Communication method and communication apparatus

By acquiring the first and second measurement results to monitor the reliability of the time series prediction model, the resource consumption and power consumption problems of time series prediction model performance monitoring in the prior art are solved, and the timely updating and switching of model performance is realized, thereby improving the accuracy and efficiency of monitoring.

WO2026233049A1PCT designated stage Publication Date: 2026-11-12HUAWEI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/089761
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-09
Filing Date
2026-04-10
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

In the existing technology, how to monitor the performance of time series prediction models without consuming additional transmission resources and increasing measurement power consumption is an unsolved problem.

Method used

By acquiring the first and second measurement results, monitoring results are obtained based on these results to determine the reliability of the time-series prediction model, avoiding resource consumption and power consumption measurement at the time domain location corresponding to the prediction results, and using the measurement results from the terminal side and the network side to monitor model performance.

Benefits of technology

It enables timely detection of unsatisfactory model performance without consuming additional resources or increasing measurement power consumption, allowing for model updates, switching, or rollback, thus improving the accuracy and efficiency of model monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026089761_12112026_PF_FP_ABST
    Figure CN2026089761_12112026_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the present application are a communication method and a communication apparatus. The method comprises: acquiring a first measurement result, wherein the first measurement result is used for acquiring a first prediction result, and a time-domain position corresponding to the first prediction result is behind a time-domain position corresponding to the first measurement result; acquiring a second measurement result, wherein an end moment of a time-domain position corresponding to the second measurement result is after an end moment of the time-domain position corresponding to the first prediction result; and on the basis of the first measurement result and the second measurement result, acquiring a monitoring result, wherein the monitoring result is used for determining the credibility of the first prediction result. On the basis of the present application, a terminal side monitors the credibility of a prediction result on the basis of a measurement result obtained after the prediction result, thereby avoiding resource consumption caused by a network side sending, at a time-domain position corresponding to the prediction result, a reference signal used for monitoring the credibility of the prediction result, and avoiding measurement power consumption caused by the terminal side performing measurement at the time-domain position corresponding to the prediction result.
Need to check novelty before this filing date? Find Prior Art

Description

Communication method and communication apparatus

[0001] The present application claims priority from the Chinese patent application No. 202510599742.9 filed on May 09, 2025, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a communication method and a communication apparatus. BACKGROUND

[0003] Time series prediction, or time domain prediction, refers to analyzing and modeling based on time series data to predict data values or development trends at future time points. Time series prediction is a direction of applying artificial intelligence (AI) / machine learning (ML) technology in the field of communication, i.e., applying AI / ML technology to perform time series prediction in the field of communication. For example, applying AI / ML technology to predict reference signal received power (RSRP), channel state information (CSI), precoding matrix indicator (PMI), optimal beam, etc.

[0004] However, the problem of how to monitor the performance of the AI / ML model used for time series prediction has not been solved. SUMMARY

[0005] The present application provides a communication method and a communication apparatus, which are beneficial to monitoring the performance of the time series prediction model without occupying additional transmission resources and / or increasing additional measurement power consumption.

[0006] In a first aspect, a communication method is provided, the method comprising: obtaining a first measurement result, the first measurement result being used to obtain a first prediction result, a time domain position corresponding to the first prediction result being after a time domain position corresponding to the first measurement result; obtaining a second measurement result, an ending time of a time domain position corresponding to the second measurement result being after an ending time of a time domain position corresponding to the first prediction result; and obtaining a monitoring result based on the first measurement result and the second measurement result, the monitoring result being used to determine a credibility of the first prediction result.

[0007] This method can be applied to the terminal side, for example, it can be executed by the terminal device; or it can be executed by components deployed in the terminal device, such as circuits or chips inside the terminal device (such as modem chips, also known as baseband chips, or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores, etc.); or it can be executed by devices deployed outside the terminal device (such as the host or cloud server of an over-the-top (OTT) system) or components within the device (such as chips, processors, or circuits inside the device, etc.); or it can be implemented by logic modules or software that can realize all or part of the functions of the terminal device, etc. Alternatively, the method can be executed by a first device, which can be a terminal device; it can also be a component within the terminal device, such as internal circuitry or a chip (e.g., a modem chip), or a SoC chip or SIP chip containing a modem core; it can also be a device outside the terminal device (e.g., the host of an OTT system or a cloud server) or a component within a device (e.g., internal chips, processors, or circuitry); or it can be a logic module or software capable of implementing some or all of the functionalities of the terminal side, etc. This application does not limit this. For ease of understanding and explanation, the method provided in the first aspect will be described below using the terminal side as an example.

[0008] Based on the above technical solution, the terminal can monitor the reliability of the prediction result based on the measurement results obtained after the prediction result. This avoids the resource consumption caused by the network sending reference signals for monitoring the reliability of the prediction result at the time domain position corresponding to the prediction result, and also avoids the measurement power consumption caused by the terminal performing measurements at the time domain position corresponding to the prediction result. Furthermore, based on the embodiments of this application, the terminal can continuously monitor the reliability of the prediction result based on the measurement results obtained after the prediction result during model operation. This allows the terminal and / or network to promptly detect when the model's performance does not meet requirements, and thus promptly update, switch, or roll back the model.

[0009] For example, the second measurement result is used to obtain the second prediction result.

[0010] Optionally, the interval between the end time of the time domain position corresponding to the second measurement result and the end time of the time domain position corresponding to the first prediction result is less than or equal to the seventh threshold.

[0011] Based on the above technical solution, it is possible to avoid the situation where the time domain position corresponding to the measurement result used by the terminal side is too large and the time domain position corresponding to the prediction result is too large when the channel changes over time, which would prevent the acquisition of monitoring results that accurately indicate the reliability of the prediction result.

[0012] This application does not limit the method by which the terminal side obtains monitoring results based on the first measurement result and the second measurement result.

[0013] In one possible implementation, obtaining monitoring results based on the first measurement result and the second measurement result includes: obtaining a first prediction result and a third prediction result based on the first measurement result and the first model, wherein the time domain position corresponding to the third prediction result is the same as the time domain position corresponding to the second measurement result; and obtaining monitoring results based on the third prediction result and the second measurement result.

[0014] Based on the above technical solution, the terminal side can monitor the reliability of the first prediction result output by the first model based on the third prediction result output by the first model, which helps to simplify the model monitoring process on the terminal side.

[0015] For example, based on the third prediction result and the second measurement result, the obtained monitoring result includes one or more of the following: a first difference information between the third prediction result and the second measurement result, and / or, the deviation between the first difference information and a first threshold; a first mean square error (MSE) information between the third prediction result and the second measurement result, and / or, the deviation between the first MSE information and the second threshold; a first normalized mean square error (NMSE) information between the third prediction result and the second measurement result, and / or, the deviation between the first NMSE information and the third threshold; a first mean absolute error (MAE) information between the third prediction result and the second measurement result, and / or, the deviation between the first MAE information and a fourth threshold; a first generalized cosine similarity (GCS) information between the third prediction result and the second measurement result, and / or, the deviation between the first GCS information and a fifth threshold; or, a first square generalized cosine similarity (SGP) information between the third prediction result and the second measurement result. Similarity (SGCS) information, and / or the deviation between the first SGCS information and the sixth threshold.

[0016] In one possible implementation, obtaining monitoring results based on the first measurement result and the second measurement result includes: obtaining monitoring results based on the first measurement result and the second measurement result includes: obtaining monitoring results based on the first measurement result, the second measurement result, and the second model.

[0017] For example, based on the first measurement result, the second measurement result, and the second model, the monitoring result is obtained, including: based on the first measurement result, the second measurement result, and the second model, a fourth prediction result is obtained, wherein the time domain position corresponding to the fourth prediction result is the same as the time domain position corresponding to the first prediction result; and based on the fourth prediction result and the first prediction result, the monitoring result is obtained.

[0018] Optionally, based on the first measurement result, the second measurement result, and the second model, a fourth prediction result is obtained, including: obtaining the first prediction result based on the first measurement result and the first model; and obtaining the fourth prediction result based on the first prediction result, the second measurement result, and the second model.

[0019] For example, based on the fourth prediction result and the first prediction result, the obtained monitoring result includes one or more of the following: second difference information between the fourth prediction result and the first prediction result, and / or, the deviation between the second difference information and the first threshold; second MSE information between the fourth prediction result and the first prediction result, and / or, the deviation between the second MSE information and the second threshold; second NMSE information between the fourth prediction result and the first prediction result, and / or, the deviation between the second NMSE information and the third threshold; second MAE information between the fourth prediction result and the first prediction result, and / or, the deviation between the second MAE information and the fourth threshold; second GCS information between the fourth prediction result and the first prediction result, and / or, the deviation between the second GCS information and the fifth threshold; or, second SGCS information between the fourth prediction result and the first prediction result, and / or, the deviation between the second SGCS information and the sixth threshold.

[0020] For another example, obtaining monitoring results based on the first measurement result, the second measurement result, and the second model includes: obtaining a first prediction result based on the first measurement result and the first model; and obtaining monitoring results based on the first prediction result, the second measurement result, and the second model.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining a third measurement result, wherein the time domain position corresponding to the third measurement result is before the time domain position corresponding to the first measurement result; and obtaining a monitoring result based on the first measurement result and the second measurement result, including: obtaining a monitoring result based on the first measurement result, the second measurement result, and the third measurement result.

[0022] Based on the above technical solution, the terminal side combines the measurement results obtained before and after obtaining the prediction results to determine the monitoring results corresponding to the prediction results, which is conducive to determining the monitoring results that accurately indicate the credibility of the prediction results.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving first information, the first information being used to instruct the execution of model monitoring, the model monitoring being used to obtain monitoring results.

[0024] For example, the first information includes information about a first model, which is used to obtain a first prediction result.

[0025] Based on the above technical solution, it is beneficial for the terminal side to start model monitoring for the first model based on the instruction of the first information.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving second information, the second information being used to indicate the time period for performing model monitoring, and the monitoring result being obtained by performing model monitoring.

[0027] For example, the second information includes information about the reference signal resources, and the time period for which the model monitoring is performed corresponds to the time-domain resources of the reference signal resources.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving third information, the third information being used to indicate performance metrics, and the performance metrics being used to determine monitoring results.

[0029] Based on the above technical solution, it is beneficial for the terminal side to obtain monitoring results that accurately indicate the reliability of the prediction results based on third-party information.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the method also includes: sending monitoring results.

[0031] Based on the above technical solution, the network side can determine the performance of the first model in a timely manner according to the monitoring results, which in turn allows the network side to trigger model switching, rollback, and update operations in a timely manner when the performance of the first model does not meet the performance requirements.

[0032] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving fourth information, the fourth information being used to indicate that the time of reporting the monitoring result is not earlier than the first time, and the first time is not earlier than the end time of the time domain position corresponding to the second measurement result.

[0033] Based on the above technical solution, it is beneficial for the terminal to report monitoring results based on the instructions of the fourth information.

[0034] Secondly, a communication method is provided, the method comprising: transmitting a first reference signal, the first reference signal being used to acquire a first measurement result, the first measurement result being used to acquire a first prediction result, the time domain position corresponding to the first prediction result being after the time domain position corresponding to the first measurement result; transmitting a second reference signal, the second reference signal being used to acquire a second measurement result, the end time of the time domain position corresponding to the second measurement result being after the end time of the time domain position corresponding to the first prediction result; the first measurement result and the second measurement result being used to acquire a monitoring result, the monitoring result being used to determine the reliability of the first prediction result.

[0035] This method can be applied to the network side, for example, it can be executed by a network device; or it can be executed by a component deployed in the network device, such as the circuits or chips inside the network device (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores, etc.); or it can be executed by a device outside the network device (e.g., intelligent network elements on the network side, etc.) or a component within the device (e.g., chips, processors, or circuits inside the device, etc.); or it can be implemented by a logic module or software capable of implementing all or part of the functions of the network device, etc. Alternatively, the method can be executed by a second device, which can be a network device; or a component within the network device, such as the circuits or chips inside the network device (e.g., modem chips, or SoC chips or SIP chips containing modem cores, etc.); or a device outside the network device (e.g., intelligent network elements) or a component within the device (e.g., chips, processors, or circuits inside the device, etc.); or it can be a logic module or software capable of implementing some or all of the functions of the network side, etc. This application does not limit this.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the interval between the end time of the time domain position corresponding to the second measurement result and the end time of the time domain position corresponding to the first prediction result is less than or equal to the seventh threshold.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a third reference signal, the third reference signal being used to acquire a third measurement result, the time domain position corresponding to the third measurement result being before the time domain position corresponding to the first measurement result; the first measurement result, the second measurement result, and the third measurement result being used to acquire a monitoring result.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending first information, the first information being used to instruct the execution of model monitoring, the model monitoring being used to obtain monitoring results.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the first information includes information from the first model, which is used to obtain the first prediction result.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending second information, the second information being used to indicate the time period for performing model monitoring, and the monitoring result being obtained by performing model monitoring.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the second information includes information about the reference signal resources, and the time period for performing model monitoring corresponds to the time-domain resources of the reference signal resources.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending third information, the third information being used to indicate performance metrics, and the performance metrics being used to determine monitoring results.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: receiving monitoring results.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a fourth message, the fourth message being used to indicate that the time of reporting the monitoring result is not earlier than the first time, and the first time is not earlier than the end time of the time domain position corresponding to the second measurement result.

[0045] It should be understood that the methods provided in the second aspect correspond to those in the first aspect. The descriptions and technical effects of the various implementation methods in the second aspect can be found in the relevant descriptions in the first aspect, and will not be repeated here.

[0046] Thirdly, an apparatus is provided. This apparatus may include functional modules corresponding to each of the methods / operations / steps / actions described in any possible implementation of the first aspect, or may include functional modules corresponding to each of the methods / operations / steps / actions described in any of the second aspects. The module may be a hardware circuit, software, or a combination of hardware circuitry and software implementation.

[0047] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the terminal side in the method described in the first aspect above, while the processing module is used to perform processing-related actions performed by the terminal side in the method described in the first aspect above.

[0048] In one design, the device can be a terminal device, or a device, module, circuit or chip configured in the terminal device, or a device that can be used in conjunction with the terminal device, such as an OTT host or cloud server.

[0049] In one design, the device may include a processing module and a communication module. The communication module is used to perform the sending and receiving actions performed by the network side in the method described in the second aspect above, while the processing module is used to perform processing-related actions performed by the network side in the method described in the second aspect above.

[0050] In one design, the device can be a network device, or a device, module, circuit, or chip configured in the network device, or a device that can be used in conjunction with the network device, such as an intelligent network element with a radio access network (RAN) intelligent controller (RIC) deployed thereon.

[0051] Fourthly, an apparatus is provided, comprising a processor and a storage medium storing instructions that, when executed by the processor, cause a method as described in the first aspect or any possible implementation thereof to be implemented, or cause a method as described in the second aspect or any possible implementation thereof to be implemented.

[0052] Fifthly, an apparatus is provided, comprising a processing circuit for processing data and / or information such that a method as in the first aspect or any possible implementation thereof is implemented, or a method as in the second aspect or any possible implementation thereof is implemented.

[0053] The processing circuit may include one or more processors, or all or part of the circuitry in one or more processors used for control or processing functions.

[0054] Optionally, the apparatus may further include a memory for storing programs or instructions, and the processor for running the programs or instructions to implement the methods as described in the first aspect or any possible implementation thereof, or to implement the methods as described in the second aspect or any possible implementation thereof.

[0055] Optionally, the device may also include the transceiver circuit, or an input / output interface.

[0056] In a sixth aspect, a chip is provided, including processing circuitry for running a program or instructions to cause the method as described in the first aspect or any possible implementation thereof to be implemented, or to cause the method as described in the second aspect or any possible implementation thereof to be implemented.

[0057] Optionally, the chip may further include a memory for storing programs or instructions.

[0058] Optionally, the chip may also include transceiver circuitry, or input / output interfaces.

[0059] A seventh aspect provides a computer-readable storage medium comprising instructions that, when executed by a processor, cause the method as described in the first aspect or any possible implementation thereof to be implemented, or cause the method as described in the second aspect or any possible implementation thereof to be implemented.

[0060] Eighthly, a computer program product is provided, the computer program product comprising computer program code or instructions, which, when executed, cause the method as described in the first aspect and any possible implementation thereof to be implemented, or cause the method as described in the second aspect and any possible implementation thereof to be implemented.

[0061] Ninth aspect, a communication system is provided, the communication system including means for performing the first aspect and any possible implementation thereof, or including means for performing the second aspect and any possible implementation thereof.

[0062] It should be understood that the third to ninth aspects of this application correspond to the technical solutions of the first to second aspects of this application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0063] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment.

[0064] Figure 2 is a schematic diagram of a communication system applicable to the communication method of this application embodiment.

[0065] Figure 3 is a schematic diagram of a possible application framework in a communication system.

[0066] Figure 4 is a schematic diagram of a possible application framework in a communication system.

[0067] Figure 5 is a schematic diagram of a time series prediction AI model.

[0068] Figure 6 illustrates a schematic diagram of model monitoring for a time series prediction AI model.

[0069] Figure 7 shows a schematic flowchart of the communication method provided in an embodiment of this application.

[0070] Figure 8 shows a schematic diagram of a time series prediction AI model.

[0071] Figure 9 shows a schematic diagram of the model monitoring method provided in an embodiment of this application.

[0072] Figure 10 shows a schematic diagram of the model monitoring method provided in an embodiment of this application.

[0073] Figure 11 shows a schematic diagram of the model monitoring method provided in an embodiment of this application.

[0074] Figure 12 shows a schematic diagram of the model monitoring method provided in an embodiment of this application.

[0075] Figure 13 shows a schematic flowchart of the communication method provided in an embodiment of this application.

[0076] Figure 14 is a schematic diagram of a communication device 1400 provided in an embodiment of this application.

[0077] Figure 15 is a schematic diagram of another communication device 1500 provided in an embodiment of this application. Detailed Implementation

[0078] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0079] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0080] First, in this application, the terminal side can also be referred to as the UE (user equipment) side, including: terminal equipment, components deployed in the terminal equipment (such as circuits or chips inside the terminal equipment), equipment deployed outside the terminal equipment (such as OTT hosts or cloud servers), or components deployed in equipment outside the terminal equipment (such as circuits or chips inside the equipment). The network (NW) side includes: network equipment communicating with the terminal equipment, components deployed in the network equipment (such as circuits or chips with near real-time RAN intelligent control functions inside the network equipment), equipment deployed outside the network equipment (such as intelligent network elements, for example, intelligent network elements with near real-time RAN intelligent control functions), or components deployed in the intelligent network element (such as circuits or chips inside the intelligent network element). The network equipment may include: access network equipment, core network equipment, or operation administration and maintenance (OAM) equipment.

[0081] Second, in this application, the indication includes direct indication (also known as explicit indication) and indirect indication (also known as implicit indication). Directly indicating information A means including information A; indirectly indicating information A can mean indicating information A through the correspondence between information A and information B and by directly indicating information B; or by indicating information A through a preset rule that can be used to determine A based on B and by directly indicating information B. The correspondence between information A and information B, and the preset rule, can be predefined, pre-stored, pre-burned, or pre-configured.

[0082] Third, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0083] Fourth, the use of prefixes such as "first" and "second" in this application is merely for the purpose of distinguishing and describing different things belonging to the same category of names, and does not constrain the order, size, or quantity of things. For example, "first measurement result" and "second measurement result" are simply different measurement results, and do not limit the number of measurement results, the order in which they were obtained, or their priority.

[0084] Fifth, in this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between a terminal device and a computing node, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0085] Sixth, in the embodiments of this application, "when," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a time, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0086] Seventh, in this application, the words "example," "exemplarily," "for example," or "such as" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "example," "exemplarily," "for example," or "such as" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "example," "exemplarily," "for example," or "such as" is intended to present the relevant concepts in a specific manner.

[0087] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0088] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This disclosure uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this disclosure can be replaced by a first network element, and the network device can be replaced by a second network element, both performing the corresponding communication methods described in this disclosure.

[0089] Figure 1 is a schematic diagram of a communication system applicable to the communication method of this application embodiment. As shown in Figure 1, the communication system 100A may include at least one access network device, such as access network device 110 shown in Figure 1; the communication system 100A may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1. Access network device 110 and terminal devices (such as terminal device 120 and terminal device 130) can communicate via a wireless link. The communication devices in this communication system, for example, access network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0090] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming (BF), and supporting beam management, network energy efficiency has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced.

[0091] Figure 2 is a schematic diagram of another communication system applicable to the communication method of this application embodiment. Compared with the communication system 100A shown in Figure 1, the communication system 100B shown in Figure 2 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models. The AI ​​network element can also be simply referred to as an intelligent network element.

[0092] In one possible implementation, access network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by terminal devices. AI network element 140 can send the results of operations related to the AI ​​model to access network device 110, which then forwards them to the terminal devices. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on access network device 110, and another portion on terminal devices 120 and / or 130. Alternatively, the trained AI model may be deployed on access network device 110. Or, the trained AI model may be deployed on terminal devices 120 and / or 130.

[0093] It should be understood that Figure 2 is only used as an example of the AI ​​network element 140 being directly connected to the access network device 110. In other scenarios, the AI ​​network element 140 can also be connected to the terminal device. Alternatively, the AI ​​network element 140 can be connected to both the access network device 110 and the terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the access network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements. For example, the AI ​​network element 140 can also be set as a module in the access network device and / or the terminal device, for example, in the access network device 110 or the terminal device shown in Figure 1.

[0094] It should be noted that Figures 1 and 2 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 1 and 2. In practical applications, the communication system may include multiple access network devices and multiple terminal devices. The embodiments of this application do not limit the number of access network devices and terminal devices included in the communication system.

[0095] In the embodiments of this application, the terminal device may also be referred to as UE, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment.

[0096] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0097] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0098] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0099] The access network device in this application embodiment can be a device used to communicate with terminal devices. This access network device can also be called a network device, such as a base station. In this application embodiment, the access network device can refer to a RAN node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names such as: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technology or equipment form used in the access network equipment.

[0100] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0101] In some deployments, the access network equipment mentioned in the embodiments of this application may be a device including a CU, or a DU, or a device including both CU and DU, or a device with a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the access network equipment may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0102] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0103] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a Common Public Radio Interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, it moves some downlink and / or uplink baseband functions—for example, for downlink, precoding, digital beamforming, or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP)—from the DU to the RU; and for uplink, digital beamforming, or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP)—from the DU to the RU. In one possible implementation, this interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting methods between DU and RU are different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0104] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. The DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping itself), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming, or one or more of IFFT / CP addition) are implemented in the RU. For uplink transmission, de-RE mapping is used as the dividing line. The DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping itself), while other functions following de-mapping (e.g., digital BF or FFT / CP removal) are implemented in the RU. It is understood that descriptions of the functions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol and will not be elaborated upon here.

[0105] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0106] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open RAN (ORAN) architecture, CU can also be called open CU (open-CU, O-CU), DU can also be called open DU (open-DU, O-DU), CU-CP can also be called open CU-CP (open-CU-CP) O-CU-CP, CU-UP can also be called open CU-UP (open-CU-UP, O-CU-UP), and RU can also be called open RU (open-RU, O-RU). Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0107] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0108] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0109] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network equipment, terminal equipment, or core network elements. Alternatively, the AI ​​node can also be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an OTT system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: access network equipment, terminal equipment, or core network elements.

[0110] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0111] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0112] AI nodes can be AI network elements or AI modules.

[0113] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected via interfaces (e.g., next-generation (NG) interfaces, Xn interfaces) or air interfaces. The NG interface is the interface between the radio access network and the 5G core network. The Xn interface is the interface between access network devices, and the air interface is the interface between access network devices and terminal devices. These network element nodes, such as core network devices, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (only one is shown in Figure 3 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in the CU-CP and / or CU-UP.

[0114] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0115] An AI module can have 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 they can be deployed on the same node or device.

[0116] Network devices can be network devices equipped with one or more AI modules. These network devices can include one or more devices in the core network, access network nodes (RAN nodes), or OAM as shown in Figure 3. For example, the AI ​​module can be a RAN intelligent controller (RIC) as shown in Figure 4, such as a near-real-time RIC (near-RT RIC) or a non-real-time RIC (non-RT RIC). For instance, a near-real-time RIC is located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC is located in the OAM, a cloud server, a core network device, or other access network devices. The RIC can obtain subsets from multiple terminal devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset, and train based on the training dataset. Exemplarily, near-real-time RICs and non-real-time RICs can also be set up as separate network elements, and the access network device can be either a near-real-time RIC or a non-real-time RIC.

[0117] Figure 4 illustrates another possible application framework in a communication system. In addition to access network nodes (CU, DU, and RU are shown in the figure) and terminals, the communication system shown in Figure 4 also includes an RIC (Regulator-Integrated Circuit). For example, the RIC could be the AI ​​module shown in Figure 3, which can be used to implement AI-related functions. The RIC includes near-real-time RICs and non-real-time RICs. Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0118] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0119] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., one or more of CU, CU-CP, CU-UP, DU, or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU; for example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0120] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0121] To facilitate understanding of the embodiments of this application, the terms involved in this application will be briefly explained below.

[0122] (1) Artificial Intelligence: This refers to enabling machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, artificial intelligence refers to the technology of presenting human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or reasoning.

[0123] (2) Machine learning (ML): This is a method of implementing artificial intelligence. Machine learning is a method that endows machines with the ability to perform functions that cannot be accomplished through direct programming. In practical terms, machine learning is a method that uses data to train a model and then uses the model to make predictions. There are many methods of machine learning, such as neural networks (NN), decision trees, and support vector machines. Machine learning theory mainly involves designing and analyzing algorithms that enable computers to learn automatically. Machine learning algorithms are a class of algorithms that automatically analyze data to obtain patterns and use these patterns to predict unknown data.

[0124] (3) AI Model: An AI model is an algorithm or computer program that can implement AI functions. An AI model represents the mapping relationship between the model's input and output; in other words, an AI model is a function model that maps an input of a certain dimension to an output of a certain dimension. The parameters of the function model can be obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b are the parameters of this AI model, and a and b can be obtained through machine learning training. For example, the AI ​​model mentioned in the following embodiments of this application is not limited to neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0125] The implementation of an AI model can be a hardware circuit, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0126] (4) Channel information.

[0127] In communication systems, network devices determine one or more of the following configurations for scheduling the downlink data channel of terminal equipment based on channel information: resources, modulation and coding scheme (MCS), and precoding. Channel information, also known as CSI or channel environment information, is information that reflects channel characteristics and quality.

[0128] CSI measurement refers to the process by which the receiver deciphers channel information based on a reference signal transmitted by the transmitter; that is, it estimates channel information using channel estimation methods. For example, the reference signal may include one or more of the following: channel state information reference signal (CSI-RS), synchronizing signal / physical broadcast channel block (SSB), sounding reference signal (SRS), or demodulation reference signal (DMRS). One or more of CSI-RS, SSB, and DMRS can be used to measure downlink channel information. SRS and DMRS can be used to measure uplink channel information.

[0129] Taking FDD communication as an example, since uplink and downlink channels lack reciprocity or cannot guarantee reciprocity, network devices need to obtain downlink CSI through uplink feedback from terminal devices. Network devices typically send a downlink reference signal to the terminal device, which receives this signal. Since the terminal device knows the transmission information of the downlink reference signal, it can perform channel measurements and interference measurements based on the received signal to estimate the downlink channel it traverses. The terminal device then generates the downlink CSI based on this measurement and the resulting downlink channel matrix. Finally, the terminal device generates a CSI report according to a predefined protocol method or network device configuration and feeds it back to the network device so that it can obtain the downlink CSI.

[0130] In this embodiment, the meaning of CSI is broader than that in traditional schemes. It is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI). It can also be channel response information (such as channel response matrix), channel matrix, channel feature matrix, precoding matrix, reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), identity (ID) of the best beam or cell, the probability that at least one beam out of X beams is the best beam, the probability that at least one cell out of X cells is the best cell, or the IDs of the top K best beams out of X beams or the top K best cells out of X cells, etc. X and K are positive integers, and X is greater than or equal to K. The signal to interference plus noise ratio can also be called the signal-to-interference-plus-noise ratio. The optimal beam or cell refers to the beam or cell that maximizes received or transmitted energy. It can also be understood as the beam or cell from which the terminal is expected to have a better experience. CSI can be a single-cell (e.g., serving cell) or multi-cell CSI, thus enabling prediction not only of the optimal beam but also the optimal cell. For example, if the receiver uses different receive beams to receive signals, the optimal beam includes the beam with the highest RSRP (Received Signal-to-Profile Ratio) among the signals received from multiple different receive beams. Similarly, if the transmitter uses different transmit beams to transmit signals, the optimal beam includes the beam with the highest RSRP (Received Signal-to-Profile Ratio) when the transmitted signals arrive at the receiver. Likewise, the top K optimal beams refer to the top K beams that maximize received or transmitted energy.

[0131] In this system, RI indicates the number of downlink transmission layers suggested by the terminal device, CQI indicates the modulation and coding schemes supported by the current channel conditions as determined by the terminal device, and PMI indicates the precoding suggested by the receiver of the reference signal, such as the terminal device. The number of precoding layers indicated by PMI corresponds to RI. The channel response and channel matrix represent the channel itself, while the channel feature matrix and precoding matrix are matrices composed of features extracted from the channel.

[0132] (5) Time Series Forecasting: Also known as time-domain forecasting, this refers to the analysis and modeling of time series data to predict data values ​​or trends at future points in time. Time series forecasting is a current direction for applying AI / ML technology in the communications field, that is, applying AI / ML technology to perform time series forecasting in the communications field. For example, AI / ML technology can be used to predict RSRP, CSI, PMI, or optimal beamforming.

[0133] Figure 5 illustrates a schematic diagram of applying an AI / ML model for time series prediction. As shown in Figure 5, the input to the AI / ML model is one or more measured values, and the output of the AI / ML model is one or more predicted values ​​for future times, meaning the predicted time is later than the time corresponding to the measured value. The AI / ML model used for time series prediction can be trained on a dataset that includes both the measured values ​​and the ground truth values ​​corresponding to the predicted values.

[0134] For example, the measurement value shown in Figure 5 is the CSI (such as RSRP or channel matrix) obtained by the terminal side through measuring the downlink reference signal (such as CSI-RS). Correspondingly, the predicted value is the CSI corresponding to a future time moment predicted by the terminal side through an AI / ML model. In this case, the network side does not need to transmit the downlink reference signal at the time corresponding to the predicted value, thereby saving reference signal transmission resources. Accordingly, the terminal side does not need to measure the downlink reference signal at the time corresponding to the predicted value, thereby saving measurement power consumption.

[0135] Figure 6 illustrates a schematic diagram of performance monitoring for a time-series prediction AI / ML model. As shown in Figure 6, the terminal can measure the downlink reference signal at the time corresponding to the predicted value to obtain the true value corresponding to the predicted value. The terminal can then compare the true value / measured value corresponding to the predicted value with the predicted value to determine the performance of the time-series prediction AI / ML model.

[0136] However, based on the aforementioned scheme for monitoring the performance of time-series prediction AI / ML models, the network side needs to send a reference signal at the time corresponding to the predicted value, thus consuming additional reference signal transmission resources. Correspondingly, the terminal side needs to measure the downlink reference signal at the time corresponding to the predicted value to obtain the true value, thereby increasing additional measurement power consumption. Furthermore, the existence of a measurement value at the same time as the predicted value renders the predicted value meaningless. Therefore, the scheme shown in Figure 6 is only suitable for sampling monitoring and cannot continuously monitor the performance of the AI / ML model during its operation.

[0137] In view of this, this application provides a communication method that facilitates the monitoring of the performance of a time series prediction model without consuming additional transmission resources and / or increasing additional measurement power consumption. Furthermore, the communication method provided in this application also facilitates continuous monitoring of the performance of the time series prediction model during its operation.

[0138] The communication method provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings. The embodiments provided by this application can be applied to the communication systems shown in Figure 1 or Figure 2 above, and are not limited thereto.

[0139] It should be noted that the time-domain location or time mentioned in the following embodiments can be replaced with a time-domain unit. A time-domain unit can be one or more of the following: slot, subframe, frame, orthogonal frequency division multiplexing (OFDM) symbol, second (s), or millisecond (ms), etc.

[0140] The time-domain location corresponding to A can be replaced with one or more time-domain units corresponding to A. For example, the time-domain location corresponding to the first measurement result mentioned in the following embodiments can be replaced with M time slots corresponding to the first measurement result, such as time slot 1 to time slot M.

[0141] The start time of the time domain position corresponding to A can be replaced with the first time domain unit corresponding to A.

[0142] The end time of the time domain position corresponding to A can be replaced with the last time domain unit corresponding to A.

[0143] Figure 7 shows a schematic flowchart of the communication method provided in an embodiment of this application. The method shown in Figure 7 illustrates the flow of method 700 from the perspective of interaction between the terminal side and the network side. More detailed descriptions of the terminal side and the network side can be found above and will not be repeated here.

[0144] S710, the terminal side acquires the first measurement result, and the first measurement result is used to acquire the first prediction result.

[0145] The time domain position corresponding to the first prediction result is after the time domain position corresponding to the first measurement result.

[0146] For example, the start time of the time domain position corresponding to the first prediction result is after the end time of the time domain position corresponding to the first measurement result. In other words, the time domain position corresponding to the first prediction result does not overlap with the time domain position corresponding to the second measurement result. An example where the time domain positions corresponding to the first prediction result and the second measurement result do not overlap is: the first measurement result corresponds to time slot #1, and the first prediction result corresponds to time slot #2.

[0147] For example, the start time of the time-domain position corresponding to the first prediction result is after the start time of the time-domain position corresponding to the first measurement result, and the end time of the time-domain position corresponding to the first prediction result is after the end time of the time-domain position corresponding to the first measurement result. In other words, the time-domain position corresponding to the first prediction result partially overlaps with the time-domain position corresponding to the first measurement result. An example of this partial overlap is as follows: the first measurement result corresponds to time slots #1 and #2, and the first prediction result corresponds to time slots #2 and #3. Here, time slot #2 follows time slot #1, and time slot #3 follows time slot #2.

[0148] For example, the first measurement result is obtained by measuring a first reference signal.

[0149] Optionally, the time-domain location corresponding to the first measurement result can be replaced with the time-domain location corresponding to the resource used to transmit the first reference signal.

[0150] The first measurement results and the first prediction results are described in more detail below.

[0151] For example, the first measurement result may include one or more measurement results. Optionally, if the first measurement result includes multiple measurement results, then the first measurement result includes any two measurement results corresponding to different time domain locations. For example, the first measurement result includes measurement result #1 corresponding to time slot #1, and measurement result #2 corresponding to time slot #2.

[0152] A measurement result may include one or more measurements. A measurement value can refer to a numerical value, a vector, a matrix, or a higher-dimensional tensor. For example, a measurement result may include a channel matrix as one of the measurements. Another example is a measurement result that includes multiple measurements, each corresponding to the RSRP of L beams, where L is an integer greater than 1.

[0153] For example, the first prediction result may include one or more prediction results. Optionally, if the first prediction result includes multiple prediction results, then the first prediction result includes any two prediction results corresponding to different time domain locations. For example, the first prediction result includes prediction result #1 corresponding to time slot #3, and prediction result #2 corresponding to time slot #4. Time slot #4 is after time slot #3.

[0154] A prediction result can include one or more predicted values. A predicted value can refer to a numerical value, a vector, a matrix, or a higher-dimensional tensor. For example, a prediction result may include a predicted channel matrix as one of its predicted values. Another example is a prediction result that includes multiple predicted values ​​representing the RSRP of each of multiple beams, and / or the probability that each of the multiple beams is the optimal beam, where the optimal beam can be the beam with the highest RSRP. Yet another example is a prediction result that includes multiple predicted values ​​representing the RSRP of each of multiple cells, and / or the probability that each of the multiple cells is the optimal cell, where the optimal cell can be the cell with the highest RSRP.

[0155] The number of measurement results included in the first measurement result may be the same as or different from the number of prediction results included in the first prediction result; there is no limitation on this.

[0156] The measurement results included in the first measurement result and the prediction results included in the first prediction result can be of the same type or different types of data, without limitation. For example, both the measurement results included in the first measurement result and the prediction results included in the first prediction result are channel matrices. Another example is that the measurement results included in the first measurement result are the RSRP of each beam in beam set B, and the prediction results included in the first prediction result are the RSRP of each beam in beam set A, where beam set B is a subset of beam set A. Yet another example is that the measurement results included in the first measurement result are the RSRP of each beam in beam set A or beam set B, and the prediction results included the RSRP of each beam among multiple beams and / or the probability that each beam is the optimal beam. Yet another example is that the measurement results included in the first measurement result are channel matrices, and the prediction results included at least one PMI and the probability corresponding to each PMI. The probability corresponding to a PMI refers to the probability that the precoding matrix indicated by the PMI is the optimal precoding matrix.

[0157] The following describes how the terminal side obtains the first measurement result and the first prediction result.

[0158] In the embodiments of this application, the device used on the terminal side to perform model inference can be a terminal device or a device other than a terminal device, such as the aforementioned OTT system server. This application does not limit this.

[0159] In one example, if the device performing model inference on the terminal side is a terminal device, then in S710, the terminal device obtains a first measurement result by measuring a first reference signal from the network device. Furthermore, the terminal device can obtain a first prediction result based on the first model and the first measurement result. In other words, the terminal device uses the first measurement result as input to the first model to obtain the first prediction result output by the first model.

[0160] Optionally, if the device performing model monitoring on the terminal side is an OTT system server, the terminal device may also send the first prediction result and / or the first measurement result to the OTT system server.

[0161] In another example, if the device performing model inference on the terminal side is an OTT system server, then in S710, the terminal device first obtains a first measurement result by measuring a first reference signal from the network device; then, the terminal device sends the first measurement result to the OTT system server. Correspondingly, after receiving the first measurement result, the OTT system server can obtain a first prediction result based on the first model and the first measurement result. In other words, the OTT system server uses the first measurement result as input to the first model to obtain the first prediction result output by the first model.

[0162] Optionally, if the device performing model monitoring on the terminal side is a terminal device, the OTT system server can also send the first prediction result to the terminal device after obtaining the first prediction result.

[0163] The following section, with reference to Figure 8, explains two possible modes for time series prediction on the terminal side using the first model.

[0164] In Mode 1, the temporal locations corresponding to two adjacent rounds of inference tasks executed by the terminal using the first model do not overlap. In other words, in two adjacent rounds of inference tasks executed by the terminal using the first model, the end time of the temporal location corresponding to the prediction result output by the previous round of inference task is no later than the start time of the temporal location corresponding to the measurement result used for the subsequent round of inference task. The non-overlapping temporal locations corresponding to two adjacent rounds of inference tasks executed by the terminal using the first model are equivalent to non-overlapping input data for two adjacent rounds of inference tasks executed by the terminal using the first model.

[0165] As shown in Figure 8(a), the measurement results used as inputs for the first round of inference tasks are M1 to M3, and the predicted output of the first round of inference tasks is P1; the measurement results used as inputs for the first round of inference tasks are M4 to M6, and the predicted output of the first round of inference tasks is P2. The time-domain positions corresponding to the first round of inference tasks are M1 to M3 and the time-domain positions corresponding to P1, while the time-domain positions corresponding to the second round of inference tasks are M4 to M6 and the time-domain positions corresponding to P2. The end time of the time-domain position corresponding to P1 is earlier than the start time of the time-domain position corresponding to M4, meaning the time-domain positions corresponding to the two rounds of inference tasks do not overlap.

[0166] In Mode 2, the temporal locations corresponding to two adjacent rounds of inference tasks executed by the terminal using the first model partially overlap. In other words, in two adjacent rounds of inference tasks executed by the terminal using the first model, the end time of the temporal location corresponding to the prediction result output by the previous round of inference task is later than the start time of the temporal location corresponding to the measurement result used for the subsequent round of inference task. When the temporal locations corresponding to two adjacent rounds of inference tasks executed by the terminal using the first model partially overlap, the input data corresponding to the two adjacent rounds of inference tasks executed by the terminal using the first model may also partially overlap.

[0167] As shown in Figure 8(b), the measurement results used as inputs for the first round of inference tasks are M1 to M3, and the predicted output of the first round of inference tasks is P3; the measurement results used as inputs for the first round of inference tasks are M2 to M4, and the predicted output of the first round of inference tasks is P4. The time-domain positions corresponding to the first round of inference tasks are the time-domain positions corresponding to M1 to P3, and the time-domain positions corresponding to the second round of inference tasks are the time-domain positions corresponding to M2 to P4. The end time of the time-domain position corresponding to P3 is later than the start time of the time-domain position corresponding to M2, meaning that the time-domain positions corresponding to the two rounds of inference tasks partially overlap.

[0168] It should be understood that Figure 8 is merely an example. This application does not limit the number of measurement results input to the first model and / or the number of prediction results output by the first model. Furthermore, the inputs and / or outputs corresponding to two adjacent rounds of inference tasks performed by the terminal through the first model may be inconsistent. For example, the number of inputs (i.e., the number of measurement results) and / or the number of outputs (i.e., the number of prediction results) corresponding to two adjacent rounds of inference tasks performed by the terminal through the first model may be different. As another example, the data types of the inputs and / or the output types corresponding to two adjacent rounds of inference tasks performed by the terminal through the first model may be different.

[0169] S720, the terminal side acquires the second measurement result.

[0170] The second measurement result corresponds to all or part of the time domain location after the time domain location corresponding to the first prediction result.

[0171] For example, the start time of the time-domain position corresponding to the second measurement result is after the end time of the time-domain position corresponding to the first prediction result. In other words, the time-domain position corresponding to the second measurement result does not overlap with the time-domain position corresponding to the first prediction result. An example where the time-domain positions corresponding to the first prediction result and the second measurement result do not overlap is: the first prediction result corresponds to time slot #a1, and the second measurement result corresponds to time slot #a2.

[0172] For example, the end time of the time-domain position corresponding to the second measurement result is after the end time of the time-domain position corresponding to the first prediction result. In other words, the time-domain position corresponding to the first prediction result and the time-domain position corresponding to the second measurement result may partially overlap. An example of partial overlap between the time-domain positions corresponding to the first prediction result and the second measurement result is as follows: the first prediction result corresponds to time slot #a1, and the second measurement result corresponds to time slots #a1 and #a2. Here, time slot #a2 is after time slot #a1.

[0173] Optionally, the interval between the end time of the time-domain position corresponding to the second measurement result and the end time of the time-domain position corresponding to the first prediction result is less than or equal to a seventh threshold. The seventh threshold can be a predefined threshold or a threshold indicated by the network side to the terminal side. For example, the network side sends information indicating the seventh threshold to the terminal side.

[0174] For example, the second measurement result is obtained by measuring a second reference signal.

[0175] Optionally, the time-domain location corresponding to the second measurement result can be replaced with the time-domain location corresponding to the resource used to transmit the second reference signal.

[0176] For example, the number of measurement results included in the second measurement result may be the same as or different from the number of measurement results included in the first measurement result, without limitation.

[0177] For example, the measurement results included in the second measurement result may be the same type of data as the measurement results included in the first measurement result, or they may be different types of data, without limitation.

[0178] For a more detailed description of the second measurement result, please refer to the relevant description of the first measurement result in S710 above.

[0179] Optionally, the second measurement result is used to obtain the second prediction result. The time-domain position corresponding to the second prediction result is after the time-domain position corresponding to the second measurement result, or the time-domain position corresponding to the second prediction result is the same as the time-domain position corresponding to the second measurement result; this application does not limit this. For example, the second measurement result is the channel matrix corresponding to time slot #b1, and the second prediction result is the channel matrix corresponding to time slot #b2, where time slot #b2 is after time slot #b1. As another example, both the second measurement result and the second prediction result correspond to time slot #c1, the second measurement result includes the RSRP of each beam in beam set B, and the second prediction result includes the RSRP of each beam in beam set A, where beam set B is a subset of beam set A.

[0180] For a more detailed description of the second prediction result, please refer to the relevant description of the first prediction result in S710 above.

[0181] S730: The terminal side obtains the monitoring result corresponding to the first prediction result based on the first measurement result and the second measurement result.

[0182] The monitoring results corresponding to the first prediction result are used to determine the credibility of the first prediction result. For example, the monitoring results may include information (such as MSE information) characterizing the similarity and / or difference between the first prediction result and the true value (or a measurement or predicted value close to the true value). Alternatively, the monitoring results may include information indicating whether the first prediction result is credible. Furthermore, the monitoring results may include the deviation of the similarity between the first prediction result and the true value (or a measurement or predicted value close to the true value) from a similarity threshold (e.g., above or below the similarity threshold), or the deviation of the difference between the first prediction result and the true value (or a measurement or predicted value close to the true value) from a difference threshold (e.g., above or below the difference threshold).

[0183] It should be understood that the credibility of the first prediction result can also be understood as the credibility of the first model, that is, the first model can be monitored by monitoring the first prediction result.

[0184] Based on the temporal relationship between the first measurement result, the first prediction result, and the second measurement result described above, an example of the terminal performing model monitoring (or performance monitoring) on ​​the first prediction result to obtain monitoring results is shown in Figure 9. Figure 9 shows an example of K1 preceding measurement values, K0 prediction values, and K2 subsequent measurement values ​​as the second measurement result. The terminal can perform performance monitoring on the K0 prediction values ​​based on the K1 preceding measurement values ​​and the K2 subsequent measurement values. K1, K2, and K0 are all positive integers.

[0185] In the embodiments of this application, the device used on the terminal side to perform model monitoring can be a terminal device or a device other than a terminal device, such as the aforementioned OTT system server. This application does not limit this.

[0186] As an example, if the device performing model monitoring on the terminal side is a terminal device, then in S730, the terminal device obtains the monitoring result corresponding to the first prediction result based on the first measurement result and the second measurement result.

[0187] Optionally, the terminal device can also send the monitoring results corresponding to the first prediction result to the OTT system server.

[0188] In another example, if the device performing model monitoring on the terminal side is an OTT system server, then in S730, the OTT system server obtains the monitoring result corresponding to the first prediction result based on the first measurement result and the second measurement result.

[0189] Optionally, the OTT system server can also send the monitoring results corresponding to the first prediction result to the terminal device.

[0190] In another example, if the devices performing model monitoring on the terminal side are a terminal device and an OTT system server, then in S730, the terminal device and the OTT system server obtain the monitoring result corresponding to the first prediction result based on the first measurement result and the second measurement result. For example, if the terminal side performs model monitoring based on a second model, and the second model is used to obtain one or more prediction results (such as the fourth prediction result described below) for determining the monitoring result corresponding to the first prediction result, then the model inference of the second model can be performed by the OTT system server, and then the terminal device obtains the monitoring result corresponding to the first prediction result based on the prediction results used to determine the monitoring result.

[0191] Optionally, prior to S730, the terminal can also acquire a third measurement result, the time domain position corresponding to the third measurement result preceding the time domain position corresponding to the first measurement result. Correspondingly, in S730, the terminal acquires the monitoring result corresponding to the first prediction result based on the first measurement result, the second measurement result, and the third measurement result. For a more detailed description of the third measurement result, please refer to the relevant description of the second measurement result above.

[0192] The following describes how the terminal side obtains the monitoring result corresponding to the first prediction result based on the first measurement result and the second measurement result.

[0193] In implementation method 1, the terminal side obtains monitoring results based on the first measurement result and the second measurement result, including: the terminal side obtains a third prediction result based on the first measurement result, and the time domain position corresponding to the third prediction result is the same as the time domain position corresponding to the second measurement result; the terminal side obtains monitoring results based on the third prediction result and the second measurement result.

[0194] The terminal side obtains the third prediction result based on the first measurement result, including: the terminal side obtains the third prediction result based on the first model and the first measurement result; or, the terminal side obtains the third prediction result based on another model different from the first model (such as a fourth model). The method by which the terminal side obtains the third prediction result based on the model and the first measurement result can be referred to the description of the method by which the terminal side obtains the first prediction result in S710 above.

[0195] For example, the third prediction result includes one or more prediction results. Optionally, the number of prediction results included in the third prediction result is related to the accuracy requirements of model monitoring. For example, if the accuracy requirements of model monitoring are relatively high, such as requiring monitoring the performance of the first model over a long period of time, the third prediction result may include Y1 prediction results, where Y1 is a positive integer greater than 1. As another example, if the accuracy requirements of model monitoring are relatively low, such as requiring monitoring the performance of the first model over a short period of time, the third prediction result may include Y2 prediction results, where Y2 is a positive integer greater than or equal to 1, and Y1 is greater than or equal to Y2.

[0196] Optionally, if the terminal device also obtains a third measurement result, the terminal side can obtain a third prediction result based on the first measurement result and the third measurement result.

[0197] For example, the terminal side obtains monitoring results based on the third prediction result and the second measurement result, including: the terminal side obtains monitoring results based on the difference and / or similarity between the third prediction result and the second measurement result.

[0198] It should be understood that if the prediction results included in the third prediction result are the same type of data as the measurement results included in the second measurement result, the terminal side can directly determine the degree of difference and / or similarity between the third prediction result and the second measurement result.

[0199] It should also be understood that if the predicted results included in the third prediction result are different types of data from the measurement results included in the second measurement result, the terminal first processes the third prediction result so that the predicted results included in the processed third prediction result #1 are of the same type as the measurement results included in the second measurement result. Then, the terminal obtains the monitoring result based on the difference and / or similarity between the third prediction result #1 and the second measurement result. Alternatively, if the predicted results included in the third prediction result are different types of data from the measurement results included in the second measurement result, the terminal first processes the second measurement result so that the measurement results included in the processed second measurement result #1 are of the same type as the predicted results included in the third prediction result. Then, the terminal obtains the monitoring result based on the difference and / or similarity between the third prediction result and the second measurement result #1.

[0200] For example, if the third prediction result includes a channel matrix and the second measurement result includes a channel feature matrix, the terminal can process the third prediction result so that the processed third prediction result #1 includes a channel feature matrix; or, the terminal can process the second measurement result so that the processed second measurement result #1 includes a channel matrix.

[0201] For example, the monitoring results obtained by the terminal side based on the difference and / or similarity between the third prediction result and the second measurement result may include one or more of the following:

[0202] The first difference information between the third prediction result and the second measurement result, and / or the deviation between the first difference information and the first threshold;

[0203] The first MSE information between the third prediction result and the second measurement result, and / or the deviation between the first MSE information and the second threshold;

[0204] The first NMSE information between the third prediction result and the second measurement result, and / or the deviation between the first NMSE information and the third threshold;

[0205] The first MAE information between the third prediction result and the second measurement result, and / or the deviation between the first MAE information and the fourth threshold;

[0206] The first GCS information between the third prediction result and the second measurement result, and / or the deviation between the first GCS information and the fifth threshold; or...

[0207] The first SGCS information between the third prediction result and the second measurement result, and / or the deviation between the first SGCS information and the sixth threshold.

[0208] For example, if the third prediction result and the second measurement result are channel matrices, then the monitoring result may include one or more of the following: first MSE information, the deviation between the first MSE information and the second threshold, first NMSE information, the deviation between the first NMSE information and the third threshold, first MAE information, the deviation between the first MAE information and the fourth threshold, first GCS information, the deviation between the first GCS information and the fifth threshold, first SGCS information, or the deviation between the first SGCS information and the sixth threshold.

[0209] For example, if the third prediction result and the second measurement result are RSRP, SINR, or the probability corresponding to PMI and PMI, then the monitoring result may include one or more of the following: first difference information, the deviation between the first difference information and the first threshold.

[0210] It should be understood that the monitoring results obtained by the terminal side based on the third prediction result and the second measurement result may also be other information or function values ​​that characterize the degree of difference and / or similarity, and this application does not impose any restrictions on this.

[0211] It should also be understood that preprocessing operations can be performed on the third prediction result and / or the second measurement result before the monitoring result is obtained on the terminal side, such as taking the logarithm, converting the numerical value to a decibel value, etc. This application does not impose any restrictions on this.

[0212] The following example, using the third prediction result comprising T prediction results #a and the second measurement result comprising T measurement results #a, illustrates the monitoring results described above. There is a one-to-one correspondence between the T prediction results #a and the T measurement results #a, and the corresponding prediction results #a and measurement results #a correspond to the same time-domain location. For example, if the t-th prediction result #a in the T prediction results #a corresponds to the t-th measurement result #a in the T measurement results #a, then the t-th prediction result #a corresponds to the t-th measurement result #a. T is a positive integer, and t is a positive integer less than or equal to T. The measurement result #a corresponding to the prediction result #a can be called the true value corresponding to the prediction result #a. The corresponding prediction result #a and measurement result #b can be called a control group.

[0213] For example, the first difference information may include one or more of the following: the difference (or absolute value of the difference) between the predicted result #a and the measured result #a in any control group, the sum of the absolute values ​​of the differences between the predicted result #a and the measured result #a in at least two control groups, the mean of the absolute values ​​of the differences between the predicted result #a and the measured result #a in at least two control groups, the maximum value among the absolute values ​​of the differences between the predicted result #a and the measured result #a in at least two control groups, the sum of the squares of the differences between the predicted result #a and the measured result #a in at least two control groups, the mean of the squares of the differences between the predicted result #a and the measured result #a in at least two control groups, or the maximum value among the squares of the differences between the predicted result #a and the measured result #a in at least two control groups.

[0214] Taking two control groups as an example, the sum of the absolute values ​​of the differences between the predicted result #a and the measured result #a in the two control groups can be expressed as: |predicted result #a1 - measured result #a1| + |predicted result #a2 - measured result #a2|. Here, predicted result #a1 corresponds to measured result #a1, and predicted result #a1 and measured result #a1 form one control group. Predicted result #a2 corresponds to measured result #a2, and predicted result #a2 and measured result #a2 form the other control group.

[0215] The first threshold can represent a range that one or more of the aforementioned first difference information should satisfy. For example, if the first threshold is the upper limit of the absolute value of the difference between the predicted result and the corresponding true value, then if the absolute value of the difference between the predicted result #a and the measurement result #a in any of the aforementioned control groups is less than or equal to the first threshold, the monitoring result is used to determine that the first predicted result is credible, or to determine that the credibility of the first predicted result is greater than or equal to the credibility threshold. If the absolute value of the difference between the predicted result #a and the measurement result #a in any of the aforementioned control groups is greater than the first threshold, the monitoring result is used to determine that the first predicted result is unreliable, or to determine that the credibility of the first predicted result is less than the credibility threshold. Alternatively, if the deviation between the first difference information included in the monitoring result and the first threshold is positive (i.e., the first difference information is greater than the first threshold), the monitoring result is used to determine that the first predicted result is unreliable. If the deviation between the first difference information included in the monitoring result and the first threshold is 0 or negative (i.e., the first difference information is less than or equal to the first threshold), the monitoring result is used to determine that the first predicted result is credible.

[0216] Optionally, the aforementioned first difference information may include or be replaced by: the number of control groups in the T control groups that satisfy condition #a, and / or, the proportion of the T control groups that satisfy condition #a in the T control groups. Condition #a is: the difference (or the absolute value or square of the difference) between the predicted result #a and the measured result #a in the control group meets the range that the difference (or the absolute value or square of the difference) should satisfy. For example, condition #a is: the absolute value of the difference between the predicted result #a and the measured result #a in the control group is less than or equal to threshold #a, where threshold #a is the upper limit of the absolute value of the difference between the predicted result and the true value corresponding to the predicted result. Accordingly, the aforementioned first threshold may include: the range that the number of control groups in the T control groups that satisfy the above condition #a should satisfy, and / or, the range that the proportion of the T control groups that satisfy the above condition #a in the T control groups should satisfy.

[0217] Optionally, if the prediction result #a includes P predicted values ​​#a and the measurement result #a includes P measured values ​​#a, where P is a positive integer, then the difference between the prediction result #a and the measurement result #a in a control group is any one of the following: the difference (or absolute value of the difference) between any group of corresponding predicted values ​​#a and measured values ​​#a, the sum of the absolute values ​​of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a, the mean of the absolute values ​​of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a, the maximum value of the absolute values ​​of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a, the sum of the squares of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a, the mean of the squares of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a, or the maximum value of the squares of the differences between at least two groups of corresponding predicted values ​​#a and measured values ​​#a.

[0218] In this context, a set of corresponding measured values ​​#a and predicted values ​​#a correspond to the same beam or PMI. For example, a set of corresponding predicted values ​​#a and measured values ​​#a are the RSRP values ​​corresponding to the same beam. Another example is that a set of corresponding predicted values ​​#a and measured values ​​#a are both probabilities corresponding to the same PMI.

[0219] Let a set of corresponding predicted values ​​#a and measured values ​​#a be denoted as a control group #a. Assuming that P measured values ​​#a and P predicted values ​​#a can form P control groups #a, the difference between the predicted result #a and the measured result #a in a control group can include or be replaced by: the number of control groups #a that satisfy condition #b in the P control groups #a, and / or the proportion of control groups #a that satisfy condition #b in the P control groups #a. Condition #b is: the difference (or the absolute value or square of the difference) between the predicted value #a and the measured value #a in the control group #a satisfies the range that the difference (or the absolute value or square of the difference) should satisfy. For example, condition #b is: the absolute value of the difference between the predicted value #a and the measured value #a in the control group #a is less than or equal to a threshold #b, where the threshold #b is the upper limit of the absolute value of the difference between the predicted value and the corresponding true value. Accordingly, the first threshold may include: the range that the number of control groups #a that meet the above condition #b among the P control groups #a should satisfy, and / or the range that the proportion of control groups #a that meet the above condition #b among the P control groups #a should satisfy.

[0220] For example, the first MSE information may include one or more of the following: the MSE between the predicted result #a and the measured result #a in any control group, the sum of the MSEs between the predicted result #a and the measured result #a in at least two control groups, the mean of the MSEs between the predicted result #a and the measured result #a in at least two control groups, and the maximum value of the MSEs between the predicted result #a and the measured result #a in at least two control groups.

[0221] Taking two control groups as an example, the sum of the MSE between the predicted result #a and the measured result #a in the two control groups can be expressed as: MSE(predicted result #a1, measured result #a1) + MSE(predicted result #a2, measured result #a2).

[0222] The second threshold can represent the range that one or more of the first MSE information should satisfy. For example, if the second threshold is the upper limit of the MSE between the predicted result and the corresponding true value, then if the MSE between the predicted result #a and the measurement result #a in any of the control groups included in the monitoring result is less than or equal to the second threshold, the monitoring result is used to determine that the first prediction result is reliable, or to determine that the reliability of the first prediction result is greater than or equal to the reliability threshold. If the MSE between the predicted result #a and the measurement result #a in any of the control groups included in the monitoring result is greater than the second threshold, the monitoring result is used to determine that the first prediction result is unreliable, or to determine that the reliability of the first prediction result is less than the reliability threshold. Alternatively, if the deviation between the first MSE information included in the monitoring result and the second threshold is positive (i.e., the first MSE information is greater than the second threshold), the monitoring result is used to determine that the first prediction result is unreliable. If the deviation between the first MSE information included in the monitoring result and the second threshold is 0 or negative (i.e., the first MSE information is less than or equal to the second threshold), the monitoring result is used to determine that the first prediction result is reliable.

[0223] Optionally, the first MSE information mentioned above may include or be replaced by: the number of control groups in the T control groups that meet condition #c, and / or the proportion of the T control groups that meet condition #c in the T control groups. Condition #c is: the MSE between the predicted result #a and the measured result #a in the control group meets the range that the MSE should satisfy. For example, condition #c is: the absolute value of the MSE between the predicted result #a and the measured result #a in the control group is less than or equal to the threshold #c, where the threshold #c is the upper limit of the MSE between the predicted result and the true value corresponding to the predicted result. Accordingly, the second threshold mentioned above may include: the range that the number of control groups in the T control groups that meet the above condition #c should satisfy, and / or the range that the proportion of the T control groups that meet the above condition #c in the T control groups should satisfy.

[0224] For further descriptions of the first NMSE information, first MAE information, first GCS information, or first SGCS information, please refer to the above description of the first MSE information, which will not be repeated here.

[0225] The following section, with reference to Figure 10, explains the method of model monitoring on the terminal side based on implementation method 1.

[0226] As shown in Figure 10, the first measurement result obtained by the terminal side may include M1 to M3, the first prediction result obtained by the terminal side based on the first measurement result is P1, and the third prediction result obtained based on the first measurement result may include PM4 to PM6. The second measurement result obtained by the terminal side may include M4 to M6. M4 and PM4 correspond to the same time-domain location, PM5 and M5 correspond to the same time-domain location, and PM6 and M6 correspond to the same time-domain location. The terminal side can obtain the monitoring result corresponding to P1 by comparing M4 with PM4, comparing M5 with PM5, and comparing M6 with PM6.

[0227] For example, if M4 to M6 and PM4 to PM6 are both RSRP values, the monitoring results obtained by the terminal side may include one or more of the following: the difference between RSRP values ​​of M4 and PM4 corresponding to the same beam (denoted as difference #1), the difference between RSRP values ​​of M5 to PM5 corresponding to the same beam (denoted as difference #2), the difference between RSRP values ​​of M6 and PM6 corresponding to the same beam (denoted as difference #3), the sum of the absolute values ​​of difference #1 to difference #3, the average of the absolute values ​​of difference #1 to difference #3, and the maximum value among the absolute values ​​of difference #1 and difference #3.

[0228] For example, if M4 to M6 and PM4 to PM6 are both channel matrices, then the monitoring results obtained by the terminal side may include one or more of the following: the MSE between M4 and PM4 (denoted as MSE#1), the MSE between M5 and PM5 (denoted as MSE#2), the MSE between M6 and PM6 (denoted as MSE#3), the sum of MSE#1 to MSE#3, the mean of MSE#1 to MSE#3, and the maximum value among MSE#1 to MSE#3. MSE can be replaced with NMSE, MAE, GCS, or SGCS.

[0229] For example, if M4 to M6 and PM4 to PM6 are all PMIs, the monitoring results obtained by the terminal side may include one or more of the following: the difference between the probabilities of M4 and PM4 corresponding to the same PMI (denoted as difference #4), the difference between the probabilities of M5 and PM5 corresponding to the same PMI (denoted as difference #5), the difference between the probabilities of M6 and PM6 corresponding to the same PMI (denoted as difference #6), the sum of the absolute values ​​of difference #4 to difference #6, the mean of the absolute values ​​of difference #4 to difference #6, and the maximum value among the absolute values ​​of difference #4 and difference #6.

[0230] Implementation method 2: The terminal side obtains monitoring results based on the first measurement result and the second measurement result, including: the terminal side obtains monitoring results based on the first measurement result, the second measurement result and the second model.

[0231] The following examples 2A to 2B illustrate how the terminal side obtains monitoring results based on the first measurement result, the second measurement result, and the second model.

[0232] Example 2A: The terminal side obtains monitoring results based on the first measurement result, the second measurement result, and the second model, including: the terminal side obtains a fourth prediction result based on the first measurement result, the second measurement result, and the second model; the terminal side obtains monitoring results based on the fourth prediction result and the first prediction result. The time domain location corresponding to the fourth prediction result is the same as the time domain location corresponding to the first prediction result.

[0233] The process of obtaining the fourth prediction result on the terminal side includes: the terminal side using the first measurement result and the second measurement result as inputs to the second model, thereby obtaining the output of the second model as the fourth prediction result.

[0234] Optionally, if the terminal also obtains a third measurement result, the terminal obtains a fourth prediction result based on the first, second, and third measurement results and the second model. In other words, the terminal can use the first, second, and third measurement results as inputs to the second model, thereby obtaining the output of the second model as the fourth prediction result.

[0235] Optionally, the terminal side obtains the fourth prediction result by: obtaining a first prediction result based on a first measurement result and a first model; and obtaining a fourth prediction result based on the first prediction result, a second measurement result, and a second model. In other words, the terminal side first uses the first measurement result as the input to the first model to obtain the output of the first model as the first prediction result. Then, the terminal side uses the first prediction result and the second measurement result as the output of the second model to obtain the output of the second model as the fourth prediction result.

[0236] Optionally, if the terminal also obtains a third measurement result, the terminal can obtain a fourth prediction result based on the first prediction result, the second measurement result, the third measurement result, and the second model. In other words, the terminal can use the first prediction result, the second measurement result, and the third measurement result as inputs to the second model, thereby obtaining the output of the second model as the fourth prediction result.

[0237] For example, the terminal side obtains monitoring results based on the fourth prediction result and the first prediction result, including: the terminal side obtains monitoring results based on the difference and / or similarity between the fourth prediction result and the first prediction result.

[0238] It should be understood that if the prediction results included in the fourth prediction result are of the same type as those included in the first prediction result, the terminal side can directly determine the degree of difference and / or similarity between the fourth prediction result and the first prediction result.

[0239] It should also be understood that if the prediction results included in the fourth prediction result are of different types from the prediction results included in the first prediction result, then the terminal side first processes the fourth prediction result so that the prediction results included in the processed fourth prediction result #1 are of the same type as the measurement results included in the first prediction result; or, the terminal side first processes the first prediction result so that the prediction results included in the processed first prediction result #1 are of the same type as the prediction results included in the fourth prediction result.

[0240] For example, the monitoring results obtained by the terminal side based on the difference and / or similarity between the fourth prediction result and the first prediction result may include one or more of the following:

[0241] The second difference information between the fourth prediction result and the first prediction result, and / or the deviation between the second difference information and the first threshold;

[0242] The second MSE information between the fourth prediction result and the first prediction result, and / or the deviation between the second MSE information and the second threshold;

[0243] The second NMSE information between the fourth prediction result and the first prediction result, and / or the deviation between the second NMSE information and the third threshold;

[0244] The second MAE information between the fourth prediction result and the first prediction result, and / or the deviation between the second MAE information and the fourth threshold;

[0245] The second GCS information between the fourth prediction result and the first prediction result, and / or the deviation between the second GCS information and the fifth threshold; or,

[0246] The second SGCS information between the fourth prediction result and the first prediction result, and / or the deviation between the second SGCS information and the sixth threshold.

[0247] For example, if the fourth prediction result and the first prediction result are channel matrices, then the monitoring result may include one or more of the following: second MSE information, the deviation between the second MSE information and the second threshold, second NMSE information, the deviation between the second NMSE information and the third threshold, second MAE information, the deviation between the second MAE information and the fourth threshold, second GCS information, the deviation between the second GCS information and the fifth threshold, second SGCS information, or the deviation between the second SGCS information and the sixth threshold.

[0248] For example, if the fourth prediction result and the first prediction result are the probabilities corresponding to RSRP, SINR, or PMI and PMI, then the monitoring result may include one or more of the following: second difference information, and the deviation between the second difference information and the first threshold.

[0249] For more details on the second difference information, second MSE information, second NMSE information, second MAE information, second GCS information, or second SGCS information, please refer to the above descriptions of the first difference information, first MSE information, first NMSE information, first MAE information, first GCS information, or first SGCS information.

[0250] It should be understood that the monitoring results obtained by the terminal side based on the fourth prediction result and the first prediction result can also be other information or function values ​​that represent the degree of difference and / or similarity, and this application does not impose any restrictions on this.

[0251] It should also be understood that preprocessing operations can be performed on the fourth prediction result and / or the first prediction result before the monitoring results are obtained on the terminal side, such as taking the logarithm, converting the numerical value to a decibel value, normalizing, etc. This application does not impose any restrictions on this.

[0252] The following section, with reference to Figure 11, explains the method of model monitoring on the terminal side based on Example 2A.

[0253] As shown in Figure 11, the first measurement result acquired by the terminal side may include M1 to M3, and the first prediction result acquired by the terminal side based on the first measurement result is P1. The second measurement result acquired by the terminal side may include M4 to M6. The fourth prediction result acquired by the terminal side based on the first and second measurement results is PP1. P1 and PP1 correspond to the same time-domain location. The terminal side can obtain the monitoring result corresponding to P1 by comparing P1 and PP1.

[0254] For example, if P1 and PP1 are both RSRP values, the monitoring results obtained by the terminal side may include one or more of the following: the sum of the absolute values ​​of the differences between the RSRP values ​​corresponding to the same beam included in P1 and PP1, the mean of the absolute values ​​of the differences between the RSRP values ​​corresponding to the same beam included in P1 and PP1, or the maximum value among the absolute values ​​of the differences between the RSRP values ​​corresponding to the same beam included in P1 and PP1.

[0255] For example, if P1 and PP1 are both channel matrices, the monitoring results obtained by the terminal side may include one or more of the following: MSE between P1 and PP1, NMSE between P1 and PP1, MAE between P1 and PP1, GCS between P1 and PP1, or SGCS between P1 and PP1.

[0256] For example, if both P1 and PP1 are PMIs, the monitoring results obtained by the terminal side may include one or more of the following: the sum of the absolute values ​​of the differences between the probabilities of P1 and PP1 corresponding to the same PMI, the mean of the absolute values ​​of the differences between the probabilities of P1 and PP1 corresponding to the same PMI, or the maximum value among the absolute values ​​of the differences between the probabilities of P1 and PP1 corresponding to the same PMI.

[0257] It should be understood that Figure 11 illustrates the second model with inputs M1 to M6 as an example. In one possible implementation, the inputs to the second model can be P1 and M4 to M6. In another possible implementation, the inputs to the second model can include measurement results M0 (an example of a third measurement result) acquired by the terminal side before M1. For example, the inputs to the second model include M0 to M6. Or, the inputs to the second model include M0, P1, and M4 to M6.

[0258] Example 2B: The terminal side obtains monitoring results based on the first measurement result, the second measurement result, and the second model, including: the terminal side obtains a first prediction result based on the first measurement result; the terminal side obtains monitoring results based on the first prediction result, the second measurement result, and the second model.

[0259] Specifically, the terminal side obtains monitoring results based on the first prediction result, the second measurement result, and the second model, including: the terminal side uses the first prediction result and the second measurement result as input to the second model, thereby obtaining the output of the second model as the monitoring result.

[0260] Optionally, if the terminal also obtains a third measurement result, the terminal obtains the monitoring result based on the first prediction result, the second measurement result, the third measurement result, and the second model. In other words, the terminal can use the first prediction result, the second measurement result, and the third measurement result as inputs to the second model, thereby obtaining the monitoring result as the output of the second model.

[0261] For example, the monitoring results output by the second model may include one or more of the following: MSE value, NMSE value, MAE value, GCS value, SGCS value, difference, deviation between the difference and the first threshold, deviation between the MSE value and the second threshold, deviation between the NMSE value and the third threshold, deviation between the MAE value and the fourth threshold, deviation between the GCS value and the fifth threshold, deviation between the SGCS value and the sixth threshold, information indicating that the first prediction result is unreliable, information indicating that the first prediction result is reliable, reliability of the first prediction result, and deviation between the reliability of the first prediction result and the reliability threshold.

[0262] The following section, with reference to Figure 12, explains the method of model monitoring on the terminal side based on Example 2B.

[0263] As shown in Figure 12, the first measurement results acquired by the terminal side may include M1 to M3, and the first prediction result acquired by the terminal side based on the first measurement results is P1. The second measurement results acquired by the terminal side may include M4 to M6. The terminal side can use P1 and M4 to M6 as inputs to the second model, thereby obtaining the monitoring result as the output of the second model.

[0264] It should be understood that Figure 12 illustrates the second model with P1 and M4 to M6 as inputs. In one possible implementation, the inputs to the second model can be M1 to M6. In other words, the terminal can use the first and second measurement results as inputs to the second model, thereby obtaining the monitoring results as the output of the second model. In another possible implementation, the inputs to the second model can include measurement result M0 (an example of the third measurement result) acquired by the terminal before M1. For example, the inputs to the second model include M0, P1, and M4 to M6. Or, the inputs to the second model include M0 to M6. Optionally, method 700 also includes S740.

[0265] S740, the terminal side sends monitoring results.

[0266] Correspondingly, the network side receives the monitoring results.

[0267] It should be understood that the terminal side sends the monitoring results to the network side at least after the end time of the time domain position corresponding to the second measurement result.

[0268] As an example, the device performing model monitoring is a terminal device. Specifically, S740 may include: the terminal device sending monitoring results to the network device, such as sending them over the air interface; or, the OTT system server sending monitoring results to the intelligent network element, such as sending them over the wired network. The monitoring results may be sent from the terminal device to the OTT system server.

[0269] In another example, the device performing model monitoring is an OTT system server. Specifically, the S740 may include: the OTT system server sending monitoring results to the intelligent network element; or, the terminal device sending monitoring results to the network device, whereby the monitoring results may be sent from the OTT system server to the terminal device.

[0270] It should be understood that in one possible implementation, the terminal side can process the monitoring results before sending them, such as through quantization, normalization, or encoding. This application does not impose any restrictions on this. In other words, the monitoring results sent by the terminal side are the processed monitoring results.

[0271] It should also be understood that, in one possible implementation, the terminal can send the monitoring results corresponding to each of the multiple rounds of prediction tasks to the network side, or send statistical information obtained by the terminal side based on the monitoring results corresponding to each of the multiple rounds of prediction tasks, such as one or more of the following statistical information: the mean, maximum, minimum, variance, percentile, etc., of the monitoring results corresponding to each of the multiple rounds of prediction tasks. The number of rounds of the multiple rounds of prediction tasks can be agreed upon in advance by the terminal side and the network side, or determined by the terminal side or configured by the network side (for example, the number of rounds of prediction tasks within the time period configured based on the second information in S760 below). The monitoring results corresponding to the prediction tasks refer to the monitoring results corresponding to the prediction results output by the prediction tasks.

[0272] In this embodiment, the terminal can monitor the reliability of the prediction result based on the measurement results obtained after the prediction result. This avoids the resource consumption caused by the network sending reference signals for monitoring the reliability of the prediction result at the time domain position corresponding to the prediction result, and also avoids the measurement power consumption caused by the terminal performing measurements at the time domain position corresponding to the prediction result. Furthermore, based on this embodiment, the terminal can continuously monitor the reliability of the prediction result based on the measurement results obtained after the prediction result during model operation. This allows the terminal and / or network to promptly detect when the model's performance does not meet requirements, and thus promptly update, switch, or rollback the model.

[0273] Optionally, prior to S710, method 700 may also include one or more steps from S750 to S780.

[0274] S750, the network side sends the first information.

[0275] Accordingly, the terminal receives the first information.

[0276] For example, the first information is used to instruct the execution of model monitoring. Accordingly, the terminal side can execute model monitoring based on the instruction of the first information.

[0277] Optionally, the first information may also include information about the first model. When the first information includes information about the first model, it is equivalent to the first information being used to instruct model monitoring to be performed on the first model.

[0278] The information of the first model may include one or more of the following: the identifier (ID) of the first model and / or the function of the first model. For example, the function of the first model is time series prediction. The information of the first model may also include other information used to identify the first model. For example, the information of the first model may include the identifier of the dataset used to train the model to obtain the first model.

[0279] For example, the terminal side performs model monitoring to obtain the monitoring results described in S730.

[0280] In the embodiments of this application, the device used on the terminal side to perform model monitoring can be a terminal device or a device other than a terminal device, such as the aforementioned OTT system server. This application does not limit this.

[0281] As an example, the device performing model monitoring is a terminal device. Specifically, the S750 may include: the terminal device receiving first information from the network device, for example, receiving it through the air interface; or, the terminal device receiving first information from the OTT system server, which is sent by the intelligent network element on the network side to the OTT system server, for example, sent through a wired network.

[0282] Another example is that the device performing model monitoring is an OTT system server. Specifically, the S750 may include: the OTT system server receiving first information from the intelligent network element, such as receiving it through a wired network; or, the OTT system server receiving first information from the terminal device, which is sent from the network device to the terminal device, such as being sent through the air interface.

[0283] In summary, whether the terminal device receives the first information or the OTT system server receives the first information, the first information always originates from the network side.

[0284] It should be noted that S750 is an optional step. For example, if the network side and the terminal side agree in advance, or if the terminal side defaults to monitoring the model deployed on the terminal side, then method 700 may not include S750.

[0285] S760, the network side sends the second information.

[0286] Accordingly, the terminal receives the second information.

[0287] For example, the second information is used to indicate the time period for performing model monitoring.

[0288] This application does not limit the time period for which the second information instruction execution model is monitored.

[0289] For example, the second information may include one or more of the following: the start time of the time period monitored by the execution model, the end time of the time period monitored by the execution model, and the duration of the time period monitored by the execution model.

[0290] For example, if the second information includes the start time of the time period for monitoring the execution model, and the end time or duration of the time period for monitoring the execution model is predefined, the terminal can determine the time period for monitoring the execution model based on the second information. For instance, the end time of the predefined time period for monitoring the execution model could be the time when the model is deactivated, turned off, switched, or rolled back.

[0291] For another example, if the second information includes the end time of the time period for monitoring the execution model, then if the start time or duration of the time period for monitoring the execution model is predefined, the terminal can determine the time period for monitoring the execution model based on the second information. For instance, the start time of the predefined time period for monitoring the execution model could be the moment when the model inference is first performed.

[0292] For example, the second information may include information about reference signal resources, which is used to determine the time period for model monitoring. For instance, the time period for model monitoring relates to the time domain resources of the reference signal resources.

[0293] For example, if the time domain resources of the reference signal resources include time slot x to time slot y, then the time period for performing model monitoring is from time slot x to time slot y.

[0294] The information of the reference signal resource may include one or more of the following: the ID of the reference signal resource, the ID of the beam corresponding to the reference signal resource, the serial number of the reference signal resource in the reference signal resource set to which the reference signal resource belongs, or the ID of the reporting configuration corresponding to the reference signal resource.

[0295] Optionally, the reference signal resources include actually configured resources and / or unconfigured resources. For example, the actually configured resources included in the reference signal resources may be resources used to transmit a first reference signal, which is used to determine the first measurement result described above.

[0296] Similar to S750, in one example, if the device performing model monitoring on the terminal side is a terminal device, then S760 may include: the terminal device receiving second information from a network device, or the terminal device receiving second information from an OTT server, where the second information may be sent from a network-side intelligent network element to the OTT system server. In another example, if the device performing model monitoring on the terminal side is an OTT system server, then S760 may include: the OTT system server receiving second information from an intelligent network element, or the OTT system server receiving second information from a terminal device, where the second information may be sent from a network device to the terminal device.

[0297] It should be noted that S760 is an optional step. For example, if the terminal performs model monitoring within a predefined or user-defined time period, then method 700 may not include S760.

[0298] S770, the network side sends third information.

[0299] Correspondingly, the terminal receives third information.

[0300] For example, third-party information is used to indicate performance metrics, which are used for model monitoring. Performance metrics can also be called monitoring metrics.

[0301] For example, the performance metric refers to the range of performance requirements that the similarity between the model's output and the true value should meet, or the range of performance requirements that the difference between the model's output and the true value should meet. The true value can be obtained through measurement or through model inference. The true value obtained through model inference can be considered as a predicted value that is infinitely close to the true value (or the difference between it and the true value is less than a preset threshold, or the similarity between it and the true value is higher than a preset threshold). This application does not limit this.

[0302] The similarity and / or difference between the model's output and the true value can be characterized by one or more of the following: MSE information between the model's output and the true value, NMSE information between the model's output and the true value, MAE information between the model's output and the true value, GCS information between the model's output and the true value, SGCS information between the model's output and the true value, or difference information between the model's output and the true value.

[0303] The MSE information between the model's output and the true value can include one or more of the following: the MSE between a single output of the model and a single true value, the mean of the MSEs between each of the model's N outputs and the true value, the sum of the MSEs between each of the model's N outputs and the true value, and the maximum value among the MSEs between each of the model's N outputs and the true value. N is an integer greater than 1.

[0304] The NMSE, MAE, GCS, or SGCS information between the model's output and the true value can be found in the description of the MSE information, and will not be repeated here.

[0305] The difference information between the model's output and the true value can include one or more of the following: the difference (or the absolute value of the difference) between a model's output and a true value, the mean of the absolute values ​​of the differences between the model's N outputs and the true value, the sum of the absolute values ​​of the differences between the model's N outputs and the true value, the maximum value among the absolute values ​​of the differences between the model's N outputs and the true value, the sum of the squares of the differences between the model's N outputs and the true value, the mean of the squares of the differences between the model's N outputs and the true value, the maximum value among the squares of the differences between the model's N outputs and the true value, and the statistical value of the differences between the model's N outputs and the true value.

[0306] The statistical values ​​of the differences between the model's N outputs and the true value can include: the number of outputs that satisfy the first condition among the model's N outputs, and / or the percentage of the N outputs that satisfy the first condition. The first condition is: the difference between the output and the true value (or the absolute value or square of the difference) meets the range that the difference (or the absolute value or square of the difference) should satisfy. For example, the first condition is: the absolute value of the difference between the output and the true value is less than or equal to threshold #1, where threshold #1 is the upper limit of the absolute value of the difference between the output and the true value.

[0307] Taking the first model as an example, if the output of the first model is a channel matrix, the similarity and / or difference between the output of the first model and the true value can be characterized by one or more of the following: MSE information between the output of the first model and the true value, NMSE information between the output of the first model and the true value, MAE information between the output of the first model and the true value, GCS information between the output of the first model and the true value, and SGCS information between the output of the first model and the true value. If the output of the first model is RSRP, the similarity and / or difference between the output of the first model and the true value can be characterized by the difference information between the output of the first model and the true value. If the output of the first model is PMI, the similarity and / or difference between the output of the first model and the true value can be characterized by the difference information between the probability corresponding to the PMI in the output of the first model and the probability corresponding to the PMI in the true value.

[0308] For example, as described above, the performance metric refers to the range of performance requirements that the similarity and / or difference between the model's output and the true value should meet. Therefore, the third information indicates the performance metric, including: the third information indicates the manner in which the similarity and / or difference between the model's output and the true value is characterized, and the range that the similarity and / or difference between the model's output and the true value should meet.

[0309] For example, the third information may include an identifier of the method used to characterize the similarity and / or difference between the model's output and the true value. For instance, if the identifier of the method used to characterize the similarity and / or difference between the model's output and the true value through MSE information is identifier #1, then if the third information includes identifier #1, it indicates that the third information is used to indicate that during the model monitoring process, the similarity and / or difference between the model's output and the true value is characterized through MSE information.

[0310] For example, the third information may include an identifier, number, or index corresponding to the performance requirement range that the similarity and / or difference between the model's output and the true value should meet. For instance, if SGCS ≥ 0.8 corresponds to identifier #2, then if the third information includes identifier #2, it indicates that the third information is used to indicate that the SGCS between the model's output and the true value should be greater than or equal to 0.8. In other words, if the SGCS between the model's output and the true value is greater than or equal to 0.8, it means that the model's performance meets the requirements, and correspondingly, the model's output is reliable or the reliability of the model's output is greater than or equal to the reliability threshold. Conversely, if the SGCS between the model's output and the true value is less than 0.8, it means that the model's performance does not meet the requirements, and correspondingly, the model's output is unreliable or the reliability of the model's output is less than the reliability threshold.

[0311] Similar to S750, in one example, if the device performing model monitoring on the terminal side is a terminal device, then S770 may include: the terminal device receiving third information from the network device, or the terminal device receiving third information from the OTT server, where the third information may be sent from the network-side intelligent network element to the OTT system server. In another example, if the device performing model monitoring on the terminal side is an OTT system server, then S770 may include: the OTT system server receiving third information from the intelligent network element, or the OTT system server receiving third information from the terminal device, where the third information may be sent from the network device to the terminal device.

[0312] It should be noted that S770 is an optional step. For example, if the terminal side performs model monitoring based on predefined or user-defined performance metrics, then method 700 may not include S770.

[0313] S780, the network side sends the fourth message.

[0314] Accordingly, the terminal receives the fourth piece of information.

[0315] For example, the fourth information is used to indicate that the time for reporting the monitoring results is no earlier than the first time, and the monitoring results are used to determine the confidence level of the first prediction result. In one possible implementation, the fourth information is used to indicate the time for reporting the monitoring results.

[0316] Specifically, the first moment is not earlier than the end time of the time-domain position corresponding to the measurement result used to determine the monitoring result. It should be understood that in this embodiment, the terminal side determines the reliability of the target prediction result based on the measurement result obtained after the first prediction result; therefore, the first moment is not earlier than the end time of the time-domain position corresponding to the earliest measurement result obtained after the first prediction result. For example, the first moment is not earlier than the end time of the time-domain position corresponding to the second measurement result. The end time of the time-domain position corresponding to the second measurement result is after the end time of the time-domain position corresponding to the first prediction result.

[0317] For example, the fourth piece of information is used to configure the resources for reporting monitoring results. The start time of the time-domain resources for reporting monitoring results is no earlier than the first time.

[0318] Similar to S750, in one example, if the device performing model monitoring on the terminal side is a terminal device, then S780 may include: the terminal device receiving fourth information from the network device, or the terminal device receiving fourth information from the OTT server, where the fourth information may be sent from the network-side intelligent network element to the OTT system server. In another example, if the device performing model monitoring on the terminal side is an OTT system server, then S780 may include: the OTT system server receiving fourth information from the intelligent network element, or the OTT system server receiving fourth information from the terminal device, where the fourth information may be sent from the network device to the terminal device.

[0319] It should be noted that S780 is an optional step. For example, if the first moment mentioned above is a predefined moment, then method 700 may not include S780.

[0320] For example, the first to fourth information can be carried in different messages. For instance, the first information is carried in message #1, the second information in message #2, the third information in message #3, and the fourth information in message #4. It should be understood that when the first to fourth information are carried in different messages, any two steps in S750 to S780 are different steps.

[0321] For example, multiple pieces of information among the first to fourth information can be carried in the same message. For instance, all four pieces of information can be carried in message #a. Or, for another example, the first and second information can be carried in message #b, and the third and fourth information can be carried in message #c. It should be understood that when multiple pieces of information among the first to fourth information are carried in the same message, the multiple steps in S750 to S780 are the same steps. For example, if all four pieces of information are carried in message #a, then S750 to S780 are the same step. If the first and second information are carried in message #b, then S750 and S760 are the same step. If the third and fourth information are carried in message #c, then S770 and S780 are the same step.

[0322] It should also be understood that this application does not limit the execution order of S750 to S780. For example, S750 can be performed before S760 or after S780.

[0323] It should also be understood that in the embodiments shown above in conjunction with Figures 7 to 12, the terminal side can be a terminal device, and the network side can be a network device. In another design, the terminal side can also include a terminal device and an OTT system host or cloud server; the network side can include network devices and intelligent network elements. In this case, devices on the terminal side can communicate with each other, and devices on the network side can also communicate with each other. The specific implementation flow of the method provided in this application in an architecture with an OTT system host or cloud server (hereinafter referred to as OTT system server), terminal device, network device, and intelligent network element will be described below using method 1300 shown in Figure 13. In this flow, it is assumed that the training device is an OTT system server.

[0324] Figure 13 is another schematic flowchart of the communication method provided in the embodiments of this application. The method 1300 shown in Figure 13 may include the following steps.

[0325] S1301, the intelligent network element sends first information #1 to the network device. First information #1 is used to instruct the execution of model monitoring.

[0326] S1301 is an optional step. If the network device triggers whether to perform model monitoring, method 1300 may not include S1301.

[0327] S1302, the network device sends first information to the terminal device. The first information is used to instruct the execution of model monitoring. The first information may be the same as or different from the first information #1, without limitation.

[0328] S1303, the terminal device sends first information #2 to the OTT system server. First information #2 is used to instruct the execution of model monitoring. First information #2 may be the same as or different from the first information, without limitation.

[0329] S1303 is an optional step. If model monitoring is performed by a terminal device, method 1300 may not include S1303.

[0330] S1304, the intelligent network element sends the second information #1 to the network device. The second information #1 is used to indicate the time period for performing model monitoring.

[0331] S1304 is an optional step. If the network device triggers whether to perform model monitoring, method 1300 may not include S1304.

[0332] S1305, the network device sends a second message to the terminal device, which indicates the time period for performing model monitoring. This second message may be the same as or different from second message #1; no limitation is made.

[0333] S1306, the terminal device sends second information #2 to the OTT system server. Second information #2 is used to indicate the time period for performing model monitoring. Second information #2 may be the same as or different from the second information, without limitation.

[0334] S1306 is an optional step. If model monitoring is performed by a terminal device, method 1300 may not include S1306.

[0335] S1307, the intelligent network element sends third information #1 to the network device. Third information #1 is used to indicate performance indicators.

[0336] S1307 is an optional step. If the performance indicators are determined by the network device, method 1300 may not include S1307.

[0337] S1308, the network device sends third information to the terminal device. The third information is used to indicate performance indicators. The third information may be the same as or different from the third information #1, without limitation.

[0338] S1309, the terminal device sends third information #2 to the OTT system server. Third information #2 is used to indicate performance indicators. Third information #2 may be the same as or different from the third information, without limitation.

[0339] S1309 is an optional step. If model monitoring is performed by a terminal device, method 1300 may not include S1309.

[0340] S1310, the intelligent network element sends the fourth information #1 to the network device. The fourth information #1 is used to indicate that the time for reporting the monitoring results is not earlier than the first moment.

[0341] S1310 is an optional step. If the timing for reporting monitoring results is determined by the network device, method 1300 may not include S1310.

[0342] S1311, the network device sends a fourth message to the terminal device. The fourth message indicates that the time for reporting the monitoring results is not earlier than the first message. The fourth message may be the same as or different from the fourth message #1, without limitation.

[0343] S1312, the terminal device sends fourth information #2 to the OTT system server. Fourth information #2 indicates that the time for reporting monitoring results is no earlier than the first time. Fourth information #2 may be the same as or different from the fourth information, without limitation.

[0344] S1312 is an optional step. If model monitoring is performed by a terminal device, method 1300 may not include S1312.

[0345] S1313, the terminal device acquires the first measurement result.

[0346] Optionally, if the model inference is performed by the OTT system server, the terminal device also sends the first measurement result to the OTT system server.

[0347] S1314, The terminal device and / or OTT system server obtain the first prediction result.

[0348] For example, in S1314, the terminal device performs model inference to obtain a first prediction result. Optionally, the terminal device may also send the first prediction result to the OTT system server.

[0349] For example, in S1314, the OTT system server performs model inference to obtain a first prediction result. Optionally, the OTT system server may also send the first prediction result to the terminal device.

[0350] S1315, the terminal device acquires the second measurement result.

[0351] Optionally, if the model monitoring is performed by the OTT system server, the terminal device also sends a second measurement result to the OTT system server.

[0352] S1316, Terminal devices and / or OTT system servers obtain monitoring results.

[0353] For example, in S1316, the terminal device performs model monitoring and obtains monitoring results.

[0354] For example, in S1316, the OTT system server performs model monitoring and obtains monitoring results.

[0355] S1317, the OTT system server sends monitoring results to the terminal device.

[0356] Optionally, if the terminal device performs model monitoring and obtains monitoring results in S1316, then method 1300 does not include S1317.

[0357] S1318, The terminal device sends the monitoring results to the network device.

[0358] S1319, the network device sends the monitoring results to the intelligent network element.

[0359] For detailed descriptions of each step in method 1300, please refer to the relevant descriptions in method 700 above in conjunction with Figure 7, which will not be repeated here. Furthermore, the technical solution shown in method 1300 corresponds to the technical solution shown in method 700 above, and therefore the beneficial effects obtained are similar, which will not be repeated here either.

[0360] It should be understood that the process shown in Figure 13 is merely one possible implementation of the method 700 shown in Figure 7 in a system architecture deploying an OTT system server and intelligent network elements, and should not be construed as limiting this application in any way. Those skilled in the art can, based on the same concept, make simple substitutions or modifications to one or more steps of method 700 to achieve the same effect. Such simple modifications or substitutions should fall within the protection scope of this application.

[0361] It should also be understood that the processes listed above are merely examples, and this application includes, but is not limited to, them. For example, the terminal device and OTT system server in Figure 13 can also be replaced by the terminal device itself. In this case, the communication between the terminal device and the OTT system server is internal communication within the terminal device. Alternatively, the network device and intelligent network element in Figure 13 can also be replaced by the network device itself. In this case, the communication between the network device and the intelligent network element is internal communication within the network device. For the sake of brevity, no further illustrations are provided in this document.

[0362] It should be understood that in the various embodiments shown above in conjunction with the accompanying drawings, the sequence number of each step does not imply the order of execution. The execution order of each step should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0363] It should also be understood that the various embodiments exemplified above can also be applied to scenarios where the terminal sends reference signals to the network side, i.e., uplink scenarios. In this case, the steps on the terminal side in the above embodiments can be performed by the network side, and vice versa. Those skilled in the art can make simple modifications or substitutions based on the same concept to obtain more embodiments.

[0364] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0365] In the above embodiments, exemplary descriptions are mainly based on devices in the current network architecture (such as terminal devices, network devices, OTT system servers, intelligent network elements, etc.). The specific form of the devices is not limited in the embodiments of this application. For example, devices that can achieve the same function in the future can also be applied to the methods provided in the embodiments of this application.

[0366] It is understood that the methods and operations implemented by devices (such as terminal devices, network devices, OTT system servers, and smart network elements) in the above-described method embodiments can also be implemented by components of the devices (such as chips or circuits).

[0367] The methods provided in the embodiments of this application have been described in detail above with reference to several accompanying drawings. The apparatus provided in the embodiments of this application will now be described with reference to the accompanying drawings.

[0368] Figures 14 and 15 are schematic block diagrams of possible apparatuses provided in embodiments of this application. These apparatuses can be used to implement the terminal-side or network-side functions in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0369] Figure 14 is a schematic block diagram of an apparatus provided in an embodiment of this application. The apparatus 1400 shown in Figure 14 may include a processing module 1410 and a communication module 1420.

[0370] In one possible design, device 1400 can be used to implement the communication method implemented by the terminal side in any of the embodiments shown in Figures 7 to 13. For example, processing module 1410 is used to implement model monitoring-related steps executed by the terminal side in each method embodiment; communication module 1420 is used to implement sending and / or receiving steps executed by the terminal side in each method embodiment, such as receiving one or more of the following: receiving first information, receiving second information, receiving third information, receiving fourth information, or sending monitoring results.

[0371] For example, the processing module 1410 can be used to obtain a first measurement result, which is used to obtain a first prediction result, and the time domain position corresponding to the first prediction result is after the time domain position corresponding to the first measurement result; the processing module 1410 can also be used to obtain a second measurement result, the end time of the time domain position corresponding to the second measurement result is after the end time of the time domain position corresponding to the first prediction result; the processing module 1410 can also be used to obtain a monitoring result based on the first measurement result and the second measurement result, and the monitoring result is used to determine the confidence level of the first prediction result.

[0372] Optionally, when the processing module 1410 is used to obtain monitoring results, it is specifically used to: obtain a first prediction result and a third prediction result based on the first measurement result and the first model, wherein the time domain position corresponding to the third prediction result is the same as the time domain position corresponding to the second measurement result; and obtain monitoring results based on the third prediction result and the second measurement result.

[0373] Optionally, when the processing module 1410 is used to obtain monitoring results, it is specifically used to: obtain monitoring results based on the first measurement result, the second measurement result, and the second model.

[0374] Optionally, when the processing module 1410 is used to obtain monitoring results, it is specifically used to: obtain a fourth prediction result based on the first measurement result, the second measurement result, and the second model, wherein the time domain position corresponding to the fourth prediction result is the same as the time domain position corresponding to the first prediction result; and obtain monitoring results based on the fourth prediction result and the first prediction result.

[0375] Optionally, when the processing module 1410 is used to obtain the fourth prediction result, it is specifically used to: obtain the first prediction result based on the first measurement result and the first model; and obtain the fourth prediction result based on the first prediction result, the second measurement result, and the second model.

[0376] Optionally, when the processing module 1410 is used to obtain monitoring results, it is specifically used to: obtain a first prediction result based on a first measurement result and a first model; and obtain monitoring results based on the first prediction result, a second measurement result, and a second model.

[0377] Optionally, the processing module 1410 can also be used to: obtain a third measurement result, wherein the time domain position corresponding to the third measurement result is before the time domain position corresponding to the first measurement result; when the processing module 1410 is used to obtain the monitoring result, it is specifically used to: obtain the monitoring result based on the first measurement result, the second measurement result and the third measurement result.

[0378] Optionally, the communication module 1420 can be used to receive first information, which is used to instruct the execution of model monitoring.

[0379] Optionally, the communication module 1420 can be used to receive second information, which indicates the time period for performing model monitoring.

[0380] Optionally, the communication module 1420 can be used to receive third information, which indicates a third model used to indicate performance indicators.

[0381] Optionally, the communication module 1420 can be used to receive a fourth message, which indicates that the time for reporting the monitoring result is no earlier than the first moment.

[0382] A more detailed description of the processing module 1410 and the communication module 1420 can be obtained directly from the relevant descriptions in the method embodiments shown in Figures 7 to 13, and will not be repeated here.

[0383] In another possible design, device 1400 can be used to implement the communication method implemented by the network side in any of the embodiments shown in Figures 7 to 13. For example, processing module 1410 is used to implement the processing-related steps performed by the network side in each method embodiment; communication module 1420 is used to implement the sending and / or receiving steps performed by the network side in each method embodiment, such as sending first information, sending second information, sending third information, sending fourth information, or receiving monitoring results, or one or more of these steps.

[0384] For example, the communication module 1420 can be used to send a first reference signal, which is used to acquire a first measurement result. The first measurement result is used to acquire a first prediction result, and the time domain position corresponding to the first prediction result is after the time domain position corresponding to the first measurement result. The communication module 1420 can also be used to send a second reference signal, which is used to acquire a second measurement result. The end time of the time domain position corresponding to the second measurement result is after the end time of the time domain position corresponding to the first prediction result. The first measurement result and the second measurement result are used to acquire a monitoring result, and the monitoring result is used to determine the confidence level of the first prediction result.

[0385] Optionally, the communication module 1420 can be used to send first information, which is used to instruct the execution of model monitoring.

[0386] Optionally, the communication module 1420 can be used to send a second message indicating the time period for performing model monitoring.

[0387] Optionally, the communication module 1420 can be used to send third information, which indicates a third model for indicating performance metrics.

[0388] Optionally, the communication module 1420 can be used to send a fourth message, which indicates that the time for reporting the monitoring results is no earlier than the first time.

[0389] A more detailed description of the processing module 1410 and the communication module 1420 can be obtained directly from the relevant descriptions in the method embodiments shown in Figures 7 to 13, and will not be repeated here.

[0390] It should be noted that the communication module can also be called a transceiver module, transceiver unit, transceiver, transceiver device, or transceiver apparatus, etc. The processing module can also be called a processor, processing board, processing unit, or processing apparatus, etc. Optionally, the communication module is used to perform the sending and receiving operations on the terminal side or network side in the above method. The device in the communication module that implements the receiving function can be considered as the receiving module, and the device in the communication module that implements the sending function can be considered as the sending module; that is, the communication module can include both a receiving module and a sending module.

[0391] It should also be noted that, in one possible design, the aforementioned processing module and / or communication module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. In another possible design, the processing module or communication module can also be implemented through physical devices. For example, if the device is implemented using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module can be an integrated processor, a microprocessor, or an integrated circuit.

[0392] The module division in this embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional modules in the various examples of this embodiment can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0393] Figure 15 is a schematic diagram of the structure of a communication device provided in another embodiment of this application. As shown in Figure 15, the device 1500 includes a processing circuit 1510 and a communication circuit 1520. The processing circuit 1510 and the communication circuit 1520 are coupled to each other.

[0394] It is understood that the processing circuit 1510 can be one or more processors, or it can be all or part of the processing functions of one or more processors.

[0395] Understandably, the communication circuit 1520 can be a transceiver or an input / output interface.

[0396] Optionally, the device 1500 may further include a memory 1530 for storing instructions executed by the processing circuit 1510, or storing input data required for the running instructions of the processing circuit 1510, or storing data generated after the running instructions of the processing circuit 1510.

[0397] It is understood that the memory 1530 may be located outside the processing circuit 1510, or inside the processing circuit 1510.

[0398] As an example, the processing circuit 1510 is used to implement the functions of the processing module 1410, and the communication circuit 1520 is used to implement the functions of the communication module 1420.

[0399] As an example, device 1500 can be a communication device or a chip used in a communication device.

[0400] When device 1500 is a communication device, the communication circuit can be a transceiver; when device 1500 is a chip, the communication circuit can be an input / output circuit, a bus, pins, or other types of communication interfaces. The input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0401] In one possible implementation, the apparatus 1500 is used to implement the various processes and steps corresponding to the terminal side in the above method embodiments. In another possible implementation, the apparatus 1500 is used to implement the various processes and steps corresponding to the network side in the above method embodiments.

[0402] It is understood that device 1500 can specifically be the terminal-side device or network-side device in the above embodiments, or it can be a chip or chip system. Correspondingly, the communication circuit can be the interface circuit of the chip, or an input / output circuit, which is not limited here.

[0403] When the aforementioned communication device is a chip or OTT device applied to the terminal side, the terminal-side chip or OTT device implements the terminal-side functions described in the above method embodiments, such as implementing terminal-side processing functions. The terminal-side chip or OTT device receiving information from the network side can be understood as the information being first received by other modules on the terminal side (such as an RF module or antenna), and then sent by these modules to the terminal-side chip or OTT device. The terminal-side chip or OTT device sending information to the network side can be understood as the information being first sent by the terminal-side chip or OTT device to other modules on the terminal side (such as an RF module or antenna), and then sent by these modules to the network side.

[0404] When the aforementioned communication device is a chip or OTT device applied to the network side, the network-side chip or OTT device implements the network-side functions described in the above method embodiments, for example, implementing network-side processing functions. The network-side chip or OTT device receiving information from the terminal side can be understood as the information being first received by other modules on the network side (such as radio frequency modules or antennas), and then sent to the network-side chip or OTT device by these modules. The network-side chip or OTT device sending information to the terminal side can be understood as the information being first sent by the network-side chip or OTT device to other modules on the network side (such as radio frequency modules or antennas), and then sent to the terminal side by these modules.

[0405] This application also provides a computer program product that, when run on a processor, can implement the communication method executed by the terminal side or the communication method executed by the network side in the above method embodiments.

[0406] This application also provides a computer-readable storage medium containing computer instructions that, when executed on a processor, can implement the communication method executed by the terminal side or the communication method executed by the network side in the above method embodiments.

[0407] This application also provides a communication system, including the aforementioned terminal side and network side. The terminal side can be used to implement the communication method implemented by the terminal side in the above method embodiments, and the network side can be used to implement the communication method implemented by the network side in the above method embodiments.

[0408] It is understood that the processor in the embodiments of this application may be any of the following devices or all or part of the circuitry used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), processors for AI, field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0409] The processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0410] The terms “unit”, “module”, etc., used in this specification may be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution.

[0411] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0412] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0413] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0414] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0415] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0416] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0417] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0418] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: A first measurement result is obtained, which is used to obtain a first prediction result. The time domain position corresponding to the first prediction result is after the time domain position corresponding to the first measurement result. Obtain a second measurement result, wherein the end time of the time domain position corresponding to the second measurement result is after the end time of the time domain position corresponding to the first prediction result; Based on the first measurement result and the second measurement result, a monitoring result is obtained, which is used to determine the credibility of the first prediction result.

2. The method according to claim 1, characterized in that, Based on the first measurement result and the second measurement result, monitoring results are obtained, including: Based on the first measurement result and the first model, the first prediction result and the third prediction result are obtained, and the time domain position corresponding to the third prediction result is the same as the time domain position corresponding to the second measurement result. The monitoring results are obtained based on the third prediction result and the second measurement result.

3. The method according to claim 2, characterized in that, The monitoring results include one or more of the following: The first difference information between the third prediction result and the second measurement result, and / or the deviation between the first difference information and the first threshold; The first mean square error (MSE) information between the third prediction result and the second measurement result, and / or the deviation between the first MSE information and the second threshold; The first normalized mean square error (NMSE) information between the third prediction result and the second measurement result, and / or the deviation between the first NMSE information and the third threshold; The first mean absolute error (MAE) information between the third prediction result and the second measurement result, and / or the deviation between the first MAE information and the fourth threshold; The first generalized cosine similarity (GCS) information between the third prediction result and the second measurement result, and / or the deviation between the first GCS information and the fifth threshold; or... The first squared generalized cosine similarity (SGCS) information between the third prediction result and the second measurement result, and / or the deviation between the first SGCS information and the sixth threshold.

4. The method according to claim 1, characterized in that, The step of obtaining monitoring results based on the first measurement result and the second measurement result includes: The monitoring results are obtained based on the first measurement result, the second measurement result, and the second model.

5. The method according to claim 4, characterized in that, Based on the first measurement result, the second measurement result, and the second model, the monitoring result is obtained, including: Based on the first measurement result, the second measurement result, and the second model, a fourth prediction result is obtained, wherein the time domain position corresponding to the fourth prediction result is the same as the time domain position corresponding to the first prediction result. The monitoring result is obtained based on the fourth prediction result and the first prediction result.

6. The method according to claim 5, characterized in that, Based on the first measurement result, the second measurement result, and the second model, a fourth prediction result is obtained, including: Based on the first measurement result and the first model, the first prediction result is obtained; Based on the first prediction result, the second measurement result, and the second model, the fourth prediction result is obtained.

7. The method according to claim 5 or 6, characterized in that, The monitoring results include one or more of the following: The second difference information between the fourth prediction result and the first prediction result, and / or the deviation between the second difference information and the first threshold; The second MSE information between the fourth prediction result and the first prediction result, and / or the deviation between the second MSE information and the second threshold; The second NMSE information between the fourth prediction result and the first prediction result, and / or the deviation between the second NMSE information and the third threshold; The second MAE information between the fourth prediction result and the first prediction result, and / or the deviation between the second MAE information and the fourth threshold; The second GCS information between the fourth prediction result and the first prediction result, and / or the deviation between the second GCS information and the fifth threshold; or... The second SGCS information between the fourth prediction result and the first prediction result, and / or the deviation between the second SGCS information and the sixth threshold.

8. The method according to claim 4, characterized in that, Based on the first measurement result, the second measurement result, and the second model, the monitoring result is obtained, including: Based on the first measurement result and the first model, the first prediction result is obtained; The monitoring results are obtained based on the first prediction result, the second measurement result, and the second model.

9. The method according to any one of claims 1 to 8, characterized in that, The interval between the end time of the time domain position corresponding to the second measurement result and the end time of the time domain position corresponding to the first prediction result is less than or equal to the seventh threshold.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: A third measurement result is obtained, wherein the time domain position corresponding to the third measurement result is before the time domain position corresponding to the first measurement result; The step of obtaining monitoring results based on the first measurement result and the second measurement result includes: The monitoring result is obtained based on the first measurement result, the second measurement result, and the third measurement result.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: Receive first information, the first information being used to instruct the execution of model monitoring, the model monitoring being used to obtain the monitoring results.

12. The method according to claim 11, characterized in that, The first information includes information about the first model, which is used to obtain the first prediction result.

13. The method according to any one of claims 1 to 12, characterized in that, The method further includes: Receive second information, which indicates the time period for performing model monitoring, and the monitoring result is obtained by performing the model monitoring.

14. The method according to claim 13, characterized in that, The second information includes information about reference signal resources, and the time period for which the model monitoring is performed corresponds to the time domain resources of the reference signal resources.

15. The method according to any one of claims 1 to 14, characterized in that, The method further includes: Receive third information, the third information being used to indicate performance indicators, the performance indicators being used to determine the monitoring results.

16. The method according to any one of claims 1 to 15, characterized in that, The method further includes: Send the monitoring results.

17. The method according to claim 16, characterized in that, The method further includes: Receive fourth information, which indicates that the time of reporting the monitoring result is not earlier than the first time, and the first time is not earlier than the end time of the time domain position corresponding to the second measurement result.

18. A communication method, characterized in that, include: A first reference signal is sent, the first reference signal is used to obtain a first measurement result, the first measurement result is used to obtain a first prediction result, and the time domain position corresponding to the first prediction result is after the time domain position corresponding to the first measurement result. A second reference signal is sent, which is used to acquire a second measurement result. The end time of the time domain position corresponding to the second measurement result is after the end time of the time domain position corresponding to the first prediction result. The first measurement result and the second measurement result are used to obtain monitoring results, and the monitoring results are used to determine the credibility of the first prediction result.

19. The method according to claim 18, characterized in that, The interval between the end time of the time domain position corresponding to the second measurement result and the end time of the time domain position corresponding to the first prediction result is less than or equal to the seventh threshold.

20. The method according to claim 18 or 19, characterized in that, The method further includes: A third reference signal is sent, which is used to acquire a third measurement result. The time domain position corresponding to the third measurement result is before the time domain position corresponding to the first measurement result. The first measurement result, the second measurement result, and the third measurement result are used to acquire the monitoring result.

21. The method according to any one of claims 18 to 20, characterized in that, The method further includes: Send a first message, which is used to instruct the execution of model monitoring, and the model monitoring is used to obtain the monitoring results.

22. The method according to claim 21, characterized in that, The first information includes information about the first model, which is used to obtain the first prediction result.

23. The method according to any one of claims 18 to 22, characterized in that, The method further includes: Send a second message, which indicates the time period for performing model monitoring, and the monitoring result is obtained by performing the model monitoring.

24. The method according to claim 23, characterized in that, The second information includes information about reference signal resources, and the time period for which the model monitoring is performed corresponds to the time domain resources of the reference signal resources.

25. The method according to any one of claims 18 to 24, characterized in that, The method further includes: Send a third message, the third message being used to indicate performance metrics, the performance metrics being used to determine the monitoring result.

26. The method according to any one of claims 18 to 25, characterized in that, The method further includes: Receive the monitoring results.

27. The method according to any one of claims 18 to 26, characterized in that, The method further includes: Send a fourth message, which indicates that the time of reporting the monitoring result is not earlier than the first time, and the first time is not earlier than the end time of the time domain position corresponding to the second measurement result.

28. A communication device, characterized in that, It includes modules or units for performing the method as described in any one of claims 1 to 17, or includes modules or units for performing the method as described in any one of claims 18 to 27.

29. A communication device, characterized in that, The device includes a processor configured to cause the communication device to perform the method of any one of claims 1 to 17, or the processor configured to cause the communication device to perform the method of any one of claims 18 to 27.

30. A computer-readable storage medium, characterized in that, The computer-readable storage medium is included in the communication device, and the computer-readable storage medium stores computer instructions that, when executed, cause the method as claimed in any one of claims 1 to 17 to be implemented, or cause the method as claimed in any one of claims 18 to 27 to be implemented.

31. A computer program product, said computer program product being included in a communication device, characterized in that, When the computer program product is run, it causes the method as described in any one of claims 1 to 17 to be implemented, or causes the method as described in any one of claims 18 to 27 to be implemented.