that is, if certain information is reported, it is reported in the potential reporting time unit, but during the actual communication process, the information may not be reported due to instructions from the network side or other reasons.

[0018] In the above embodiment, the first monitoring window can be set to be relatively large to cover N second time units and N third time units, so that the first communication device has enough time to monitor the model and report information.

[0019] In a possible implementation, the first indication information further indicates at least one of a first monitoring window, a period of the first monitoring window, or a first time unit for sending the first information. The first time unit is within the first monitoring window.

[0020] In the above-described embodiment, the first indication information can also indicate multiple items, enriching the content of the first indication information. The first indication information also indicates the period of the first monitoring window, eliminating the need to separately indicate multiple monitoring windows. This helps to relatively reduce the number of interactions between the first communication device and the second communication device. The first indication information also indicates the first time unit, facilitating the first communication device to promptly report the first information, thereby increasing the timeliness of model monitoring.

[0021] In a possible implementation, the method further includes: receiving N third indication information from the second communication device, where the N third indication information instruct the first communication device to generate N first data.

[0022] The above implementation can be applied to the scenario of non-periodic reference signals. In this case, the N third indication information can multiplex the information for triggering reference signal measurement, so that no additional interactive signaling between the first communication device and the second communication device is added.

[0023] In one possible implementation, the fourth indication information among the N third indication information instructs the first communication device to send the first information. Optionally, the fourth indication information is the indication information received earliest or latest by the first communication device among the N third indication information, or an indication information configured by the second communication device. The fourth indication information can also be described as triggering the first communication device to send the first information.

[0024] In the above implementation, the fourth indication information may also multiplex the information for triggering reference signal measurement, without adding additional interactive signaling between the first communication device and the second communication device.

[0025] In one possible implementation, the fifth indication information among the N third indication information further indicates at least one of the following: the first communication device stores the first data corresponding to the fifth indication information among the N first data; the first communication device accumulates the first data corresponding to the fifth indication information among the N first data; or the first communication device does not send the first data corresponding to the fifth indication information.

[0026] In the above implementation, more information of the third indication information can be reused so that the first communication device can prepare for determining the first information in a timely manner, which is conducive to improving the timeliness of determining the first information and will not increase the interaction between the first communication device and the second communication device.

[0027] In one possible implementation, before sending the first information, the information sent by the first communication device to the second communication device does not include any first data among the N first data; or, before sending the first information, the first communication device sends third data to the second communication device, and the third data belongs to the N first data.

[0028] In the above embodiment, the first communication device may not only feedback the first information, but also the N first data, thereby reducing the number of interactions between the first communication device and the second communication device. Alternatively, the first communication device may also feedback the third data, so that the second communication device can obtain the monitoring information of the model more timely.

[0029] In one possible implementation, the N inference results correspond to channel state information (CSI) prediction results, and accordingly, the model of the first communication device is used to predict CSI. For example, when the model is used to predict CSI, the input of the model may be a reference signal, and the output of the model is CSI. Alternatively, the N inference results correspond to beam prediction results, and accordingly, the model of the first communication device is used to predict the beam. For example, when the model is used to predict the beam, the input of the model may be a measurement result of a reference signal, and the output of the model is beam information (such as the signal strength of the beam).

[0030] In the second aspect, an embodiment of the present application provides a data collection method. The method is applied to a second communication device, a chip system or other functional modules in the second communication device. Other functional modules may be, for example, software modules (such as programs), hardware modules, or hardware modules running programs, etc., and are not specifically limited to this. For ease of description, the following mainly introduces the application to the second communication device as an example. The method includes: sending a first indication message to a first communication device, and receiving a first message from the first communication device. The first indication message instructs the first communication device to send a first message, the first information is related to N first data, and the N first data reflect the performance monitoring results of N reasoning results respectively, where N is a positive integer.

[0031] In a possible implementation, the method further includes: sending a second indication message to the first communication device, the second indication message instructing the first communication device to generate a first cycle of the first data, the N inference results being the inference results generated within the N first cycles, and the N first cycles being the cycles for generating the N first data.

[0032] In one possible implementation, the sum of the durations of N first cycles is less than or equal to the duration of the first monitoring window, wherein the first monitoring window is used to generate M first data, the M first data include N first data, and M is an integer greater than or equal to N.

[0033] In one possible embodiment, the first information is received on a first time unit, wherein the first time unit corresponds to a second time unit, the second time unit is a time unit for potentially reporting second data, the second data is the last first data among M first data, and the second time unit is associated with a first period for generating the second data.

[0034] In a possible implementation, the first indication information further indicates: a period of the first monitoring window; and / or a first time unit for sending the first information, wherein the first time unit is within the first monitoring window.

[0035] In a possible implementation, the method further includes: sending N third indication information to the first communication device, where the N third indication information instruct the first communication device to generate N first data.

[0036] In a possible implementation, the fourth indication information among the N third indication information instructs the first communication device to send the first information.

[0037] In a possible implementation, the fourth indication information is the indication information received earliest or latest by the first communication device among the N third indication information, or an indication information configured by the second communication device.

[0038] In one possible implementation, the fifth indication information among the N third indication information further indicates at least one of the following: the first communication device stores the first data corresponding to the fifth indication information among the N first data; the first communication device accumulates the first data corresponding to the fifth indication information among the N first data; or the first communication device does not send the first data corresponding to the fifth indication information.

[0039] In one possible implementation, before receiving the first information, the information received by the second communication device from the first communication device does not include any first data among the N first data; or, before receiving the first information, the second communication device sends third data from the first communication device, and the third data belongs to the N first data.

[0040] In one possible implementation, the N inference results correspond to channel state information CSI prediction results; or, the N inference results correspond to beam prediction results.

[0041] In a possible implementation, the first information is related to N first data, including: the first information includes the N first data; or the first information includes statistical information generated based on the N first data.

[0042] In a third aspect, an embodiment of the present application provides a communication device. The communication device may be the first communication device in the first aspect above, or a module (for example, a chip system) configured in the first communication device, or a device having the same function as the first communication device. The communication device includes corresponding means (means) or modules for performing the first aspect or any possible implementation method above. For example, the communication device includes a transceiver module (sometimes also referred to as a transceiver unit). Optionally, the communication device also includes a processing module (sometimes also referred to as a processing unit).

[0043] For example, the transceiver module is used to receive first indication information and send first information.

[0044] In an optional implementation, the communication device is also used to implement any possible implementation of the first aspect above, which will not be listed one by one here.

[0045] In a fourth aspect, an embodiment of the present application provides a communication device. The communication device may be the second communication device in the second aspect above, or a module (for example, a chip system) configured in the second communication device, or a device having the same function as the second communication device. The second communication device includes corresponding means (means) or modules for performing the second aspect above or any possible implementation method. For example, the communication device includes a transceiver module (sometimes also referred to as a transceiver unit). Optionally, the communication device also includes a processing module (sometimes also referred to as a processing unit).

[0046] For example, the transceiver module is used to send the first indication information and receive the first information.

[0047] In an optional implementation, the communication device is also used to implement any possible implementation of the second aspect above, which will not be listed one by one here.

[0048] In a fifth aspect, an embodiment of the present application provides a communication device. The communication device includes a processor and an interface circuit, wherein the interface circuit is configured to receive signals from a communication device other than the communication device and transmit the signals to the processor, or to transmit the signals from the processor to the communication device other than the communication device, and the processor is configured to implement any of the methods described in the first aspect and any possible implementation manner or the second aspect and any possible implementation manner through a logic circuit or executing code instructions.

[0049] In the specific implementation process, the communication device can be a chip, and the processor can be a transistor, a gate circuit, a trigger, and various logic circuits, etc. The embodiment of the present application does not limit the specific implementation method of the processor.

[0050] In one implementation, the communication device may be a wireless communication device, i.e., a computer device that supports wireless communication functions. Specifically, the wireless communication device may be a terminal device such as a smartphone, or a network device such as a wireless access network device (e.g., a base station).

[0051] In another implementation, the communication device may be a component of a wireless communication device, such as an integrated circuit product such as a system chip or a communication chip. The system chip may also be referred to as a system on chip (SoC), or simply an SoC chip. The communication chip may include a baseband processing chip and a radio frequency processing chip. The baseband processing chip is sometimes also referred to as a modem or baseband chip. The radio frequency processing chip is sometimes also referred to as a radio frequency transceiver or radio frequency chip. In a physical implementation, some or all of the chips in the communication chip may be integrated within the SoC chip. For example, the baseband processing chip is integrated into the SoC chip, while the radio frequency processing chip is not integrated with the SoC chip. The interface circuit may be the radio frequency processing chip in the wireless communication device, and the processor may be the baseband processing chip in the wireless communication device. The interface circuit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip or chip system. The processor may also be embodied as a processing circuit or a logic circuit.

[0052] In another embodiment, the communication device may be a chip system, which may be composed of chips or include chips and other discrete devices. The chip system may include, for example, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a CPU, a network processor (NP), a DSP, a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0053] In a sixth aspect, embodiments of the present application provide a communication device. The communication device includes: a processor; when the communication device is in operation, the processor executes the method described in the first aspect and any possible implementation manner, or the second aspect and any possible implementation manner. Optionally, the communication device also includes a memory storing one or more computer programs, and the processor can execute the one or more computer programs to implement the method described in the first aspect and any possible implementation manner, or the second aspect and any possible implementation manner.

[0054] Optionally, the communication device further includes other components, such as an antenna, an input / output module, an interface (such as a communication interface), etc. These components may be hardware, software, or a combination of software and hardware.

[0055] In a seventh aspect, an embodiment of the present application provides a communication system. The communication system includes a first communication device and a second communication device. The first communication device is used to implement the functions of the method described in the first aspect and any possible implementation manner, and the second communication device is used to implement the functions of the method described in the second aspect and any possible implementation manner. Furthermore, the first communication device is, for example, the communication device described in the third aspect or any possible implementation manner, and the second communication device is, for example, the communication device described in the fourth aspect or any possible implementation manner.

[0056] In an eighth aspect, an embodiment of the present application provides a chip system. The chip system includes a processor. Optionally, the chip system may further include an interface (such as a communication interface). The processor may be used to implement the method described in the first aspect and any possible implementation manner or the second aspect and any possible implementation manner. Optionally, the chip system also includes a memory. The memory is used to store computer programs (also referred to as codes, or instructions). The processor is used to call and run the computer program from the memory so that the device equipped with the chip system executes the method described in the first aspect and any possible implementation manner or the second aspect and any possible implementation manner. The implementation method of the chip system can refer to the content of the chip system involved in the foregoing text and will not be listed here.

[0057] In a ninth aspect, embodiments of the present application provide a computer-readable storage medium for storing a computer program or instruction that, when executed, implements the method described in the first aspect and any possible implementation manner or the second aspect and any possible implementation manner.

[0058] In a tenth aspect, embodiments of the present application provide a computer program product that, when executed on a computer, implements any of the methods described in the first aspect and any possible implementation manner or the second aspect and any possible implementation manner.

[0059] In one possible implementation, the computer program product includes a computer program, which, when executed on a computer, enables the computer to execute any method described in the first aspect and any possible implementation or the second aspect and any possible implementation.

[0060] In another possible implementation, the computer program product includes instructions, and when the instructions are executed on a computer, the computer executes any method described in the first aspect and any possible implementation or the second aspect and any possible implementation.

[0061] Regarding the beneficial effects of any technical solution in the above-mentioned second to tenth aspects, reference can be made to the beneficial effects discussion of the corresponding technical solution in the first aspect, and the repeated parts will not be listed here. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a schematic structural diagram of the model;

[0063] Figure 2 is a schematic diagram of a neuron;

[0064] 3 to 6 are schematic diagrams of the architectures of four communication systems applicable to embodiments of the present application;

[0065] FIG7 is a schematic diagram of a data collection method provided in an embodiment of the present application;

[0066] FIG8 is a schematic diagram of a first monitoring window provided in an embodiment of the present application;

[0067] FIG9 is another schematic diagram of the first monitoring window provided in an embodiment of the present application;

[0068] FIG10 is a schematic diagram of a first time unit, a second time unit, and a first monitoring window provided in an embodiment of the present application;

[0069] FIG11 is a schematic diagram of an application model management beam provided in an embodiment of the present application;

[0070] FIG12 is a schematic diagram of another data collection method provided in an embodiment of the present application;

[0071] FIG13 is a schematic diagram of reporting first information provided in an embodiment of the present application;

[0072] Figures 14 and 15 are schematic diagrams of two data collection methods provided in embodiments of the present application;

[0073] 16 to 18 are schematic structural diagrams of three communication devices provided in embodiments of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0075] Below, some of the terms involved in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0076] 1. Artificial intelligence (AI)

[0077] Artificial intelligence is the process of giving machines human intelligence, using computer hardware and software to simulate certain intelligent human behaviors, including machine learning and many other methods.

[0078] 2. Machine learning (ML)

[0079] Machine learning is the process of imbuing machines with human intelligence, applying computer hardware and software to simulate certain human intelligent behaviors. This includes machine learning and many other methods. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0080] Supervised learning involves learning a mapping from samples to labels based on samples and labels, and expressing this mapping using a model. The process of training a model can be considered the process of learning this mapping. For example, in signal detection, a noisy signal can serve as a sample, and the true constellation points corresponding to this signal serve as labels. Machine learning aims to learn the mapping between samples and labels through training, enabling the model to detect signals. During model training, the error between the model's predictions and the labels is used to optimize the model's parameters. After the model is trained, it can be used to predict the label of each new sample. The mappings learned by supervised learning include both linear and nonlinear mappings. Learning tasks can be categorized into classification and regression based on the type of label.

[0081] Unsupervised learning involves using algorithms to discover or learn inherent patterns in samples based on their values. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping from one sample to another. This type of learning is therefore called self-supervised learning. During model training, the error between the model's predictions and the samples is calculated to optimize model parameters. Self-supervised learning can be used in signal compression and decompression recovery applications. Models suitable for self-supervised learning include autoencoders and generative adversarial networks.

[0082] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have clear "correct" labels. Instead, the algorithm interacts with the environment, obtaining reward signals from the environment, and then adjusts its actions to maximize the reward signal value. For example, in downlink power control, a reinforcement learning model adjusts the downlink transmit power of each user based on the overall system throughput fed back by the wireless network, hoping to achieve higher system throughput. The goal of reinforcement learning is also to learn the mapping between environmental states and optimal decision actions. However, because the "correct" labels cannot be obtained in advance, network optimization cannot be achieved by calculating the error between actions and the "correct" labels. Training in reinforcement learning is achieved through iterative interaction with the environment.

[0083] 3. Model

[0084] A model is a form of machine learning, or the purpose of machine learning is to obtain a model that can implement the corresponding function. A model is a specific implementation of one or more functions, representing the mapping relationship between the model's input and output. A model can include one or more parameters. A substructure (or, submodule) of a model can include one or more parameters. For example, f(x) = ax 2+b can be considered a model, where a and b correspond to the model's parameters, which can be obtained through learning and training. The process of training a model can be considered the process of optimizing its parameters. The process of using the model to implement its corresponding functions can be considered the model's inference process. The output of the model during inference can be called the inference result.

[0085] In the field of ML and AI, a model can be understood as an algorithm or system that can make predictions or perform tasks after training and learning based on input data. Models include, for example, ML models, AI models, algorithms, features or functions. The AI ​​model can be at least one of a linear regression model, a logistic regression model, a decision tree model, a support vector machine (SVM), a neural network model, a clustering model, a Bayesian network, a Q learning model, a generative adversarial network, or other machine learning models, without limitation. A neural network model is a mathematical model that imitates the behavioral characteristics of animal neural networks and performs distributed parallel information processing. A neural network model can be, for example, one or more of a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN), without specific limitation.

[0086] Neural networks are a typical model. For example, deep neural networks (DNNs) are a specific implementation of machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, enabling them to learn arbitrary mappings.

[0087] Taking the neural network model as an example, a model may include at least one layer, and the "layer" may include a "network layer". Each "network layer" may contain at least one node, and the "node" may also be called a "neuron". Please refer to Figure 1, which is a structural diagram of the model. Taking the model shown in Figure 1 as an example, there is an input layer, a hidden layer, and an output layer. The circles in Figure 1 represent neurons, and the lines between the circles between the network layers represent connections. Optionally, the model may also include a loss layer, and the loss layer may correspond to a cross entropy loss function, for example. Any layer involved here can be regarded as a network layer. For example, at least one parameter may be included between network layers, and the parameter may be, for example, a weight or an operator, such as a convolution operator, a fully connected operator, etc.

[0088] Neurons in one network layer are connected to neurons in adjacent layers through weights, and each connection can be considered an operation. For example, the connection between the input layer and the hidden layer shown in Figure 1 represents the model's parameters. That is, every neuron in the input layer is connected to every neuron in the hidden layer.

[0089] The following is an example of a neuron, using the neuron diagram shown in Figure 2. As shown in Figure 2, neurons perform a weighted sum operation on their input values, and the weighted summation result generates an output through a nonlinear function. Assume that the input of the neuron is x = [x0,…,x n ], the weight corresponding to the input is d=[d0,…,d n ], the bias of the weighted sum is b, then the output of the neuron

[0090] In a possible implementation, the model is used to predict CSI, i.e., the model's inference result is a CSI prediction result. In this case, the model input is, for example, a reference signal, specifically, a CSI-RS. Alternatively, the model is used to predict beams, i.e., the model's inference result is a beam prediction result. In this case, the model input is, for example, a reference signal measurement result.

[0091] 4. Beam

[0092] A beam can be understood as a spatial filter or spatial parameters. The beam used to send signals can be called a transmit beam, a transmission beam (Tx beam), a spatial domain transmit filter, or spatial transmit parameters (spatial Tx parameters). A transmit beam can also refer to the distribution of signal strength in different directions in space after the signal is transmitted by the antenna. From this perspective, a transmit beam can also be a spatial transmission angle (such as azimuth (also called horizontal angle), zenith angle (also called elevation angle)) or a spatial transmission angle range (such as azimuth center angle and offset, azimuth uncertainty, azimuth protection range, zenith center angle and offset, zenith angle uncertainty, zenith angle protection range), etc. Correspondingly, a beam used to receive signals can be called a reception beam (Rx beam), a spatial domain receive filter, or spatial receive parameters (spatial Rx parameters). The receive beam can also refer to the signal strength distribution of wireless signals received from an antenna in different spatial directions. From this perspective, the receive beam can also be a spatial receive angle (such as azimuth and zenith) or a spatial receive angle range (such as azimuth center angle and offset, azimuth uncertainty, azimuth protection range, zenith center angle and offset, zenith angle uncertainty, and zenith angle protection range).

[0093] Beams can be categorized as wide or narrow. A wide beam refers to a beam with a relatively large radiation range from the transmitting or receiving antenna when transmitting or receiving signals. Wide beams are typically used in applications where signals need to be broadcast to a larger area or for wider coverage. They provide wider coverage, but the signal strength is relatively weaker. A narrow beam refers to a beam with a relatively small radiation range from the transmitting or receiving antenna. Narrow beams are typically used in applications where signals need to be focused on a specific target or area. They provide higher signal strength and greater directionality, but the coverage is relatively shorter.

[0094] 5. Reference signal (RS)

[0095] A reference signal may also be referred to as a pilot signal or pilot, which is a known signal. For example, it may be a known signal provided by a transmitting end to a receiving end for channel estimation, channel detection or data demodulation. Reference signals include synchronization signal blocks (SSB) and channel state information-reference signals (CSI-RS). SSB is a cell broadcast signal, which includes a primary synchronization signal (PSS), a secondary synchronization signal (SSS), a physical broadcast channel (PBCH) and a demodulation reference signal (DMRS). There are many types of reference signals. As the standard continues to evolve, the names of the above reference signals may change, and more reference signals may appear, and there is no specific limitation on this.

[0096] CSI includes at least one of rank indication (RI) information, channel quality indicator (CQI) information, precoding matrix (PMI) or layer 1 reference signal receiver power (L1-RSRP).

[0097] The reference signal includes a periodic reference signal, a semi-periodic reference signal or an aperiodic reference signal. Alternatively, the measurement result of the reference signal reported by the device (such as the terminal device) includes a periodic reporting measurement result, a semi-periodic reporting measurement result or an aperiodic reporting measurement result.

[0098] Among them, a periodic reference signal means that after the signaling (such as radio resource control (RRC)) configures the measurement resources, the device (such as a terminal device) begins to periodically measure and report the measurement results of the reference signal. A semi-periodic reference signal means that after the signaling (such as RRC) configures the measurement resources, a separate signaling (such as downlink control information (DCI)) is required to trigger the periodic measurement and reporting of the reference signal measurement results. An aperiodic reference signal requires a separate signaling trigger from the network side each time the device measures and reports CSI.

[0099] If the reference signal is a CSI-RS, CSI-RS includes periodic CSI-RS, semi-periodic CSI-RS, and aperiodic CSI-RS. The CSI-RS measurement result is CSI. Accordingly, CSI reporting includes periodic CSI (P-CSI), semi-periodic (or semi-static, or semi-persistent) CSI (SP-CSI), and aperiodic CSI (A-CSI).

[0100] 6. Time unit

[0101] A time unit is a time domain resource and may be a slot, symbol, subframe, half-frame, frame, mini-subframe, mini-slot, or transmission occasion (TO), etc., without limitation.

[0102] The first time unit, the second time unit, and the third time unit involved in the embodiments of the present application are used to execute the time domain resources corresponding to the corresponding processes. The units of the first time unit, the second time unit, and the third time unit may be the same or different, and this is not limited. For example, the units of the first time unit, the second time unit, and the third time unit are all symbols.

[0103] 7. First Data

[0104] The first data may also be referred to as monitoring data or other. The first data refers to data obtained by monitoring the inference data of the model. For example, the first data represents (or reflects, or is) at least one performance metric(s) of the model. For example, at least one performance metric includes at least one of the accuracy, precision or mean square error of the model. Accordingly, the first data includes at least one of the accuracy, precision standard deviation, cumulative distribution function (CDF), probability density function (PDF) or mean square error of the model, without specific limitation. Optionally, the first data is obtained by monitoring (or performance monitoring) the inference result of the model. For example, the first data is determined based on the error between the inference result of the model and the label or ground-truth corresponding to the inference result.

[0105] 8. Monitoring Window

[0106] A monitoring window is a time window used to monitor a model or its inference results. In other words, the model is monitored within the monitoring window and not outside it. A monitoring window is essentially a time window or time period. The length (or size) of a monitoring window can be arbitrary; for example, a monitoring window can include one or more symbols or one or more time slots.

[0107] Optionally, the monitoring window may occur periodically. For example, a monitoring window may have a duration of 1 hour (i.e., 3600 seconds), a monitoring window period of 2 minutes, and the first monitoring window may be from 13:00 to 14:00. The second monitoring window may be from 14:02 to 15:02, and so on.

[0108] The first monitoring window involved in the embodiment of the present application is an example of a monitoring window. The content of the first monitoring window can also refer to the content of the monitoring window discussed herein.

[0109] In the various embodiments of the present application, the number of nouns, unless otherwise specified, means "singular noun or plural noun", that is, "one or more". "At least one" means one or more, and "plural" means two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. For example, A / B means: A or B. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0110] In the embodiments of the present application, "indication" may include direct indication, indirect indication, explicit indication, and implicit indication. When describing a certain indication information as indicating A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A. In the present application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or an index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, where the other information is associated with the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, it is also possible to indicate specific information by using a pre-agreed (e.g., protocol-specified) order of arrangement of each piece of information, thereby reducing the indication overhead to a certain extent. In addition, the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different.

[0111] In the embodiments of the present application, "sending" and "receiving" indicate the direction of signal transmission. For example, "sending information to XX" can be understood as the destination end of the information is XX, which can include direct sending through the air interface, and also include indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as the source end of the information is YY, which can include direct receiving from YY through the air interface, and also include indirect receiving from YY through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can be carried out between devices, for example, between a network device and a terminal device, or can be carried out within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, a line or an interface.

[0112] To monitor the model, an embodiment of the present application provides a data collection solution. In this solution, a second communication device instructs a first communication device to send (or report) first information. The first communication device then sends the first information to the second communication device. The first information reflects N pieces of first data obtained by performance monitoring N inference results of the model, which is equivalent to the first information reflecting the monitoring results of the model. In this way, the first and second communication devices monitor the model.

[0113] The solutions provided in the embodiments of the present application can be applied to various communication systems including a first communication device and a second communication device. Both the first communication device and the second communication device have communication functions. The communication device can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, or a communication node, etc., without limitation.

[0114] For example, the first communication device is a terminal device, or a chip system (such as a chip) or other functional modules or components in the terminal device. The second communication device is a network device, or a chip system (such as a chip) or other functional modules or components in the network device.

[0115] A terminal device may be a device with wireless transceiver capabilities, and may be a fixed device, a mobile device, a handheld device, a wearable device, an in-vehicle device, or a wireless device built into the above devices (e.g., a communication module or a chip system, etc.). The terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, such as but not limited to the following scenarios: cellular communications, device-to-device communications (D2D), vehicle-to-everything (V2X), machine-to-machine / machine-type communications (M2M / MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, drones, robots, and other scenarios. The terminal device may sometimes be referred to as user equipment (UE), terminal, access station, UE station, remote station, wireless communication device, or user equipment.

[0116] The network equipment includes, for example, access network equipment (or, referred to as access network devices / access network elements), and / or core network equipment (or, referred to as core network devices / core network elements).

[0117] The access network device is a device with wireless transceiver functions, which is used to communicate with the terminal device. The access network device includes but is not limited to the base station (BTS, Node B, eNodeB / eNB, or gNodeB / gNB) in the above-mentioned communication system, the transmission reception point (TRP), the base station of the subsequent evolution of 3GPP, the access node in the wireless fidelity (WiFi) system, the wireless relay node, the wireless backhaul node, the satellite or drone, etc. The base station can be: a macro base station, a micro base station, a pico base station, a small station, a relay station, etc. Multiple base stations can support the same access technology mentioned above, or they can support the networks of different access technologies mentioned above. The base station can include one or more co-sited or non-co-sited transmission and reception points. The access network device can also be a wireless controller, a centralized unit (CU), also known as a convergence unit, and / or a distributed unit (DU) in the cloud radio access network (C(R)AN) scenario. The access network device can also be a server, a wearable device, or an in-vehicle device. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The following description uses a base station as an example of an access network device. The multiple access network devices in the communication system can be base stations of the same type or different types. A base station can communicate with a terminal device or through a relay station. A terminal device can communicate with multiple base stations using different access technologies.

[0118] In the case where the access network device includes a CU and / or a DU. CU and DU can be understood as a division of the access network device from a logical function perspective. CU and DU can be physically separated or deployed together, and this embodiment of the present application does not specifically limit this. A CU can be connected to a DU, or multiple DUs can share a CU. The division of CU and DU can be based on the protocol stack. One possible way is to deploy the RRC, service data adaptation protocol stack (SDAP) and packet data convergence protocol (PDCP) layers in the CU, and the remaining radio link control (RLC) layers, media access control (MAC) layers and physical layers in the DU. The embodiment of the present application does not completely limit the division of CU and DU in accordance with the above-mentioned protocol stack method, and there may be other division methods, such as division according to service type.

[0119] The access network equipment in the embodiments of the present application may also refer to a centralized unit control plane (CU-CP) node or a centralized unit user plane (CU-UP) node, or include CU-CP and CU-UP. Among them, CU-CP is responsible for the control plane functions, mainly including RRC and PDCP-C. PDCP-C is mainly responsible for encryption and decryption, integrity protection, data transmission, etc. of the control plane data. CU-UP is responsible for user plane functions, mainly including SDAP and PDCP-U. Among them, SDAP is mainly responsible for processing the data of the core network and mapping the flow to the bearer. PDCP-U is mainly responsible for encryption and decryption, integrity protection, header compression, sequence number maintenance, data transmission, etc. of the data plane.

[0120] In different systems, CU (including CU-CP or CU-UP) or DU may have different names, but those skilled in the art will understand their meanings. For example, in an open radio access network (O-RAN) system, CU may also be referred to as O-CU (Open CU), DU may also be referred to as O-DU, CU-CP may also be referred to as O-CU-CP, and CU-UP may also be referred to as O-CU-UP.

[0121] The core network device is used to implement at least one of the following functions: mobility management, data processing, session management, policy and billing. The names of the devices that implement core network functions in systems with different access technologies may be different, and this embodiment of the present application is not limited to this. Taking the 5G system as an example, the core network device includes: access and mobility management function (AMF), session management function (SMF), or user plane function (UPF).

[0122] Various communication systems applicable to the embodiments of the present application include long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD) system, fifth generation (5G) system, th Generation, 5G) (such as new radio (NR) system), wireless local area network (WLAN) system, satellite communication system, side link (SL) communication system, future evolved communication system, or a fusion system of multiple systems, etc., without limitation. SL can also be called side communication link, side link, side link, direct link, side link or auxiliary link, etc. SL includes vehicle-to-everything (V2X) communication, etc. V2X communication may include: vehicle-to-vehicle (V2V) communication, vehicle-to-roadside infrastructure (V2I) communication, vehicle-to-pedestrian (V2P) communication, vehicle-to-network (V2N) communication, etc., without specific limitation.

[0123] The following is an example of a schematic diagram of a communication system applicable to the embodiments of the present application, with reference to the accompanying drawings.

[0124] Please refer to Figure 3, which is a schematic diagram of a communication system applicable to embodiments of the present application. As shown in Figure 3, the communication system includes a terminal device and a network device. Figure 3 uses two terminal devices and one network device as an example, but the number of terminal devices and network devices is not actually limited. Any terminal device in Figure 3 can be used as an example of a first communication device, and the network device can be used as an example of a second communication device.

[0125] The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. Optionally, the terminal device can deploy a model, and the network device can monitor the model by interacting with the terminal device. Alternatively, the model can be deployed in another device that communicates with the terminal device. In this way, the network device can also monitor the model by interacting with the terminal device.

[0126] Please refer to Figure 4, which is a schematic diagram of a communication system applicable to an embodiment of the present application. Compared to the communication system shown in Figure 3, the communication system shown in Figure 4 also includes an AI network element. The AI ​​network element is used to perform AI-related operations, such as building a training data set or training an AI model. The terminal device involved in Figure 4 can be used as an example of a first communication device, and the network device can be used as an example of a second communication device.

[0127] For example, a network device may send data related to AI model training to an AI network element, which then constructs a training dataset and trains the model. For example, data related to model training may include data reported by a terminal device. The AI ​​network element may send the results of AI model-related operations to the network device, which then forwards them to the terminal device. For example, the results of model-related operations may include at least one of the following: a trained model, model evaluation results, or test results.

[0128] Optionally, a portion of the trained AI model can be deployed on a network device, and another portion can be deployed on a terminal device. Alternatively, the trained AI model can be deployed on a network device. Alternatively, the trained AI model can be deployed on a terminal device. Alternatively, the AI ​​network element can be provided as a module in a network device and / or a terminal device, for example, in the network device or terminal device shown in FIG4 .

[0129] Figure 4 illustrates a scenario where an AI network element is directly connected to a network device. In other scenarios, the AI ​​network element can also be connected to a terminal device. Alternatively, the AI ​​network element can be connected to both the network device and the terminal device. Alternatively, the AI ​​network element can be connected to the network device through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0130] FIG3 and FIG4 are simplified schematic diagrams for ease of understanding only. For example, the communication system may further include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in FIG3 and FIG4 .

[0131] The architecture of the access network device is introduced below with reference to the structural diagrams of the communication systems shown in FIG5 and FIG6 .

[0132] As shown in Figure 5, the devices in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are set in these devices, such as core network devices, access network nodes (such as RAN devices), terminal devices or one or more devices in operation, administration and maintenance (OAM). In Figure 5, the number of AI modules set in one device is 1 for example, and there is no actual limit on the number of AI modules set. The access network node can be a separate RAN node or include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be set with one or more AI modules. The terminal device involved in Figure 5 can be used as an example of a first communication device, and one or more devices in the CU or DU core network device or access network node (RAN node) can be used as an example of a second communication device. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are set in the CU-CP and / or CU-UP.

[0133] The AI ​​module is used to implement the corresponding functions. The AI ​​modules deployed in any two devices in one or more devices may be completely identical, partially identical, or completely different, and the embodiments of the present application do not specifically limit this. The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different devices may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0134] An AI module can include one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0135] In one possible implementation, the AI ​​module may be a RAN intelligent controller (RIC), such as a near-real time RIC (near-real time RIC, near-RT RIC) or a non-real time RIC (non-real time RIC, Non-RT RIC). For example, the near-real time RIC is set in a RAN node (e.g., in a CU and / or DU), while the non-real time RIC is set in an OAM, a cloud server, a core network device, or other network devices. The RIC may obtain subsets from multiple terminal devices from a RAN node (e.g., a CU, CU-CP, CU-UP, DU, and / or RU), reorganize them into a training data set, and perform model training based on the training data set.

[0136] For example, the near real-time RIC and the non-real-time RIC may also be separately configured as a network element.

[0137] As shown in Figure 6, the communication system includes an RIC. For example, the RIC can be the AI ​​module shown in Figure 5, which is used to implement AI-related functions. The RIC includes a near-real-time RIC and a non-real-time RIC. The near-real-time RIC and / or the non-real-time RIC can be used as an example of one of the second communication devices. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to latency and has a latency of tens of milliseconds. The non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to latency and has a latency of seconds.

[0138] Near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. Near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminal devices. This information can be used as training data or reasoning data. Optionally, near real-time RIC can deliver the reasoning results to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and DU, and / or between the DU and RU. For example, the near real-time RIC delivers the reasoning results to the DU, and the DU sends it to the RU.

[0139] Non-real-time RIC is also used for model training and reasoning. For example, it is used to train AI models and use the models for reasoning. Non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and DU, and / or between the DU and RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0140] The near-real-time RIC and the non-real-time RIC may also be separately configured as a network element. Optionally, the near-real-time RIC and the non-real-time RIC may also be separately configured as part of other devices. For example, the near-real-time RIC may be configured in a RAN node (e.g., a CU and / or DU), while the non-real-time RIC may be configured in an OAM, a cloud server, a core network device, or other network device.

[0141] The above-mentioned Figures 3 to 6 are examples of the communication system applied in the embodiments of the present application, and do not actually limit the communication system to which the embodiments of the present application can be applied.

[0142] The data collection solution provided in the embodiments of the present application is introduced below with reference to the accompanying drawings.

[0143] In the drawings corresponding to the various embodiments of the present application, the steps represented by dotted lines are all optional steps. In addition, the first communication device involved in the various embodiments of the present application is, for example, the terminal device involved in any one of Figures 3 to 6. The second communication device involved in the various embodiments of the present application is, for example, the network device involved in Figure 3, the network device involved in Figure 4, the CU, DU, core network device, access network node or OAM involved in Figure 5, or the non-real-time RIC, near real-time RIC, CU, DU, CU-CP, RU or access network node involved in Figure 6. In addition, with the continuous evolution of the standard, the name and / or function of the device or node may change, and there is no restriction on this.

[0144] Please refer to Figure 7, which shows a data collection method provided by an embodiment of the present application. The following describes the various steps shown in Figure 7.

[0145] S701: A second communication device sends first indication information to a first communication device. Correspondingly, the first communication device receives the first indication information from the second communication device.

[0146] Exemplarily, the first indication information may be carried in RRC signaling, DCI, a media access control (MAC) layer control element (CE), or other signaling, without limitation. For example, the first indication information is carried in a CSI report configuration (CSI-ReportConfig) of the RRC signaling.

[0147] The first indication information indicates the content shown in the following A1. Optionally, the first indication information further indicates at least one of the content shown in the following A2 to A9. A1 to A9 are introduced below respectively.

[0148] A1. Sending the first information. That is, the first instruction information instructs sending the first information.

[0149] The first information is related to (or associated with) the N first data, or can be described as being determined based on the N first data. The content of the N first data can refer to the content of the first data discussed above. In one possible implementation, the first information includes the N first data and / or statistical information of the N first data.

[0150] The N first data may be determined by separately performing performance monitoring on the N inference results of the model. For example, each of the N first data may be determined by performing performance monitoring on one of the N inference results of the model. Specifically, for example, each of the N first data is determined based on one of the N inference results and a true value (or label) corresponding to the inference result. Each of the N inference results may include one or more inference results, without specific limitation.

[0151] Any two of the N inference results can be inference results obtained by the model for different inputs. For example, if the first communications device receives reference signal 1, reference signal 2, reference signal 3, and reference signal 4 at t1, t2, t3, and t4, respectively, the first communications device can sequentially determine four inference results based on reference signal 1, reference signal 2, reference signal 3, and reference signal 4. These four inference results can be used as an example of the N inference results.

[0152] The statistical information of the N first data is obtained based on the statistical results of the N first data. For example, the statistical information of the N first data indicates the statistical results of the N first data. The statistical results may be, for example, at least one of the average value of the N first data, the maximum value of the N first data, the sum of the N first data, the average value of the N first data, the standard deviation of the N first data, or the variance of the N first data. Alternatively, the statistical information of the N first data indicates whether the statistical results of the N first data meet or fail to meet the standards. Meeting the standards, for example, means that the statistical result is greater than or equal to a first threshold value, and failing to meet the standards, for example, means that the statistical result is less than the first threshold value. Alternatively, meeting the standards, for example, means that the statistical result is less than the first threshold value, and failing to meet the standards, for example, means that the statistical result is greater than or equal to the first threshold value. Alternatively, meeting the standards, for example, means that the proportion of first data greater than or equal to the first threshold value in the N first data is greater than or equal to a first ratio, and failing to meet the standards, for example, means that the proportion of first data less than the first threshold value in the N first data is less than the first ratio.

[0153] The following introduces the manner in which the first indication information indicates sending the first information.

[0154] In a first embodiment, the first indication information includes a first field. The first field is a field specifically used to indicate whether to send the first information or not.

[0155] For example, the value of the first field is a first value, indicating that the first information is sent. The value of the first field is a second value, indicating that the first information is not sent. One of the first value and the second value is 1, and the other of the first value and the second value is 0.

[0156] In the second mode, the first information includes at least one of the following information A1-1 to A1-5, and the at least one of the information A1-1 to A1-5 is used to instruct the sending of the first information. The at least one of the information A1-1 to A1-5 is introduced below.

[0157] A1-1. The first information includes information about the number of N first data items. The number of N first data items is used to indicate that the first information is being sent. The number of N first data items is N.

[0158] A1-2. The first information includes information about the number of N groups of reference signal resources corresponding to the N first data. The number of N groups of reference signal resources is used to indicate the transmission of the first information. The number of N groups of reference signal resources corresponding to the N first data is also N. One group of reference signal resources in the N groups of reference signal resources is used to determine one inference result among the N inference results, or can be described as being used to determine one first data item in the N first data items. One group of reference signal resources in the N groups of reference signal resources is used to transmit one reference signal. The one group of reference signal resources, for example, includes time-frequency resources for transmitting one reference signal.

[0159] A1-3. The first information includes a period for sending (or reporting) the first information. For ease of description, the period for sending the first information may be referred to as a second period hereinafter. The second period is used to indicate sending the first information.

[0160] The second period is, for example, related to a reference signal (e.g., CSI-RS) configuration period. The reference signal configuration period can be understood as a reference signal transmission period, for example, the time interval between two reference signal transmissions. For example, the second period is Q reference signal configuration periods, where Q is a positive integer. When the first indication information is RRC, the CSI reporting period offset (CSI-ReportPeriodicityAndOffset) in the first indication information can be used to indicate the second period.

[0161] For example, the length of the second period can be any one of 4 slots (i.e., 0.5 milliseconds (ms)) to 320 slots (i.e., 40 ms), without specific limitation. Alternatively, if the reference signal configuration period is 20 ms, the second period can be 8 reference signal configuration periods, i.e., 160 ms.

[0162] Optionally, the length of the second period is less than or equal to the length of the first monitoring window. The first monitoring window can be understood as a time window for monitoring the model or the inference results of the model. For example, the second period is 160ms and the length of the first monitoring window is 3600s.

[0163] A1-4. The first information includes information about the number of N inference data. The number of N inference data is used to indicate that the first information is sent. The number of N inference data is N.

[0164] A1-5. The first information includes a reference signal measurement count. The measurement count is used to indicate that the first information is sent. The measurement count is N.

[0165] The first instruction information may also indicate the sending of the first information by at least one of the information in A1-1 to A1-5. In addition, the first instruction information may also indicate information other than the at least one of the information in A1-1 to A1-5. In other words, part of the information in A1-1 to A1-5 is used to indicate the sending of the first information.

[0166] A2. First monitoring window, that is, the first indication information also indicates the first monitoring window.

[0167] Exemplarily, the first monitoring window is used to generate M first data, or it can be described as all M first data are generated within the first monitoring window, or it can be described as the first monitoring window is used to monitor the model or M inference results to obtain M first data, or it can be described as the first monitoring window is used to instruct to monitor the model M times, etc., or it can be described as M first data can be generated within the first monitoring window. The M first data can be N first data, that is, M is equal to N, or the M first data include N first data, that is, M is an integer greater than N.

[0168] In one possible implementation, the first indication information indicates at least one of the start (or beginning) time, length, or end (or ending) time of the first monitoring window. When the first indication information indicates one of the start time, length, or ending time of the first monitoring window, the other of the start time, length, or ending time of the first monitoring window may be preconfigured or predefined in the first communication device. The following examples, in conjunction with B1 or B2, illustrate the start and end times of the first monitoring window.

[0169] B1. The starting time of the first monitoring window is the time when the first communication device receives the first indication information, and / or the ending time of the first monitoring window is the time when the first communication device receives the first indication information plus the time corresponding to the length of the first monitoring window, that is, the starting time of the first monitoring window plus the time corresponding to the length of the first monitoring window.

[0170] B2. The starting time of the first monitoring window is the time corresponding to the time when the first communication device receives the first indication information plus the first time offset (or offset value), and / or the end time of the first monitoring window is the time corresponding to the time when the first communication device receives the first indication information plus the first time offset and the length of the first monitoring window, that is, the starting time of the first monitoring window plus the time corresponding to the length of the first monitoring window.

[0171] For example, please refer to Figure 8, which is a schematic diagram of the first monitoring window provided in an embodiment of the present application. Figure 8 takes the start time of receiving the first indication information as t1 and the end time of receiving the first indication information as t2 as an example.

[0172] As shown in (1) of FIG8 , the start time of the first monitoring window is the end time of receiving the first indication information (i.e., t2), and the length of the first monitoring window is equal to the time interval between t2 and t3. The first monitoring window is the time period from t2 to t3. Specifically, the start time of the first monitoring window is t2, and the end time is t3.

[0173] As shown in (2) of FIG8 , the start time of the first monitoring window is the end time of receiving the first indication information (i.e., t2), the first time offset is equal to the time interval between t2 and t3, and the length of the first monitoring window is the time interval between t3 and t4. The first monitoring window is the time period from t2 to t4. Specifically, the start time of the first monitoring window is t2, and the end time is t4.

[0174] In another possible implementation, the first indication information indicates at least one of the start time unit, length, or end time unit of the first monitoring window. Optionally, the start time of the first monitoring window is, for example, any time within the start time unit, such as the start time, an intermediate time, or the end time of the start time unit. Similarly, the end time of the first monitoring window is, for example, any time within the end time unit, such as the start time, an intermediate time, or the end time. The following examples, combined with those shown in C1, C2, or C3, illustrate the start time unit and end time unit of the first monitoring window.

[0175] C1. The starting time unit of the first monitoring window is the time unit when the first communication device receives the first indication information, and / or the ending time unit of the first monitoring window is the time unit when the first communication device receives the first indication information plus the time unit corresponding to the length of the first monitoring window, that is, the starting time unit of the first monitoring window plus the time unit corresponding to the length of the first monitoring window.

[0176] The time unit in which the first communication device receives the first indication information may be the time unit corresponding to when the first communication device starts to receive the first indication information, or may be described as the time unit in which the first communication device starts to receive the first indication information, or may be the time unit corresponding to when the first communication device stops receiving the first indication information, or may be described as the time unit in which the first communication device stops receiving the first indication information.

[0177] C2. The starting time unit of the first monitoring window is the time unit corresponding to the time unit at which the first communication device receives the first indication information plus the first time offset, and / or the ending time unit of the first monitoring window is the time unit corresponding to the time unit at which the first communication device receives the first indication information plus the first time offset and the length of the first monitoring window, that is, the time unit corresponding to the starting time unit of the first monitoring window plus the length of the first monitoring window. For example, if the time unit is a symbol, and the time unit at which the first communication device receives the first indication information is symbol 0, then the starting time unit of the first monitoring window is symbol 1.

[0178] For example, please refer to Figure 9, which is a schematic diagram of the first monitoring window provided in an embodiment of the present application. Figure 9 takes the start time of receiving the first indication information as t1, the end time of receiving the first indication information as t2, the unit of the time unit as symbol, and the time unit where t2 is located as symbol 1 as an example.

[0179] As shown in (1) of FIG9 , the starting time unit of the first monitoring window is the time unit (i.e., symbol 1) at which the end time t2 of receiving the first indication information is located, and the length of the first monitoring window is 5 symbols. The first monitoring window is the time period from symbol 1 to symbol 5, wherein the starting time unit of the first monitoring window is symbol 1 and the ending time unit is symbol 5.

[0180] As shown in (2) of FIG9 , taking the case where the starting time unit of the first monitoring window is the time unit (i.e., symbol 1) at which the end time t2 of receiving the first indication information is located, the first time offset is 2 time units, and the length of the first monitoring window is 7 symbols, the first monitoring window is the time period from symbol 4 to symbol 10, wherein the starting time unit of the first monitoring window is symbol 4 and the ending time unit is symbol 10.

[0181] C3. The start time unit of the first monitoring window is the Sth time unit after the time unit in which the first communications device receives the first indication information, and / or the end time unit of the first monitoring window is the Sth time unit after the time unit in which the first communications device receives the first indication information plus the time unit corresponding to the length of the first monitoring window. S is a positive integer.

[0182] In one possible design, the first monitoring window includes N third time units corresponding to N reasoning results. Or it can be described as N third time units being located within the first monitoring window. The N third time units are the time units where the measurement resources corresponding to the N reasoning results are located. Or, the N third time units are the time units where the N reasoning results are generated. Or, the N third time units are the time units where the N reasoning results are potentially reported. The time unit for potential reporting can be understood as a time unit that may be used for reporting, that is, if a certain information is reported, the information is reported in the potential reporting time unit, but in the actual communication process, the information may not be reported due to instructions from the network side or other reasons.

[0183] For example, the starting time unit of the third time unit corresponding to one of the N inference results may be the time unit for receiving the first reference signal. The first reference signal is a reference signal received by the first communication device corresponding to the one inference result, and the time unit for receiving the first reference signal may be a time unit at any moment in the process of receiving the first reference signal, and any moment in the process of receiving the first reference signal may be, for example, the moment of starting to receive the first reference signal, or the moment of ending to receive the first reference signal. Alternatively, the starting time unit of the third time unit corresponding to the one inference result may be H time units after the time unit of receiving the first reference signal, where H is a positive integer. Alternatively, the starting time unit of the third time unit corresponding to the one inference result may be the time unit for receiving the first reference signal plus a third offset.

[0184] The N third time units may be periodically distributed, i.e., the time intervals between the start times of any two adjacent time units in the N third time units are equal. Alternatively, the N third time units may be aperiodically distributed. The N third time units may be preconfigured or predefined in the first communication device, or indicated to the first communication device by the second communication device via first indication information or other indication information, and this is not specifically limited.

[0185] In one possible design, the first monitoring window includes N fourth time units corresponding to the N first data. Alternatively, the N fourth time units can be described as being within the first monitoring window. The N fourth time units are time units in which the measurement resources corresponding to the N first data are located. Alternatively, the N fourth time units are time units in which the N first data are generated. Alternatively, the N fourth time units are potential reporting time units for the N first data.

[0186] In one possible implementation, the first communication device may generate N first data in N fourth time units respectively, or the time units where the measurement resources corresponding to the N first data are located are N fourth time units. The N fourth time units may be preconfigured or predefined in the first communication device, or the N fourth time units may be indicated by indication information of the second communication device (such as first indication information or other indication information), which is not limited. Optionally, the N fourth time units are located within the first monitoring window. Optionally, the fourth time unit corresponding to one first data among the N first data includes the third time unit corresponding to the inference result corresponding to the first data.

[0187] For example, the starting time unit of the fourth time unit corresponding to one of the N first data may be the time unit for receiving the first reference signal. The contents of the first reference signal and the time unit for receiving the first reference signal may refer to the contents of the first reference signal and the time unit for receiving the first reference signal discussed above, respectively. Alternatively, the starting time unit of the fourth time unit corresponding to the one first data may be F time units after the time unit for receiving the first reference signal, where F is a positive integer. Alternatively, the starting time unit of the fourth time unit corresponding to the one first data may be the time unit for receiving the first reference signal plus a fourth offset. The N fourth time units may be periodically distributed or non-periodically distributed. The first communication device may obtain the contents of the N fourth time units with reference to the first communication device obtaining the contents of the N third time units discussed above, which will not be listed here.

[0188] A3. The period of the first monitoring window, i.e., the first indication information also indicates the period of the first monitoring window. Alternatively, the first indication information can be described as indicating K periodic monitoring windows, or equivalently, the first indication information indicates K monitoring windows. The K monitoring windows include the first monitoring window, where K is an integer greater than 1.

[0189] A4. A first time unit for sending the first information. That is, the first indication information also indicates the first time unit.

[0190] The first time unit may be within the first monitoring window or not within the first monitoring window, without limitation. Optionally, the first time unit corresponds to the second time unit. For example, the first time unit is the second time unit, or the first time unit is the result of adding the second offset to the first time unit.

[0191] The second time unit is a potential reporting time unit for the second data among the M first data, or can be described as a time unit in which the second data may be reported as the second time unit. The second data can be the last first data among the M first data, or the last first data among the N first data, etc., without limitation. Optionally, the second time unit can be one of the N fourth time units described above, for example, the last time unit among the N fourth time units.

[0192] The second time unit may be the time unit corresponding to the first communications device receiving the sixth indication information, or may be the result of adding a third offset value to the time unit corresponding to the first communications device receiving the sixth indication information. The sixth indication information is used to instruct the first communications device to generate the second data. The third offset value may be, for example, greater than or equal to the duration of time the first communications device generates the second data, or greater than or equal to the latency of the first communications device processing CSI.

[0193] The second time unit or the first time unit may be indicated by the second communications device to the first communications device via other information (e.g., the seventh indication information). The seventh indication information is carried in DCI or RRC. For example, the report slot configuration (reportSlotConfig) in the RRC indicates the second time unit or the second offset value. The seventh indication information may be applicable to aperiodic reference signals or semi-periodic reference signals when the DCI is in use. The seventh indication information may be applicable to periodic reference signals when carried in RRC.

[0194] In another possible implementation corresponding to A4, the second time unit or the first time unit may also be preconfigured or predefined in the first communication device. In this way, the second communication device does not need to indicate the second time unit or the first time unit to the first communication device.

[0195] For example, please refer to Figure 10, which is a schematic diagram of a first time unit, a second time unit, and a first monitoring window provided in an embodiment of the present application. As shown in Figure 10, the first time window includes the time period shown from t1 to t9. t1, t3, t5, and t7 respectively represent the time when different reference signals are started to be received. t2, t4, t6, and t8 respectively represent the time when the generation of the first data ends. Among them, t2 to t3 represent a second time unit, t4 to t5 represent a second time unit, t6 to t7 represent a second time unit, and t8 to t9 represent a second time unit. t8 to t9 can represent a first time unit, that is, the first communication device reports the first information at t8-t9.

[0196] In the case where the first indication information indicates A1 and A4, it can be described as the first indication information indicating that the first information is sent in the first time unit.

[0197] A5. The first communication device stores N first data. That is, the first instruction information instructs the first communication device to store N first data.

[0198] Exemplarily, after calculating any first data among the N first data, the first communication device stores the first data so as to facilitate subsequent calculation using the first data.

[0199] A6. The first communication device accumulates N first data. That is, the first instruction information instructs the first communication device to accumulate N first data.

[0200] Exemplarily, the first information is statistical information of N first data. After the first communication device obtains the first data, it can accumulate the obtained first data so as to quickly obtain the first information later.

[0201] A7. The first communication device does not send N first data. That is, the first indication information instructs the first communication device not to send N first data. Alternatively, in another possible implementation, the first indication information instructs the first communication device to send N first data.

[0202] A8. N groups of reference signal resources. That is, the first indication information further indicates N groups of reference signal resources. The contents of the N groups of reference signal resources can refer to the contents of the N groups of reference signal resources discussed above, and the repeated parts are not listed again.

[0203] In one possible implementation, before the second communication device sends a reference signal (e.g., referred to as a first reference signal) to the first communication device based on a set of reference signal resources, the second communication device may further send third indication information to the first communication device. The third indication information instructs the first communication device to generate the first data. The third indication information may be, for example, a DCI or a MAC CE, and is not specifically limited thereto.

[0204] By analogy, the second communication device may cumulatively send N third indication information to the first communication device. This optional implementation manner may be applicable to the case of A-CSI or SP-CSI.

[0205] Optionally, any one of the N third indication information (e.g., referred to as fourth indication information) may further instruct the first communications device to send the first information. The fourth indication information may be understood as being used to trigger the first communications device to send the first information. For example, the fourth indication information may be the earliest sent third indication information, the latest sent third indication information, or a third indication information configured for the first communications device, without limitation.

[0206] Optionally, one of the N pieces of third indication information (e.g., referred to as fifth indication information) may further instruct the first communications device to store the first data corresponding to the fifth indication information, accumulate the first data corresponding to the fifth indication information, or not send at least one of the first data corresponding to the fifth indication information. The fifth indication information is, for example, any one of the N pieces of third indication information except the fourth indication information.

[0207] A9. Configuration information for reporting reference signal measurement results. That is, the first indication information further indicates configuration information for reporting measurement results. The configuration information for reporting measurement results may include, for example, time-frequency resources and / or periods for reporting measurement results, and is not limited thereto.

[0208] In addition to sending the first indication information, the second communications device may also send N reference signals to the first communications device. For example, the second communications device may send one of the N reference signals to the first communications device based on each of the N groups of reference signal resources. The reference signal may be, for example, a CSI-RS.

[0209] In one possible design, the second communication device may further send second indication information to the first communication device, where the second indication information indicates periodic generation of the first data. For example, the first indication information indicates a first period for generating the first data, and the first period is used to instruct the first communication device to periodically generate the first data. The second indication information and the first indication information may be carried in different signaling or in the same signaling, without limitation. Optionally, the length of the first period is less than the length of the first monitoring window.

[0210] Optionally, the first periods corresponding to the N first data, that is, the N first periods, may be an example of N fourth time units.

[0211] S702: The first communication device sends first information to the second communication device. Correspondingly, the second communication device receives the first information from the first communication device.

[0212] The first communication device determines an inference result based on a reference signal from the second communication device. Similarly, the first communication device can obtain N inference results of the model based on N reference signals from the second communication device. In this way, the first communication device obtains N first data based on the N inference results, and further obtains first information based on the N first data.

[0213] For example, if the N third time units are time units for generating N inference results, the first communication device may generate N inference results in each of the N third time units. Alternatively, after receiving N reference signals, the first communication device may determine N inference results based on the N reference signals. This embodiment of the present application does not specifically limit the timing of determining the inference results.

[0214] Similarly, if N fourth time units (or N first periods) are time units for generating N first data, then the first communication device can generate N first data in each of the N fourth time units. Alternatively, after determining the N inference data, the first communication device can determine the N first data based on the N inference data. The embodiments of the present application do not specifically limit the timing of determining the inference result.

[0215] If the content of the first indication information or the third indication information is different, the operations performed by the first communication device after generating the first data will also be different, which will be described below with examples.

[0216] D1. The first indication information indicates the content shown in A5 above, that is, the first indication information instructs the first communication device to store N first data.

[0217] In D1, after determining N first data, the first communication device may cache the N first data.

[0218] Similarly, when the fifth indication information among the N third indication information indicates to store the first data, the first communication device may also store the first data corresponding to the fifth indication information.

[0219] D2. The first indication information indicates the content shown in A6 above, that is, the first indication information instructs the first communication device to accumulate N first data.

[0220] If the first indication information indicates to accumulate the first data, the first communication device will simultaneously count the first data when determining the N first data. In this way, after obtaining the N first data, the first communication device also obtains the statistical information of the N first data, which facilitates rapid acquisition of the first information.

[0221] Similarly, when the fifth indication information among the N third indication information indicates to accumulate the first data, the first communications device may also accumulate the first data corresponding to the fifth indication information.

[0222] D3. The first indication information indicates the content shown in A7 above. The first indication information instructs the first communication device not to send N first data.

[0223] If the first indication information does not report the N first data, then the first communications device may not report the N first data. In this case, before sending the first information, the information sent by the first communications device to the second communications device does not include any of the N first data. In another embodiment relative to D3, if the first communications device can report the N first data, then after determining any first data among the N first data, the first communications device may report the any first data.

[0224] Similarly, optionally, if the third indication information indicates that at least one first data among the N first data is to be reported, the first communication device reports the at least one first data. Alternatively, if the third indication information indicates that at least one first data among the N first data is not to be reported, the first communication device does not need to report the at least one first data.

[0225] If the model of the first communication device is different (or the inference result is different), then the specific content of the first information obtained by the first communication device will also be different, which will be introduced below with examples combining F1 or F2.

[0226] The F1 model is used to predict the beam. Accordingly, the inference result is the beam prediction result.

[0227] The first communication device may measure N reference signals from the second communication device respectively to obtain N measurement results. Each measurement result may include, for example, beam information, such as beam signal strength. The beam signal strength may be, for example, reference signal receiving power (RSRP).

[0228] The first communication device may input each of the N measurement results into a model to obtain a beam prediction result. Similarly, N beam prediction results may be obtained. For example, one of the N beam prediction results may include probabilities that multiple beams belong to the optimal beam, or may include signal strengths corresponding to multiple beams.

[0229] In this way, the first communication device can be based on the N beam prediction results and the true values ​​corresponding to the N beam prediction results, for example, information about the optimal beam (such as an identification (ID)) or the measured signal strengths of multiple beams. The first communication device can compare the beam prediction results with the true values ​​corresponding to the beam prediction results, which is equivalent to implementing model performance monitoring to obtain N first data.

[0230] The following describes an example of how the model manages beams, with reference to a schematic diagram of an application model managing beams shown in FIG11. The first direction and the second direction shown in FIG11 are, for example, the horizontal direction and the vertical direction, respectively. As shown in FIG11, the first communication device measures or scans a portion of the beams based on the reference signal to obtain measurement results for this portion of the beams. The model can predict the measurement results of this portion of the beams, thereby predicting multiple relatively optimal beams (three beams as shown in FIG11). The first communication device can measure or scan these multiple beams to ultimately determine the optimal beam.

[0231] The F2 model is used to predict CSI. Correspondingly, the inference result is the CSI prediction result.

[0232] The first communications device may input N reference signals from the second communications device into the model to obtain CSI prediction results, thereby obtaining a total of N CSI prediction results. The first communications device may monitor model performance based on the N CSI prediction results and the true values ​​corresponding to the N CSI prediction results, for example, the CSI actually measured by the first communications device. The first communications device may compare the CSI prediction results with the measured CSI to obtain N first data.

[0233] If the first information includes N first data, then after the first communications device obtains the N first data, it is equivalent to obtaining the first information. If the first information includes statistical information of the N first data, then the first communications device may perform statistics on the N first data to obtain the first information. Optionally, if the first indication information or the third indication information indicates accumulation of the first data, then the first communications device simultaneously performs statistics on the first data during the process of determining the N first data. Therefore, after obtaining the N first data, the first communications device also obtains the statistical information of the N first data, and thus obtains the first information based on the statistical information of the N first data.

[0234] After receiving the first information, the second communication device may determine a policy for managing the model based on the first information. The policy may include, for example, switching the model, deactivating the model, or updating model parameters, which are not specifically limited. The second communication device may determine the policy in various ways, as exemplified below.

[0235] For example, if the first information indicates an average value of N first data items, and the second communication device determines that the average value is less than a first threshold, the second communication device may train a model based on the data set to update the model parameters, and then provide feedback of the updated model parameters to the first communication device. Alternatively, the second communication device may instruct the first communication device to deactivate the model or switch the model. There are various other ways for the second communication device to determine a strategy, which are not specifically limited in the embodiments of the present application.

[0236] In an embodiment of the present application, a mechanism supporting a monitoring model is proposed in a scenario where a network device configures a reference signal for a terminal device. Furthermore, in a first indication message, the terminal device is instructed to transmit first information, store first data, accumulate first data, or not transmit first data, thereby reducing modifications to the first communication device and enabling the monitoring model mechanism provided in the embodiment of the present application to better adapt to the process of measuring reference signals. Furthermore, the first indication message may be multiplexed RRC signaling, for example, without increasing the number of interactions between devices.

[0237] The following example describes the data collection method involved in FIG7 by taking the first communication device as a terminal device, the second communication device as a network device, the reference signal as a CSI-RS, and the terminal device periodically reporting CSI as an example.

[0238] Please refer to Figure 12, which is a schematic diagram of a data collection method provided in an embodiment of the present application. The following describes the various steps involved in Figure 12.

[0239] S1201: A network device sends first indication information to a terminal device. Correspondingly, the terminal device receives the first indication information from the network device.

[0240] Exemplarily, the first indication information indicates sending the first information. Optionally, the first indication information may also indicate at least one of A2 to A9 discussed in the embodiment shown in FIG7 above. For example, the first indication information further instructs the terminal device to store the first data. The content of the first indication information, the content of the first information, and the content of the first indication information indicating that the first information is to be sent may refer to the content of the first indication information, the content of the first information, and the content of the first indication information indicating that the first information is to be sent, respectively, as discussed in the embodiment shown in FIG7 above.

[0241] S1202: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device. In the embodiment of the present application, the network device periodically sends a CSI-RS to the terminal device as an example.

[0242] The ellipsis after S1202 in FIG12 indicates that the network device sends multiple CSI-RSs to the terminal device, and the terminal device can determine the first data multiple times. There is no specific limitation on the number of CSI-RSs sent and the number of times the first data is determined.

[0243] S1203. The terminal device determines the first data and caches the first data.

[0244] The content of the first data and the determination of the content of the first data may refer to the content of the first data and the determination of the content of the first data discussed in the embodiment shown in FIG. 7 , respectively.

[0245] S1204: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device.

[0246] The above steps S1202 and S1204 are performed periodically. The terminal device can determine the first data based on the CSI-RS. Similarly, the terminal device can obtain N first data.

[0247] S1205. The terminal device determines the first information based on N first data.

[0248] The contents of the N first data, the contents of the first information, and the determination of the contents of the first information can refer to the contents of the N first data, the contents of the first information, and the determination of the contents of the first information discussed in the embodiment shown in Figure 7 above.

[0249] S1202 to S1205 are optional steps, which are indicated by dotted lines in FIG12 .

[0250] S1206: The terminal device sends the first information to the network device. Correspondingly, the network device receives the first information from the terminal device.

[0251] For example, please refer to Figure 13, which is a schematic diagram of reporting first information provided in an embodiment of the present application. As shown in Figure 13, the terminal device receives a CSI-RS within the first CSI-RS configuration period. The terminal device measures the CSI-RS, obtains a measurement result, and determines a first data based on the measurement result and the model. By analogy, the terminal device can obtain N first data (4 first data as shown in Figure 13). In this way, the terminal device can determine the first information based on the 4 first data and report the first information to the network device.

[0252] The network device may determine the policy of the management model based on the first information. The content of the policy of the management model may refer to the content of the policy of the management model discussed in FIG. 7 , which will not be listed here.

[0253] In an embodiment of the present application, a mechanism for supporting a monitoring model is proposed in a scenario where a network device configures a periodic CSI-RS for a terminal device. Furthermore, instructing the terminal device to send the first information in a first indication message (such as RRC signaling) does not increase the number of interactions between the terminal device and the network device, and can reduce the changes to the terminal device and the network device, and enables the monitoring model mechanism provided in the embodiment of the present application to better adapt to the process of measuring reference signals.

[0254] The following example describes the data collection method involved in FIG7 by taking the first communication device as a terminal device, the second communication device as a network device, the reference signal as a CSI-RS, and the terminal device reporting CSI non-periodically.

[0255] Please refer to Figure 14, which is a schematic diagram of a data collection method provided in an embodiment of the present application. The following describes the various steps involved in Figure 14.

[0256] S1401: A network device sends first indication information to a terminal device. Correspondingly, the terminal device receives the first indication information from the network device.

[0257] Exemplarily, the first indication information indicates that the first information is to be sent. Optionally, the first indication information may also indicate at least one of A2 to A9 discussed in the embodiment shown in FIG7 . For example, the first indication information further instructs the terminal device to store the first data. The content of the first indication information, the content of the first information, and the content of the first information indicated by the first indication information for sending the first information may refer to the content of the first indication information, the content of the first information, and the content of the first information indicated by the first indication information for sending the first information discussed in the embodiment shown in FIG7 , respectively.

[0258] S1402: The network device sends third indication information to the terminal device. Accordingly, the terminal device receives the third indication information from the network device. The content of the third indication information may refer to the content of the third indication information discussed in the embodiment shown in FIG7 . S1402 uses the third indication information indicating the generation of first data and the triggering of a CSI-RS as an example. Optionally, the third indication information may be, for example, a DCI.

[0259] S1403: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device.

[0260] The ellipsis after S1403 in FIG14 indicates that the network device sends multiple CSI-RSs to the terminal device, and the terminal device can determine the first data multiple times. There is no specific limitation on the number of CSI-RSs sent and the number of times the first data is determined.

[0261] S1404: The terminal device determines the first data and caches the first data. The content of the first data and the determination of the content of the first data may refer to the content of the first data and the determination of the content of the first data involved in the embodiment shown in FIG. 7 , respectively.

[0262] Optionally, if the first indication information or the third indication information in S1402 further indicates that the terminal device does not report the first data, then after the terminal device determines the first data, it is not necessary to report the first data. Alternatively, if the first indication information or the third indication information in S1402 indicates that the terminal device reports the first data, then the terminal device may also report the first data to the network device.

[0263] S1405: The network device sends third indication information to the terminal device. Accordingly, the terminal device receives the third indication information from the network device. The content of the third indication information can refer to the content of the third indication information discussed in S1402. S1404 uses the third indication information indicating the generation of first data and the triggering of CSI-RS as an example.

[0264] S1406: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device.

[0265] Similarly, the terminal device can determine N first data. The contents of the N first data and the terminal device determining the contents of the N first data can refer to the contents of the N first data and the terminal device determining the contents of the N first data discussed in the embodiment shown in FIG7 , respectively.

[0266] S1407. The terminal device determines the first information based on the N first data. The contents of the N first data, the contents of the first information, and the determination of the contents of the first information can refer to the contents of the N first data, the contents of the first information, and the determination of the contents of the first information, respectively, discussed in the embodiment shown in FIG. 7 .

[0267] S1402 to S1407 are optional steps, which are indicated by dotted lines in FIG14 .

[0268] S1408: The terminal device sends the first information to the network device. Correspondingly, the network device receives the first information from the terminal device.

[0269] In an embodiment of the present application, a model monitoring mechanism is provided. This model monitoring mechanism is applicable to scenarios where a network device configures aperiodic CSI-RS for a terminal device, thereby reducing modifications to both the terminal device and the network device. Furthermore, by coordinating the configuration of the first indication information and the indication of the third indication information, the terminal device is supported in monitoring the model, and the number of information exchanges between the terminal device and the network device is reduced.

[0270] The following example describes the data collection method involved in FIG7 by taking the first communication device as a terminal device, the second communication device as a network device, the reference signal as a CSI-RS, and the terminal device semi-periodically reporting CSI as an example.

[0271] Please refer to Figure 15, which is a schematic diagram of a data collection method provided in an embodiment of the present application. The following describes the various steps involved in Figure 15.

[0272] S1501: A network device sends first indication information to a terminal device. Correspondingly, the terminal device receives the first indication information from the network device.

[0273] Exemplarily, the first indication information indicates sending the first information. Optionally, the first indication information may also indicate at least one of A2 to A9 discussed in the embodiment shown in FIG7 . The content of the first indication information, the content of the first information, and the content of the first indication information indicating sending the first information may refer to the content of the first indication information, the content of the first information, and the content of the first indication information indicating sending the first information discussed in the embodiment shown in FIG7 , respectively.

[0274] S1502: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device.

[0275] The ellipsis after S1502 in FIG15 indicates that the network device sends multiple CSI-RSs to the terminal device, and the terminal device can determine the first data multiple times. There is no specific limitation on the number of CSI-RSs sent and the number of times the first data is determined.

[0276] S1503. The terminal device determines the first data and caches the first data.

[0277] The content of the first data and the determination of the content of the first data may refer to the content of the first data and the determination of the content of the first data discussed in the embodiment shown in FIG. 7 , respectively.

[0278] S1504: The network device sends fourth indication information to the terminal device. Accordingly, the terminal device receives the fourth indication information from the network device. The content of the fourth indication information may refer to the content of the fourth indication information discussed in the embodiment shown in FIG. 7 . For example, the fourth indication information may be a DCI or a MAC CE.

[0279] In one possible implementation, if the terminal device reports the measurement result of the reference signal based on the physical uplink control channel (PUCCH), then the fourth indication information may be MAC CE, that is, MAC CE activates PUCCH-based semi-static CSI reporting.

[0280] In another possible implementation, if the terminal device reports the measurement result of the reference signal based on the physical uplink shared channel (PUCCH), then the fourth indication information may be DCI, ie, DCI activates PUCCH-based semi-static CSI reporting.

[0281] S1505: The network device sends a CSI-RS to the terminal device. Correspondingly, the terminal device receives the CSI-RS from the network device.

[0282] In this way, the terminal device can determine the first data based on the CSI-RS. Similarly, the terminal device can obtain N first data.

[0283] S1506. The terminal device determines the first information based on the N first data.

[0284] The contents of the N first data, the contents of the first information, and the determination of the contents of the first information can refer to the contents of the N first data, the contents of the first information, and the determination of the contents of the first information discussed in the embodiment shown in Figure 7 above.

[0285] S1502 to S1506 are optional steps, which are indicated by dotted lines in FIG15 .

[0286] S1507: The terminal device sends the first information to the network device. Correspondingly, the network device receives the first information from the terminal device.

[0287] After the terminal device completes reporting the measurement result, the network device may optionally instruct the terminal device to deactivate reporting. If the fourth indication information is a MAC CE, the network device may instruct the terminal device to deactivate reporting the measurement result via the MAC CE. If the fourth indication information is a DCI, the network device may instruct the terminal device to deactivate reporting the measurement result via the DCI.

[0288] In an embodiment of the present application, a model monitoring mechanism is provided. This model monitoring mechanism is applicable to scenarios where a network device configures a semi-periodic CSI-RS for a terminal device, thereby reducing modifications to both the terminal device and the network device. Furthermore, by coordinating the configuration of the first indication information and the indication of the third indication information, the terminal device is supported in monitoring the model, and the number of information exchanges between the terminal device and the network device is reduced.

[0289] It is understood that, in order to implement the functions in the above embodiments, the base station and the terminal include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily appreciate that, in conjunction with the units and method steps of the various examples described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in hardware or in a computer software-driven hardware manner depends on the specific application scenario and design constraints of the technical solution.

[0290] Figures 16 to 18 are schematic diagrams of the structures of possible communication devices provided by the embodiments of the present application. These communication devices can be used to implement the functions of the first communication device or the second communication device in the above-mentioned method embodiment, or to implement the functions of the terminal device or network device in the above-mentioned method embodiment, and thus can also achieve the beneficial effects possessed by the above-mentioned method embodiment. In the embodiments of the present application, the communication device can be a terminal device as described in any one of Figures 3 to 6, or a network device as described in Figure 3, a network device as described in Figure 4, a CU, DU, core network device, access network node or OAM as described in Figure 5, or a non-real-time RIC, near real-time RIC, CU, DU, CU-CP, RU or access network node as described in Figure 6, or a module (such as a chip) applied to a terminal device or a network device.

[0291] As shown in FIG. 16 , the communication device 1600 includes a processing module 1610 and a transceiver module 1620 .

[0292] In a possible embodiment, the communication device 1600 is used to implement the function of the first communication device in the method embodiment shown in Figure 7 above, or the function of the terminal device in the method embodiment shown in Figure 12, Figure 14 or Figure 15.

[0293] For example, the transceiver module 1620 may be configured to receive first indication information and send first information under the control of the processing module 1610 .

[0294] The communication device 1600 can also implement the steps implemented by the first communication device in the method embodiment shown in Figure 7, or the steps implemented by the terminal device in the method embodiment shown in Figure 12, Figure 14 or Figure 15, which are not listed one by one here.

[0295] In a possible embodiment, the communication apparatus 1600 is used to implement the function of the second communication device in the method embodiment shown in FIG. 7 , or the function of the network device in the method embodiment shown in FIG. 12 , FIG. 14 , or FIG. 15 .

[0296] For example, the transceiver module 1620 may be configured to send first indication information and receive first information under the control of the processing module 1610 .

[0297] The communication device 1600 can also implement the steps implemented by the second communication device in the method embodiment shown in Figure 7, or the steps implemented by the network device in the method embodiment shown in Figure 12, Figure 14 or Figure 15, which are not listed one by one here.

[0298] As shown in Figure 17, communication device 1700 includes a processor 1710 and an interface circuit 1720. Processor 1710 and interface circuit 1720 are coupled to each other. It is understood that interface circuit 1720 can be a transceiver or an input / output interface. Optionally, communication device 1700 may also include a memory 1730 for storing instructions executed by processor 1710, input data required by processor 1710 to execute instructions, or data generated by processor 1710 after executing instructions.

[0299] The communication device 1700 can be used to implement the method embodiments shown in Figure 7, Figure 12, Figure 14 or Figure 15.

[0300] Optionally, the communication device 1700 is further configured to implement the functions of the communication device 1600 shown in Figure 16. In this case, the processor 1710 is configured to implement the functions of the processing module 1610, and the interface circuit 1720 is configured to implement the functions of the transceiver module 1620.

[0301] When the communication device is a chip used in a terminal device, the terminal device chip implements the functions of the terminal device in the above method embodiments. The terminal device chip receives information from other modules in the terminal device (such as a radio frequency module or antenna), and the information is sent by the network device to the terminal device; or the terminal device chip sends information to other modules in the terminal device (such as a radio frequency module or antenna), and the information is sent by the terminal device to the network device.

[0302] When the above-mentioned communication device is a module applied to a network device, the network device module implements the functions of the network device in the above-mentioned method embodiment. The network device module receives information from other modules in the network device (such as a radio frequency module or an antenna), and the information is sent by the terminal device to the network device; or the network device module sends information to other modules in the network device (such as a radio frequency module or an antenna), and the information is sent by the network device to the terminal device. The network device module here can be a baseband chip of the network device, or it can be a DU or other module. The DU here can be a DU under the open radio access network (O-RAN) architecture.

[0303] It is understood that the processor involved in the various embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor. In addition, the memory involved in the various embodiments of the present application may include volatile memory, such as random access memory (RAM). The memory may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD) or solid state drive (SSD).

[0304] An embodiment of the present application provides another example of a communication device, which includes at least one processor and at least one memory, the at least one processor and the at least one memory being coupled, the at least one memory being used to store instructions, and when the instructions are executed by the at least one processor, the communication device executes the method in the above embodiment. Taking the communication device including a processor and a memory as an example, as shown in Figure 18, the communication device 1800 includes a processor 1810 and a memory 1820. The processor 1810 and the memory 1820 are coupled, and the memory 1820 stores instructions. When the instructions stored in the memory 1820 are executed by the processor 1810, the communication device 1800 executes any method embodiment shown in Figures 7, 12, 14, or 15.

[0305] The method steps in each embodiment of the present application can be implemented in hardware or in software instructions that can be executed by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in a base station or a terminal. The processor and storage medium can also exist in a base station or a terminal as discrete components.

[0306] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

[0307] An embodiment of the present application provides a communication system, comprising: a first communication device and a second communication device. The first communication device can implement the functions of the first communication device in Figure 7, or the functions of the terminal device in Figure 12, Figure 14, or Figure 15. The second communication device can implement the functions of the second communication device in Figure 7, or the functions of the network device in Figure 12, Figure 14, or Figure 15.

[0308] An embodiment of the present application provides a chip system, comprising: a processor and an interface, wherein the processor is configured to call and execute instructions from the interface, and when the processor executes the instructions, any of the methods shown in FIG. 7 , FIG. 12 , FIG. 14 , or FIG. 15 is implemented.

[0309] An embodiment of the present application provides a computer-readable storage medium for storing computer programs or instructions, which, when executed, implements any of the methods shown in FIG. 7 , FIG. 12 , FIG. 14 , or FIG. 15 .

[0310] An embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, implements any of the methods shown in FIG. 7 , FIG. 12 , FIG. 14 , or FIG. 15 .

[0311] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0312] It should be understood that the various numbers used in the various embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily imply a specific order of execution; the order of execution of the processes should be determined by their functions and inherent logic.

Claims

1. A data collection method, characterized in that: Applied to a first communication device, the method includes: receiving first indication information from a second communication device, the first indication information instructing the first communication device to send first information, where the first information is determined based on N first data, where the N first data are obtained by respectively performing performance monitoring on N inference results, where N is a positive integer; The first information is sent to the second communication device.

2. The method according to claim 1, characterized in that The method further comprises: Receive second indication information from the second communication device, the second indication information instructs the first communication device to generate a first cycle of first data, the N inference results are respectively the inference results generated within N first cycles, and the N first cycles are the cycles for generating the N first data.

3. The method according to claim 2, characterized in that The total duration of the N first cycles is less than or equal to the duration of the first monitoring window, wherein the first monitoring window is used to generate M first data, the M first data include the N first data, and M is an integer greater than or equal to N.

4. The method according to claim 3, characterized in that The first information is sent on a first time unit, wherein the first time unit corresponds to a second time unit, the second time unit is a time unit for potentially reporting second data, the second data is the last first data among the M first data, and the second time unit is associated with a first period for generating the second data.

5. The method according to claim 3 or 4, characterized in that The first indication information further indicates: The period of the first monitoring window; and / or, A first time unit for sending the first information, wherein the first time unit is within the first monitoring window.

6. The method according to claim 1, characterized in that The method further comprises: N third indication information is received from a second communication device, where the N third indication information instructs the first communication device to generate the N first data.

7. The method according to claim 6, characterized in that The fourth indication information among the N third indication information instructs the first communication device to send the first information.

8. The method according to claim 7, characterized in that The fourth indication information is the indication information received earliest or latest by the first communication device among the N third indication information, or an indication information configured by the second communication device.

9. The method according to any one of claims 6 to 8, characterized in that: The fifth indication information in the N third indication information further respectively indicates at least one of the following: The first communication device stores the first data corresponding to the fifth indication information among the N first data; The first communication device accumulates the first data corresponding to the fifth indication information among the N first data; or, The first communication device does not send the first data corresponding to the fifth indication information.

10. The method according to any one of claims 1 to 9, characterized in that Before sending the first information, the information sent by the first communication device to the second communication device does not include any first data among the N first data; or Before sending the first information, the first communication device sends third data to the second communication device, where the third data belongs to the N first data.

11. The method according to any one of claims 1 to 10, characterized in that The N inference results correspond to channel state information CSI prediction results; or, The N inference results correspond to beam prediction results.

12. The method according to any one of claims 1 to 11, characterized in that The first information is determined based on N first data, including: The first information includes the N first data; or, The first information includes statistical information generated according to N first data.

13. A data collection method, characterized in that: Applied to a second communication device, the method includes: Sending first indication information to a first communication device, where the first indication information instructs the first communication device to send first information, where the first information is related to N first data, where the N first data reflect performance monitoring results of N reasoning results, respectively, where N is a positive integer; The first information is received from the first communication device.

14. The method according to claim 13, characterized in that The method further comprises: Send second indication information to the first communication device, the second indication information instructing the first communication device to generate a first cycle of first data, the N inference results are respectively the inference results generated within N first cycles, and the N first cycles are the cycles for generating the N first data.

15. The method according to claim 14, characterized in that The total duration of the N first cycles is less than or equal to the duration of the first monitoring window, wherein the first monitoring window is used to generate M first data, the M first data include the N first data, and M is an integer greater than or equal to N.

16. The method according to claim 15, characterized in that The first information is received at a first time unit, wherein the first time unit corresponds to a second time unit, the second time unit is a time unit for potentially reporting second data, the second data is the last first data among the M first data, and the second time unit is associated with a first period for generating the second data.

17. The method according to claim 15 or 16, characterized in that The first indication information further indicates: The period of the first monitoring window; and / or, A first time unit for sending the first information, wherein the first time unit is within the first monitoring window.

18. The method according to claim 13, characterized in that The method further comprises: N pieces of third indication information are sent to the first communication device, where the N pieces of third indication information instruct the first communication device to generate the N first data.

19. The method according to claim 18, characterized in that The fourth indication information among the N third indication information instructs the first communication device to send the first information.

20. The method according to claim 19, characterized in that The fourth indication information is the indication information received earliest or latest by the first communication device among the N third indication information, or an indication information configured by the second communication device.

21. The method according to any one of claims 13 to 20, characterized in that: The fifth indication information in the N third indication information further respectively indicates at least one of the following: The first communication device stores the first data corresponding to the fifth indication information among the N first data; The first communication device accumulates the first data corresponding to the fifth indication information among the N first data; or, The first communication device does not send the first data corresponding to the fifth indication information.

22. The method according to any one of claims 13 to 21, characterized in that Before receiving the first information, the information received by the second communication device from the first communication device does not include any of the N first data; or Before receiving the first information, the second communication device transmits third data from the first communication device, where the third data belongs to the N first data.

23. The method according to any one of claims 13 to 22, characterized in that The N inference results correspond to channel state information CSI prediction results; or, The N inference results correspond to beam prediction results.

24. The method according to any one of claims 13 to 23, characterized in that The first information is related to N first data, including: The first information includes the N first data; or, The first information includes statistical information generated according to N first data.

25. A communication device, characterized in that: include: A module for executing the method according to any one of claims 1 to 12; or, Module for performing the method according to any one of claims 13-24.

26. A communication device, characterized in that: The method comprises a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices outside the communication device and transmit them to the processor or send signals from the processor to other communication devices outside the communication device, and the processor is used to implement the method according to any one of claims 1 to 12 through a logic circuit or by executing code instructions, or to implement the method according to any one of claims 13 to 24.

27. A computer program product comprising instructions, characterized in that When the instruction is executed by the communication device, the communication device executes the method according to any one of claims 1 to 12, or executes the method according to any one of claims 13 to 24.

28. A computer-readable storage medium, characterized in that The storage medium stores a computer program or instruction. When the computer program or instruction is executed by the communication device, the method according to any one of claims 1 to 12 is implemented, or the method according to any one of claims 13 to 24 is executed.

Images