Communication method and related device

Abstract

Provided in the present application are a communication method and a communication device. The method comprises: determining a first accuracy rate of a first AI model, wherein the first accuracy rate is used for representing the accuracy rate of a probability corresponding to a first optimal reference signal resource in a first reference signal resource set determined by the first AI model, and the first AI model is used for determining a probability that each reference signal resource in the first reference signal resource set is an optimal reference signal resource in the first reference signal resource set; and sending first indication information, wherein the first indication information is used for indicating the first accuracy rate, or the first indication information is used for requesting the configuration of a second reference signal resource set. A terminal device in the method can determine the accuracy rate of the first AI model, thereby facilitating the monitoring of the first AI model. The terminal device may further request, on the basis of the first accuracy rate, a network device to configure reference signal resource sets, so as to determine appropriate communication resources.

Description

A communication method and related equipment

[0001] This application claims priority to Chinese Patent Application No. 202411062334.1, filed with the State Intellectual Property Office of China on August 2, 2024, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more specifically, to a communication method, a communication device, a computer-readable storage medium, a chip, and a computer program product. Background Technology

[0003] In AI-based beam management scenarios, to save measurement overhead, the terminal device measures a subset of reference signal resources in reference signal resource set A to obtain the channel state information (CSI) measurements corresponding to that subset. Based on these CSI measurements and the AI ​​model, the terminal device predicts the probability that each reference signal resource in reference signal resource set B is the optimal resource in set B, and then reports the identification information of one or more reference signal resources with higher probabilities in set B to the network device. Each reference signal resource in this set carries a reference signal, including a synchronizing signal block (SSB) and / or a channel state information reference signal (CSI-RS). For example, a beam can be used for this purpose. The network device determines the resource for communication with the terminal device based on the received reference signal resources. Since these reference resources are determined based on the AI ​​model, the AI ​​model needs to be monitored to facilitate the selection of suitable communication resources.

[0004] Therefore, how to monitor AI models has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method, communication device, computer-readable storage medium, chip, and computer program product that can determine the accuracy of an AI model, thereby facilitating the monitoring of the AI ​​model.

[0006] Firstly, a communication method is provided. The method includes: determining a first accuracy rate of a first AI model, the first accuracy rate being used to characterize the accuracy rate of the probability corresponding to a first optimal reference signal resource in a first set of reference signal resources determined by the first AI model, the first AI model being used to determine the probability that each reference signal resource in the first set of reference signal resources is the optimal reference signal resource in the first set of reference signal resources, the probability corresponding to the first optimal reference signal resource being the maximum value among the probabilities corresponding to each reference signal resource in the first set of reference signal resources, the first set of reference signal resources including at least one reference signal resource; and sending first indication information, the first indication information being used to indicate the first accuracy rate, or the first indication information being used to request the configuration of a second set of reference signal resources, the second set of reference signal resources including at least one reference signal resource.

[0007] For example, the accuracy of the probability corresponding to the first optimal reference signal resource is: the probability that the reference signal resource with the highest probability in the first reference signal resource set determined by the first AI model is the reference signal resource with the highest measured value of channel information state in the first reference signal resource set.

[0008] For example, the measured value of the channel state information of the best reference signal resource in the first reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the first reference signal resource set besides the best reference signal resource.

[0009] In this embodiment, the terminal-side device can determine the accuracy of the first AI model, thereby facilitating its monitoring. Simultaneously, the terminal-side device can report the accuracy of the first AI model to the network-side device, facilitating its monitoring as well. Alternatively, the terminal-side device can request the network-side device to configure a set of reference signal resources based on the accuracy of the first AI model, thereby determining suitable communication resources.

[0010] In conjunction with the first aspect, in some implementations, the probability corresponding to the first optimal reference signal resource is determined based on the first AI model; and the first accuracy is determined based on the first correspondence and the probability corresponding to the first optimal reference signal resource. The first correspondence is used to indicate the correspondence between the probability interval to which the probability determined by the first AI model belongs and the accuracy of the first AI model.

[0011] In this embodiment of the application, the terminal device determines the accuracy of the probability corresponding to the first optimal reference signal resource determined by the first AI model based on the first correspondence relationship, thereby facilitating the monitoring of the first AI model.

[0012] In conjunction with the first aspect, in some implementations, based on the first value M, M probability intervals are determined, where the minimum value in the M probability intervals is greater than or equal to 0, and the maximum value in the M probability intervals is less than or equal to 1, where M is an integer greater than 1; a second optimal reference signal resource and a third optimal reference signal resource are determined in each of at least one third reference signal resource set, where the measured value of the channel state information corresponding to the second optimal reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set, and the probability corresponding to the third optimal reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model; a first correspondence is determined based on the M probability intervals and the second optimal reference signal resource and the third optimal reference signal resource in each third reference signal resource set.

[0013] In conjunction with the first aspect, in some implementations, the probability interval to which the probability of the third best reference signal resource in each third reference signal resource set belongs is determined; based on the number of third best reference signal resources included in each of the M probability intervals, the identification information of each third best reference signal resource included in each probability interval, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in each probability interval, the accuracy corresponding to each probability interval is determined, and each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belong to the same third reference signal resource set.

[0014] In this embodiment, the terminal device determines a first correspondence based on a first value M, at least one third set of reference signal resources, and a first AI model. This facilitates determining the accuracy of the first AI model based on the first correspondence and the probability interval to which the probability of the optimal reference signal resource determined by the first AI model belongs. Furthermore, in this method, the network device does not need to configure a large number of reference signal resources for the terminal device each time to determine the accuracy of the probability corresponding to the optimal reference signal resource determined by the first AI model each time. Instead, it can directly determine the accuracy of the first AI model based on the first correspondence, thus reducing resource waste.

[0015] In conjunction with the first aspect, in some implementations, a second indication information is received, which is used to indicate a first value M, or the second indication information is used to indicate a first determination method and a first value M; wherein, the first value M is the number of probability intervals included in the first correspondence, and the first determination method is the method of determining the first correspondence.

[0016] In this embodiment of the application, the terminal device receives indication information from the network device, and then determines M probability intervals or a first correspondence based on the indication information.

[0017] In conjunction with the first aspect, in some implementations, where the first indication information is used to indicate the first accuracy, the first indication information is also used to indicate the identification information of the first optimal reference signal resource.

[0018] In this embodiment, while reporting the accuracy of the first AI model, the terminal device can also report the identification information of the best reference signal resource determined by the first AI model, thereby facilitating the network device to determine suitable communication resources.

[0019] In conjunction with the first aspect, in some implementations, when the first indication information is used to request the configuration of the second reference signal resource set, the first indication information is sent when the first accuracy is less than or equal to the first preset threshold; and when the first accuracy is greater than the first preset threshold, the third indication information is sent, wherein the third indication information is used to indicate the identification information of the first optimal reference signal resource.

[0020] In this embodiment, after determining the accuracy of the first AI model, the terminal device can determine whether further measurement is needed based on the accuracy of the first AI model and a first preset threshold, in order to determine suitable communication resources. If the terminal device determines that the accuracy of the first AI model meets expectations, the terminal device can directly send the identification information of the optimal reference signal resource determined by the first AI model to the network device, so that the optimal reference signal resource can be used as the communication resource for communicating with the network device.

[0021] In conjunction with the first aspect, in some implementations, a second accuracy rate is determined based on at least one accuracy rate of the first AI model, wherein the at least one accuracy rate includes the first accuracy rate; and the first AI model is calibrated if the second accuracy rate is less than or equal to a second preset threshold.

[0022] In this embodiment, the terminal device determines whether the expected results are met based on the statistical information of the accuracy of the first AI model, and corrects the first AI model if the expected results are not met, thereby realizing the monitoring of the first AI model.

[0023] Secondly, a communication method is provided. The method includes: determining a first accuracy rate of a first AI model, the first accuracy rate being used to characterize the accuracy rate of the probability corresponding to a first optimal reference signal resource in a first set of reference signal resources determined by the first AI model; the first AI model being used to determine the probability that each reference signal resource in the first set of reference signal resources is the optimal reference signal resource in the first set of reference signal resources; the probability corresponding to the first optimal reference signal resource being the maximum value among the probabilities corresponding to each reference signal resource in the first set of reference signal resources; the first set of reference signal resources including at least one reference signal resource; and sending first configuration information, the first configuration information being used to configure a second set of reference signal resources, the second set of reference signal resources including at least one reference signal resource.

[0024] For example, the accuracy of the probability corresponding to the first optimal reference signal resource is: the probability that the reference signal resource with the highest probability in the first reference signal resource set determined by the first AI model is the reference signal resource with the highest measured value of channel information state in the first reference signal resource set.

[0025] For example, the measured value of the channel state information of the best reference signal resource in the first reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the first reference signal resource set besides the best reference signal resource.

[0026] In this embodiment, the network-side device can determine the accuracy of the first AI model, thereby facilitating its monitoring. Furthermore, the network-side device can determine the reliability of the optimal reference signal resource predicted by the first AI model based on its accuracy. If the accuracy of the first AI model does not meet a preset threshold, the network-side device can instruct the terminal-side device to perform further measurements, thereby facilitating the determination of suitable communication resources.

[0027] In conjunction with the second aspect, in some implementations, a first accuracy rate is determined based on the first correspondence and the probability corresponding to the first optimal reference signal resource. The first correspondence is used to indicate the correspondence between the probability interval to which the probability determined by the first AI model belongs and the accuracy rate of the first AI model.

[0028] In conjunction with the second aspect, in some implementations, a fourth indication information is received, which is used to indicate the first correspondence; and / or, a fifth indication information is received, which is used to indicate the probability corresponding to the first optimal reference signal resource.

[0029] In this embodiment, the network-side device receives the first correspondence reported by the terminal-side device and the probability corresponding to the best reference signal resource determined by the first AI model. Based on the first correspondence and the probability corresponding to the best reference signal resource, the accuracy of the first AI model is determined, which facilitates the monitoring of the first AI model.

[0030] In conjunction with the second aspect, in some implementations, the first correspondence is determined based on M probability intervals and the second and third best reference signal resources in each of the at least one third reference signal resource set; wherein, the minimum value in the M probability intervals is greater than or equal to 0, the maximum value in the M probability intervals is less than or equal to 1, M is an integer greater than 1, the measured value of the channel state information corresponding to the second best reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set, and the probability corresponding to the third best reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model.

[0031] In conjunction with the second aspect, in some implementations, the accuracy corresponding to each probability interval is determined based on the number of third best reference signal resources included in each of the M probability intervals, the identification information of each third best reference signal resource included in each probability interval, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in each probability interval; wherein, the probability corresponding to the third best reference signal resource in each set of third reference signal resources belongs to one of the M probability intervals, and each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belong to the same set of third reference signal resources.

[0032] In this embodiment of the application, the network-side device can sense the specific method by which the terminal-side device determines the first correspondence, thereby facilitating the monitoring of the first AI model.

[0033] In conjunction with the second aspect, in some implementations, a sixth indication information is received, which is used to indicate the first accuracy rate.

[0034] In this embodiment of the application, the network-side device can directly receive the first accuracy rate from the terminal-side device, and then monitor the first AI model based on the first accuracy rate.

[0035] In conjunction with the second aspect, in some implementations, a second indication message is sent, which is used to indicate a first value M, or the second indication message is used to indicate a first determination method and a first value M; wherein, the first value M is the number of probability intervals included in the first correspondence, the first determination method is the method of determining the first correspondence, the first correspondence is used to indicate the correspondence between the probability interval to which the probability determined by the first AI model belongs and the accuracy of the first AI model, and M is an integer greater than 1.

[0036] In this embodiment of the application, the network-side device indicates a first value M to the terminal-side device, or indicates a first value M and a first determination method to the terminal-side device, so that the terminal-side device determines the first correspondence relationship according to the instruction of the network-side device.

[0037] In conjunction with the second aspect, in some implementations, if the first accuracy is less than or equal to the first preset threshold, the first configuration information is sent; if the first accuracy is greater than the first preset threshold, data is transmitted through the first optimal reference signal resource.

[0038] In this embodiment, the network-side device determines whether it needs to instruct the terminal-side device to perform further measurements based on a first accuracy rate and a first preset threshold, in order to determine suitable communication resources. If the first accuracy rate does not meet expectations, the network-side device instructs the terminal-side device to perform further measurements; if the first accuracy rate meets expectations, the network-side device directly uses the optimal reference signal resource determined by the first AI model as the communication resource for communicating with the terminal-side device.

[0039] In conjunction with the second aspect, in some implementations, a second accuracy rate is determined based on at least one accuracy rate of the first AI model, wherein the at least one accuracy rate includes the first accuracy rate; if the second accuracy rate is less than or equal to a second preset threshold, a seventh indication message is sent, wherein the seventh indication message is used to instruct the calibration of the first AI model.

[0040] In this embodiment, the network-side device determines whether the expected performance is met based on the statistical information of the accuracy of the first AI model, and if the expected performance is not met, instructs the terminal-side device to correct the first AI model, thereby achieving monitoring of the first AI model.

[0041] Thirdly, a communication method is provided. The method includes: determining a first correspondence, the first correspondence indicating the correspondence between the probability interval to which the probability corresponding to the best reference signal resource determined by a first AI model belongs and the accuracy of the first AI model; the first AI model determining the probability that each reference signal resource in a fourth set of reference signal resources is the best reference signal resource in the fourth set of reference signal resources; the accuracy of the first AI model characterizing the accuracy of the probability determined by the first AI model; the fourth set of reference signal resources including at least one reference signal resource; and sending fourth indication information indicating the first correspondence.

[0042] For example, the measured value of the channel state information of the best reference signal resource in the fourth reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the fourth reference signal resource set besides the best reference signal resource.

[0043] In this embodiment, the terminal device determines the first correspondence between the probability interval to which the probability of the best reference signal resource determined by the first AI model belongs and the accuracy of the first AI model, and reports it to the network device, so that the terminal device and / or the network device can monitor the first AI model according to the first correspondence.

[0044] In conjunction with the third aspect, in some implementations, based on the first value M, M probability intervals are determined, where the minimum value in the M probability intervals is greater than or equal to 0, and the maximum value in the M probability intervals is less than or equal to 1, where M is an integer greater than 1; a second optimal reference signal resource and a third optimal reference signal resource are determined in each of at least one third reference signal resource set, where the measured value of the channel state information corresponding to the second optimal reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set, and the probability corresponding to the third optimal reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model; a first correspondence is determined based on the M probability intervals and the second optimal reference signal resource and the third optimal reference signal resource in each third reference signal resource set.

[0045] In conjunction with the third aspect, in some implementation methods, the probability interval to which the probability of the third best reference signal resource in each third reference signal resource set belongs is determined; based on the number of third best reference signal resources included in each of the M probability intervals, the identification information of each third best reference signal resource included in each probability interval, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in each probability interval, the accuracy corresponding to each probability interval is determined, and each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belong to the same third reference signal resource set.

[0046] In this embodiment, the terminal device determines a first correspondence based on a first value M, at least one third set of reference signal resources, and a first AI model. This facilitates determining the accuracy of the first AI model based on the first correspondence and the probability interval to which the probability of the optimal reference signal resource determined by the first AI model belongs. Furthermore, in this method, the network device does not need to configure a large number of reference signal resources for the terminal device each time to determine the accuracy of the probability corresponding to the optimal reference signal resource determined by the first AI model each time. Instead, it can directly determine the accuracy of the first AI model based on the first correspondence, thus reducing resource waste.

[0047] In conjunction with the third aspect, in some implementations, a second indication information is received, which is used to indicate a first value M, or the second indication information is used to indicate a first determination method and a first value M; wherein, the first value M is the number of probability intervals included in the first correspondence, and the first determination method is the method of determining the first correspondence.

[0048] In this embodiment of the application, the terminal device receives indication information from the network device, and then determines M probability intervals or a first correspondence based on the indication information.

[0049] In conjunction with the third aspect, in some implementations, based on the first AI model, the probability corresponding to the first optimal reference signal resource in the first reference signal resource set is determined. The probability corresponding to the first optimal reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the first reference signal resource set. The first reference signal resource set includes at least one reference signal resource. Fifth indication information is sent, which is used to indicate the probability corresponding to the first optimal reference signal resource.

[0050] In this embodiment, the terminal device determines the probability corresponding to the first optimal reference signal resource based on the first AI model and reports the probability corresponding to the first optimal reference signal resource to the network device, thereby enabling the network device to determine the accuracy of the first AI model and thus monitor the first AI model.

[0051] Fourthly, a communication method is provided. The method includes: receiving fourth indication information, the fourth indication information indicating a first correspondence, the first correspondence indicating a correspondence between the probability interval to which the probability corresponding to the best reference signal resource determined by the first AI model belongs and the accuracy of the first AI model, the first AI model determining the probability that each reference signal resource in the fourth reference signal resource set is the best reference signal resource in the fourth reference signal resource set, the accuracy of the first AI model characterizing the accuracy of the probability determined by the first AI model, and the fourth reference signal resource set including at least one reference signal resource.

[0052] For example, the measured value of the channel state information of the best reference signal resource in the fourth reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the fourth reference signal resource set besides the best reference signal resource.

[0053] In this embodiment of the application, the network-side device can receive a first correspondence between the probability interval to which the probability of the best reference signal resource determined by the first AI model belongs and the accuracy of the first AI model, as reported by the terminal-side device, so as to facilitate the monitoring of the first AI model according to the first correspondence.

[0054] In conjunction with the fourth aspect, in some implementations, the first correspondence is determined based on M probability intervals, the second best reference signal resource and the third best reference signal resource in each of the at least one third reference signal resource set; wherein, the minimum value in the M probability intervals is greater than or equal to 0, the maximum value in the M probability intervals is less than or equal to 1, M is an integer greater than 1, the measured value of the channel state information corresponding to the second best reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set, and the probability corresponding to the third best reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model.

[0055] In conjunction with the fourth aspect, in some implementations, the accuracy corresponding to each probability interval is determined based on the number of third best reference signal resources included in each of the M probability intervals, the identification information of each third best reference signal resource included in each probability interval, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in each probability interval; wherein, the probability corresponding to the third best reference signal resource in each set of third reference signal resources belongs to one of the M probability intervals, and each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belong to the same set of third reference signal resources.

[0056] In this embodiment of the application, the network-side device can sense the specific method by which the terminal-side device determines the first correspondence, thereby facilitating the monitoring of the first AI model.

[0057] In conjunction with the fourth aspect, in some implementations, a second indication message is sent, which is used to indicate the first value M, or the second indication message is used to indicate the first determination method and the first value M; wherein, the first value M is the number of probability intervals included in the first correspondence, and the first determination method is the method of determining the first correspondence.

[0058] In this embodiment of the application, the network-side device can send indication information to the terminal-side device, thereby enabling the terminal-side device to determine M probability intervals or determine a first correspondence based on the indication information.

[0059] In conjunction with the fourth aspect, in some implementations, a fifth indication information is received. The fifth indication information is used to indicate the probability corresponding to the first optimal reference signal resource. The probability corresponding to the first optimal reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the first set of reference signal resources determined by the first AI model. The first set of reference signal resources includes at least one reference signal resource.

[0060] In conjunction with the fourth aspect, in some implementation methods, the first accuracy of the first AI model is determined based on the first correspondence and the probability corresponding to the first optimal reference signal resource. The first accuracy is used to characterize the accuracy of the probability corresponding to the first optimal reference signal resource determined by the first AI model.

[0061] For example, the accuracy of the probability corresponding to the first optimal reference signal resource is: the probability that the reference signal resource with the highest probability in the first reference signal resource set determined by the first AI model is the reference signal resource with the highest measured value of channel information state in the first reference signal resource set.

[0062] In this embodiment of the application, the network-side device receives the probability corresponding to the first optimal reference signal resource reported by the terminal-side device, and then determines the accuracy of the first AI model based on the first correspondence and the probability corresponding to the first optimal reference signal resource, thereby realizing the monitoring of the first AI model.

[0063] Fifthly, a communication device is provided. The device includes modules or units for implementing either the first or third aspect, or any possible implementation thereof.

[0064] In a sixth aspect, a communication device is provided. The device includes modules or units for implementing either the second or fourth aspect, or any possible implementation thereof.

[0065] In a seventh aspect, a communication device is provided. The communication device includes at least one processor and a communication interface, the communication interface being used for the communication device to interact with other communication devices, and when program instructions are executed in the at least one processor, causing the communication device to perform the method as described in any one of the first or third aspects or any possible implementation thereof.

[0066] Eighthly, a communication device is provided. The communication device includes at least one processor and a communication interface for the communication device to interact with other communication devices. When program instructions are executed in the at least one processor, the communication device causes the communication device to perform the method described in any of the second or fourth aspects, or any possible implementation thereof.

[0067] Ninthly, a communication system is provided. This communication system includes the communication devices described in the fifth aspect and the communication devices described in the sixth aspect, or includes the communication devices described in the seventh aspect and the communication devices described in the eighth aspect.

[0068] In a tenth aspect, a computer-readable storage medium is provided that stores program code for execution by a device, wherein when the program code is executed, the method described in any of the first to fourth aspects above, or in any possible implementation thereof, is executed.

[0069] Eleventhly, a chip is provided, the chip including at least one processor, which, when program instructions are executed in the at least one processor, causes the method described in any one of the first to fourth aspects or any possible implementation thereof to be executed.

[0070] In a twelfth aspect, a computer program product is provided, the computer program product including program instructions that, when the computer program product is run on a communication device, cause the communication device to perform the method described in any one of the first to fourth aspects or any possible implementation thereof. Attached Figure Description

[0071] Figure 1 is a schematic structural diagram of a communication system according to an embodiment of this application.

[0072] Figure 2 is a schematic structural diagram of a communication system according to another embodiment of this application.

[0073] Figure 3 is a schematic structural diagram of a communication system according to another embodiment of this application.

[0074] Figure 4 is a schematic diagram of wide beam and narrow beam.

[0075] Figure 5 is a schematic flowchart of a communication method according to an embodiment of this application.

[0076] Figure 6 is a schematic flowchart of a communication method according to another embodiment of this application.

[0077] Figure 7 is a schematic flowchart of a communication method according to another embodiment of this application.

[0078] Figure 8 is a schematic flowchart of a communication method according to another embodiment of this application.

[0079] Figure 9 is a schematic flowchart of a method for determining a first correspondence according to an embodiment of this application.

[0080] Figure 10 is a schematic structural block diagram of a communication device according to an embodiment of the present application.

[0081] Figure 11 is a schematic structural block diagram of a communication device according to another embodiment of this application. Detailed Implementation

[0082] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0083] This application will present various aspects, embodiments, or features relating to a system comprising multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible.

[0084] Furthermore, in the embodiments of this application, the words "exemplary," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in the embodiments of this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplary" is intended to present the concept in a concrete manner.

[0085] The business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0086] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0087] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "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 represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0088] 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 networks, such as 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.

[0089] In the communication system of this application embodiment, a network element can send signals to or receive signals from another network element. The signals may include information, signaling, or data. The network element can also be replaced by an entity, network entity, device, communication device, communication module, node, communication node, etc. This application embodiment uses a network element as an example for description. For example, the communication system may 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 application embodiment 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.

[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, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or 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 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 100 may include at least one network device, such as network device 110 shown in Figure 1. The communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1. Network device 110 and terminal devices (such as terminal devices 120 and 130) can communicate via a wireless link. The communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0092] In some embodiments, the communication system 100 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.

[0093] In one possible implementation, 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 the terminal device. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal device. 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 network device 110, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on the terminal device.

[0094] It should be understood that Figure 1 is only used as an example of the AI ​​network element 140 being directly connected to the network device 110. In other scenarios, the AI ​​network element 140 can also be connected to a terminal device. Alternatively, the AI ​​network element 140 can be connected to both the network device 110 and a terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the 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.

[0095] AI element 140 can also be set as a module in network devices and / or terminal devices, for example, in network device 110 or terminal device shown in Figure 1.

[0096] It should be noted that Figure 1 is a simplified schematic diagram 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 Figure 1. In practical applications, the communication system may include multiple network devices or multiple terminal devices. This application embodiment does not limit the number of network devices and terminal devices included in the communication system.

[0097] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0098] 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 vehicles, 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 wireless modems, 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.

[0099] 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.

[0100] 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.

[0101] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can include an access network device (i.e., an access network node) or a radio access network device, such as a base station. In this application embodiment, the radio access network device can refer to a radio access network (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 including: 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, equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in future communication networks, or equipment performing base station functions in future communication networks. 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 vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0102] 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.

[0103] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0104] 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.

[0105] RAN nodes can support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs 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, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0106] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement one or more functions before and after layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more functions of inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU. For uplink transmission, the DU is configured to implement one or more functions before and after demapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and demapping), while other functions after demapping (e.g., digital BF or one or more functions of fast Fourier transform (FFT) / removing CP) are moved to the RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0107] 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.

[0108] 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 radio access network (ORAN / O-RAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called 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.

[0109] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself, or 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 or used in conjunction with the network device. In this embodiment, the example of a network device is used only to illustrate the apparatus for implementing the functions of the network device, and does not constitute a limitation on the solutions described in this embodiment.

[0110] 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.

[0111] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can 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 over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0112] 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.

[0113] It can also be understood that AI nodes can be AI network elements or AI modules. AI nodes can be independent devices, or they can be integrated into the same device to implement 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 AI ​​nodes described above.

[0114] Figure 2 illustrates a possible application framework in a communication system. As shown in Figure 2, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminal equipment, or one or more devices in operation administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 2 for clarity). An access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. CU and / or DU can also be equipped with one or more AI modules. Optionally, a CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP. Exemplarily, CU and DU are connected via an F1 interface. CU and CU are connected via an Xn interface.

[0115] AI modules are 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 biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0116] 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.

[0117] The network device can be a network device equipped with one or more AI modules. The network device can be one or more devices in the core network, access network (RAN) node, or OAM as shown in Figure 2. For example, the AI ​​module can be the RIC shown in Figure 3, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in the RAN node (e.g., in CU, DU), while the non-real-time RIC is set in the OAM, cloud server, core network device, or other network device. The RIC can obtain a subset from multiple terminal devices from the RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble it into a training dataset #2, and train based on the training dataset #2. Exemplarily, the near real-time RIC and the non-real-time RIC can also be set up separately as a network element; the network device can be a near real-time RIC or a non-real-time RIC.

[0118] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 2, used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0119] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. Optionally, the NRT RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the NRT RIC delivers inference results to a DU, which then forwards them to an RU.

[0120] Non-real-time RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0121] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Optionally, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0122] Beam management refers to the process by which terminal devices and network devices periodically identify the optimal beam. To achieve beam management, one possible approach is to reduce beam scanning overhead through methods such as layered scanning. This involves scanning a wide beam first, followed by scanning a small portion of narrow beams within the wide beam, thus reducing overhead. A schematic diagram of wide and narrow beams is shown in Figure 4. As shown in Figure 4, compared to narrow beams, wide beams have a wider beam angle and can transmit signals in a wider range of directions. Compared to wide beams, narrow beams have a narrower beam angle and can transmit signals in a smaller range of directions. When the sum of the beam angles of a set of wide beams is the same as the sum of the beam angles of a set of narrow beams, the number of beams included in the wide beam set is less than the number of beams included in the narrow beam set.

[0123] Beam selection is primarily accomplished through reference signals and corresponding beam measurements. Specifically, the reference signal can include one or more of the following: SSB, or CSI-RS. The SSB can be a cell broadcast signal, comprising the primary synchronization signal (PSS), secondary synchronization signal (SSS), physical broadcast channel (PBCH), and demodulation reference signal (DMRS). The SSB is transmitted periodically according to the cell configuration, and can be considered a wide-beam signal. Correspondingly, the CSI-RS signal can be a user-level signal, and can be understood as a narrow-beam signal. AI technology can also be applied to beam scanning to reduce overhead. AI-based beam management typically uses the results of wide-beam scanning as input to the AI ​​model. This input might be, for example, the measured reference signal received power (RSRP) obtained by the terminal device under the SSB beam. The output of the AI ​​model is the identification information (ID) of one or more narrow beams and the probability that each narrow beam is the best narrow beam in a set of narrow beams. When the AI ​​model is deployed in the terminal device, the UE can directly use the SSB measurement results, that is, the RSRP value, as the input of the AI ​​model, and report the output of the AI ​​model to the network device. Specifically, when reporting the ID of a narrow beam, this narrow beam is the optimal beam predicted by the AI ​​model. In AI model-based beam management, the network device and / or the terminal device need to monitor the AI ​​model to ensure beam management quality.

[0124] For AI models deployed in terminal devices, Scheme 1 allows the UE to report the ID of the beam predicted by the AI ​​model and the probability corresponding to the beam, enabling the network device to use the probability corresponding to the beam as the accuracy of the AI ​​model's prediction result. However, there is a significant error between the probability corresponding to the beam and the accuracy of the AI ​​model in Scheme 1. Scheme 2 determines the accuracy of the AI ​​model through the following steps: the network device configures reference signal resource set A and reference signal resource set B for the terminal device; the terminal device uses the measured value of the channel state information corresponding to at least one reference signal resource in reference signal resource set A as the input to the AI ​​model, thereby obtaining the output of the AI ​​model: the best reference signal resource determined by prediction in reference signal resource set B; the terminal device performs measurements based on reference signal resource set B to determine the best reference signal resource determined by measurement in reference signal resource set B; the terminal device determines the accuracy of the AI ​​model by comparing the best reference signal resource determined by measurement in reference signal resource set B with the best reference signal resource determined by prediction. However, in Scheme 2, a large number of reference signal resources are not used for data transmission, resulting in resource waste.

[0125] In view of this, this application provides a communication method that can determine the accuracy of an AI model, thereby facilitating the monitoring of the AI ​​model. Furthermore, the method provided in this application can improve the reliability of determining the accuracy of the AI ​​model and reduce resource waste.

[0126] The methods provided in this application embodiment can be executed by a terminal-side device or a network-side device. The terminal-side device can refer to the terminal device itself, a component within the terminal device (e.g., a processor, chip, or chip system), an AI entity serving the terminal device, such as a server (e.g., an over-the-top (OTT) server or a cloud server), or a logic module or software capable of implementing all or part of the terminal device's functions. The network-side device can refer to the network device itself, a component within the network device (e.g., a processor, chip, or chip system), an AI entity serving the network device, such as a RAN intelligent controller (RIC), operation administration and maintenance (OAM), or a server (e.g., an OTT server or a cloud server), or a logic module or software capable of implementing all or part of the network device's functions. Communication between the terminal-side device and the network-side device can be achieved through a communication link between the terminal device and the network device, a communication link between servers, forwarding through other communication devices outside the server, or a wired link. The following description uses terminal devices or network devices as examples. It is understood that terminal devices can be replaced by terminal-side devices, such as one or more of the aforementioned terminal-side devices, and network devices can also be replaced by network-side devices, such as one or more of the aforementioned network-side devices.

[0127] Figure 5 is a schematic flowchart of a communication method provided in an embodiment of this application. The method in Figure 5 is applied to a communication system, such as the communication system shown in Figure 1, Figure 2, or Figure 3. The network device in Figure 5 is, for example, the network device 110 in Figure 1, the core network device in Figure 2, the access network node, or the access network node in Figure 3. The terminal device in Figure 5 is, for example, the terminal device in Figure 1, Figure 2, or Figure 3. The method in Figure 5 includes the following steps.

[0128] 510, determine the first accuracy of the first AI model.

[0129] A first AI model is used to determine the probability that each reference signal resource in a first set of reference signal resources is the best reference signal resource in the first set of reference signal resources. The first set of reference signal resources includes at least one reference signal resource. A first accuracy rate is used to characterize the accuracy of the probability corresponding to the first best reference signal resource in the first set of reference signal resources determined by the first AI model. The probability corresponding to the first best reference signal resource is the probability that the first best reference signal resource is the best reference signal resource in the first set of reference signal resources. The probability corresponding to the first best reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the first set of reference signal resources.

[0130] For example, the accuracy of the probability corresponding to the first optimal reference signal resource is: the probability that the reference signal resource with the highest probability in the first reference signal resource set determined by the first AI model is the reference signal resource with the highest measured value of channel information state in the first reference signal resource set.

[0131] For example, the measured value of the channel state information of the best reference signal resource in the first reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the first reference signal resource set besides the best reference signal resource.

[0132] In some embodiments, the first reference signal resource set may be a virtual set. In other words, the network device may not have configured the first reference signal resource set to the terminal device.

[0133] For example, the first AI model is a classification model. This classification model is used to predict the probability that each reference signal resource in reference signal resource set B is the best reference signal resource in reference signal resource set B, based on the measured values ​​of channel state information corresponding to at least one reference signal resource in reference signal resource set A. The measured value of the channel state information of the best reference signal resource in reference signal resource set B is greater than or equal to the measured values ​​of the channel state information of other reference signal resources in reference signal resource set B besides the best reference signal resource. The signal angle corresponding to reference signal resource set A is the same as the signal angle corresponding to reference signal resource set B, and the number of reference signal resources included in reference signal resource set A is less than or equal to the number of reference signal resources included in reference signal resource set B. For example, reference signal resource set A is a subset of reference signal resource set B. For example, the reference signal resources in reference signal resource set B are narrow beams. Or, the signal angles corresponding to the reference signal resources included in reference signal resource set A are greater than the signal angles corresponding to the reference signal resources included in reference signal resource set B. For example, the reference signal resources in reference signal resource set A are wide beams, while the reference signal resources in reference signal resource set B are narrow beams.

[0134] It should be understood that the probability corresponding to a reference signal resource is the probability that the reference signal resource is the best reference signal resource in the set of reference signal resources to which it belongs. The meaning of "the probability corresponding to the best reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the set to which the best reference signal resource belongs" is similar to the meaning of "the probability corresponding to the best reference signal resource is greater than the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs," and "the probability corresponding to the best reference signal resource is greater than or equal to the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs," and they can be used interchangeably.

[0135] Optionally, the terminal device determines the first accuracy rate based on the first correspondence and the probability corresponding to the first optimal reference signal resource. In other words, the first accuracy rate is determined based on the first correspondence and the probability corresponding to the first optimal reference signal resource. The first correspondence is used to indicate the correspondence between the probability determined by the first AI model and the accuracy rate of the first AI model. For example, the first correspondence is used to indicate the correspondence between the probability interval to which the probability determined by the first AI model belongs and the accuracy rate of the first AI model.

[0136] In some embodiments, the terminal device determines the probability interval to which the probability corresponding to the first optimal reference signal resource belongs based on the probability corresponding to the first optimal reference signal resource. The terminal device then determines the accuracy rate corresponding to the probability interval to which the probability corresponding to the first optimal reference signal resource belongs based on a first correspondence, thereby determining the first accuracy rate.

[0137] For example, suppose the first correspondence is as shown in Table 1 below.

[0138] Table 1 First Correspondence Relationship

[0139] As shown in Table 1, probability intervals A, B, and C are three non-overlapping probability intervals. The value range of these three probability intervals is either continuous or discrete (i.e., each of the three probability intervals includes at least one discrete value). The value range of these three probability intervals is greater than or equal to 0, and less than or equal to 1. The accuracy rate corresponding to probability interval A is accuracy rate A, the accuracy rate corresponding to probability interval B is accuracy rate B, and the accuracy rate corresponding to probability interval C is accuracy rate C. If the network device determines that the probability interval to which the probability corresponding to the first optimal reference signal resource belongs is probability interval A, then the network device can determine the first accuracy rate of the first AI model as accuracy rate A according to Table 1.

[0140] Optionally, before step 510, the terminal device determines the probability corresponding to the first optimal reference signal resource based on the first AI model.

[0141] In some embodiments, the terminal device determines the probability corresponding to the first optimal reference signal resource based on a fifth set of reference signal resources and a first AI model. The fifth set of reference signal resources includes at least one reference signal resource. Specifically, the terminal device performs measurements based on the fifth set of reference signal resources to determine the measured value of channel state information corresponding to each reference signal resource in the fifth set. The terminal device uses the measured value of channel state information corresponding to each reference signal resource in the fifth set as input to the first AI model to obtain the output of the first AI model. The output of the first AI model includes the probability corresponding to at least one reference signal resource in the first set, where the at least one reference signal resource includes the first optimal reference signal resource. The output of the first AI model also includes identification information for each of the at least one reference signal resource.

[0142] For example, the signal angle corresponding to each reference signal resource in the fifth reference signal resource set is greater than the signal angle corresponding to each reference signal resource in the first reference signal resource set. In other words, when the signal angle corresponding to the fifth reference signal resource set is the same as the signal angle corresponding to the first reference signal resource set, the number of reference signal resources included in the fifth reference signal resource set is less than the number of reference signal resources included in the first reference signal resource set. For example, when the reference signal resource is a beam, the reference signal resources in the fifth reference signal resource set are wide beams, and the reference signal resources in the first reference signal resource set are corresponding narrow beams. In this case, the network device configures the fifth reference signal resource set for the terminal device.

[0143] For example, the signal angle corresponding to each reference signal resource in the fifth reference signal resource set is the same as the signal angle corresponding to each reference signal resource in the first reference signal resource set, and the number of reference signal resources included in the fifth reference signal resource set is less than or equal to the number of reference signal resources included in the first reference signal resource set. For example, the fifth reference signal resource set is a subset of the first reference signal resource set. For example, the reference signal resources in the first reference signal resource set are narrow beams.

[0144] For example, the channel state information includes RSRP or signal to interference plus noise ratio (SINR).

[0145] Optionally, before step 510, the terminal device determines a first correspondence. This first correspondence is determined based on M probability intervals, a second optimal reference signal resource in each of at least one third reference signal resource set, and a third optimal reference signal resource. Each of the M probability intervals is a value range between 0 and 1. The value range of each of the M probability intervals is either continuous or discrete (i.e., each probability interval includes at least one discrete value). The values ​​in each of the M probability intervals are not repeated. The minimum value in the M probability intervals is greater than or equal to 0, and the maximum value in the M probability intervals is less than or equal to 1, where M is an integer greater than 1. The measured value of the channel state information corresponding to the second optimal reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set. The probability corresponding to the third optimal reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model.

[0146] It should be understood that the meaning of "the measured value of the channel state information corresponding to the best reference signal resource is the maximum value of the channel state information corresponding to each reference signal resource in the reference signal resource set to which the best reference signal resource belongs" is similar to the meaning of "the measured value of the channel state information corresponding to the best reference signal resource is greater than the measured value of the channel state information corresponding to the reference signal resources in the reference signal resource set to which the best reference signal resource belongs, excluding the best reference signal resource" and "the measured value of the channel state information corresponding to the best reference signal resource is greater than or equal to the measured value of the channel state information corresponding to the reference signal resources in the reference signal resource set to which the best reference signal resource belongs, excluding the best reference signal resource".

[0147] In some embodiments, the terminal device determines M probability intervals based on a first value M. The terminal device also determines a second optimal reference signal resource and a third optimal reference signal resource in each of at least one third reference signal resource set. The terminal device further determines the first correspondence based on the M probability intervals and the second optimal and third optimal reference signal resources in each third reference signal resource set. See Figure 9 for a detailed implementation description.

[0148] For example, before step 510, the terminal device receives second indication information from the network device. This second indication information is used to indicate a first value M. Alternatively, the second indication information is used to indicate the first value M and a first determination method. The first value M is the number of probability intervals included in the first correspondence. The first determination method is the method for determining the first correspondence.

[0149] For example, when the second indication information is used to indicate the first determination method, the second indication information includes the first determination method, or the second indication information is used to indicate the index of the first determination method in the determination method set. The determination method set includes at least one method for determining the first correspondence. The determination method set is pre-configured information.

[0150] For example, the first determination method includes: determining the first correspondence based on M probability intervals and the second and third best reference signal resources in each of the at least one third reference signal resource set. See the description in step 930 for the specific determination method.

[0151] For example, the first value M and / or the first determination method are pre-configured information.

[0152] 520, send the first instruction message to the network device.

[0153] The terminal device sends a first indication message to the network device, and correspondingly, the network device receives the first indication message from the terminal device. This first indication message is used to indicate a first accuracy rate. Alternatively, the first indication message is used to request the configuration of a second set of reference signal resources. The second set of reference signal resources includes at least one reference signal resource.

[0154] When the first indication information is used to indicate a first accuracy, the first indication information is also used to indicate the identification information of a first optimal reference signal resource.

[0155] When the first indication information is used to request the configuration of a second set of reference signal resources, if the first accuracy is less than or equal to a first preset threshold, the terminal device sends the first indication information to the network device. If the first accuracy is greater than the first preset threshold, the terminal device sends a third indication information to the network device, which is used to indicate the identification information of the first optimal reference signal resource. In other words, the terminal device determines whether the accuracy of the first AI model meets expectations or requirements based on the first accuracy and the first preset threshold, thereby determining whether further measurement is needed. The specific value of the first preset threshold is not limited in this application embodiment; the first preset threshold is less than or equal to 1 and greater than or equal to 0.

[0156] For example, the first reference signal resource set and the second reference signal resource set may be the same or different.

[0157] It should be understood that, in this application, "two sets of reference signal resources are the same" means that each reference signal resource included in the two sets of reference signal resources is the same. "Two sets of reference signal resources are different" means that at least one reference signal resource included in the two sets of reference signal resources is different.

[0158] Optionally, the terminal device determines a second accuracy rate based on at least one accuracy rate of the first AI model. The at least one accuracy rate includes the first accuracy rate. Each of the at least one accuracy rate is determined according to the first correspondence. If the second accuracy rate is less than or equal to a second preset threshold, the terminal device calibrates the first AI model. The specific value of the second preset threshold is not limited in this embodiment; the second preset threshold is less than or equal to 1 and greater than or equal to 0.

[0159] For example, the second accuracy rate is the average or weighted average of the at least one accuracy rate.

[0160] For example, after calibrating the first AI model, the terminal device determines a second correspondence between the probability interval to which the probabilities determined by the calibrated first AI model belong and the accuracy rate. Based on this second correspondence, the terminal device determines the accuracy rate of the calibrated first AI model.

[0161] In this embodiment, the terminal device can determine the accuracy of the first AI model, thereby facilitating its monitoring. Simultaneously, the terminal device can report the accuracy of the first AI model to the network device, facilitating its monitoring as well. Alternatively, the terminal device can request the network device to configure a set of reference signal resources based on the accuracy of the first AI model, thereby facilitating the determination of suitable communication resources.

[0162] For example, in the method shown in Figure 5, the terminal device can determine the first accuracy rate of the first AI model itself. In the method shown in Figure 6, the network device can receive the first accuracy rate of the first AI model from the terminal device, or it can determine the first accuracy rate of the first AI model itself.

[0163] Figure 6 is a schematic flowchart of a communication method provided in an embodiment of this application. The method in Figure 6 is applied to a communication system, such as the communication system shown in Figure 1, Figure 2, or Figure 3. The network device in Figure 6 is, for example, the network device 110 in Figure 1, the core network device in Figure 2, the access network node, or the access network node in Figure 3. The terminal device in Figure 6 is, for example, the terminal device in Figure 1, Figure 2, or Figure 3. The method in Figure 6 includes the following steps.

[0164] 610, determine the first accuracy of the first AI model.

[0165] A first AI model is used to determine the probability that each reference signal resource in a first set of reference signal resources is the best reference signal resource in the first set of reference signal resources. The first set of reference signal resources includes at least one reference signal resource. A first accuracy rate is used to characterize the accuracy of the probability corresponding to the first best reference signal resource in the first set of reference signal resources determined by the first AI model. The probability corresponding to the first best reference signal resource is the probability that the first best reference signal resource is the best reference signal resource in the first set of reference signal resources. The probability corresponding to the first best reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the first set of reference signal resources.

[0166] For example, the accuracy of the probability corresponding to the first optimal reference signal resource is: the probability that the reference signal resource with the highest probability in the first reference signal resource set determined by the first AI model is the reference signal resource with the highest measured value of channel information state in the first reference signal resource set.

[0167] For example, the measured value of the channel state information of the best reference signal resource in the first reference signal resource set is greater than or equal to the measured value of the channel state information of other reference signal resources in the first reference signal resource set besides the best reference signal resource.

[0168] In some embodiments, the first reference signal resource set may be a virtual set. In other words, the network device may not have configured the first reference signal resource set to the terminal device.

[0169] For example, the first AI model is a classification model. See the description of the classification model in step 510.

[0170] It should be understood that the probability corresponding to a reference signal resource is the probability that the reference signal resource is the best reference signal resource in the set of reference signal resources to which it belongs. The meaning of "the probability corresponding to the best reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the set to which the best reference signal resource belongs" is similar to the meaning of "the probability corresponding to the best reference signal resource is greater than the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs," and "the probability corresponding to the best reference signal resource is greater than or equal to the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs."

[0171] Optionally, the network device determines a first accuracy rate based on the first correspondence and the probability corresponding to the first optimal reference signal resource. In other words, the first accuracy rate is determined based on the first correspondence and the probability corresponding to the first optimal reference signal resource. The first correspondence is used to indicate the correspondence between the probability determined by the first AI model and the accuracy rate of the first AI model. For example, the first correspondence is used to indicate the correspondence between the probability interval to which the probability determined by the first AI model belongs and the accuracy rate of the first AI model. The specific method for determining the first accuracy rate is described in step 510.

[0172] For example, before step 610, the network device receives fourth indication information from the terminal device, which is used to indicate the first correspondence.

[0173] For example, before step 610, the network device receives fifth indication information from the terminal device, which is used to indicate the probability corresponding to the first optimal reference signal resource.

[0174] Optionally, the network device receives a sixth indication information from the terminal device, which is used to indicate the first accuracy rate.

[0175] Optionally, before step 610, the network device sends indication information to the terminal device to instruct the terminal device to determine a first correspondence, thereby enabling the network device to determine a first accuracy of the first AI model based on the first correspondence. For example, the network device sends second indication information to the terminal device, which indicates a first value M. Alternatively, the second indication information indicates the first value M and a first determination method. The first value M is the number of probability intervals included in the first correspondence. The first determination method is the method for determining the first correspondence.

[0176] For example, when the second indication information is used to indicate the first determination method, the second indication information includes the first determination method, or the second indication information is used to indicate the index of the first determination method in the determination method set. The determination method set includes at least one method for determining the first correspondence. The determination method set is pre-configured information.

[0177] For example, the first determination method includes: determining the first correspondence based on M probability intervals and the second and third best reference signal resources in each of the at least one third reference signal resource set. See the description in step 930 for the specific determination method.

[0178] For example, when the second indication information is used to indicate the first value M, the first determination method is a pre-configured method.

[0179] Optionally, if the first accuracy is greater than a first preset threshold, the network device determines the first optimal reference signal resource as the resource for communicating with the terminal device. That is, the network device communicates with the terminal device through the first optimal reference signal resource, such as transmitting data. The specific value of the first preset threshold is not limited in this embodiment; the first preset threshold is less than or equal to 1 and greater than or equal to 0.

[0180] Optionally, if the first accuracy is less than or equal to a first preset threshold, the network device performs step 620.

[0181] 620, Send the first configuration information to the terminal device.

[0182] The network device sends first configuration information to the terminal device, the first configuration information being used to configure a second set of reference signal resources. The second set of reference signal resources includes at least one reference signal resource.

[0183] For example, the first reference signal resource set and the second reference signal resource set may be the same or different.

[0184] It should be understood that two sets of reference signal resources being identical includes the following: every reference signal resource included in the two sets of reference signal resources is the same. Two sets of reference signal resources being different includes the following: at least one reference signal resource included in the two sets of reference signal resources is different.

[0185] Optionally, the network device determines a second accuracy rate based on at least one accuracy rate of the first AI model. The at least one accuracy rate includes the first accuracy rate. Each of the at least one accuracy rates is determined according to the first correspondence. If the second accuracy rate is less than or equal to a second preset threshold, the network device sends a seventh indication message to the terminal device. The seventh indication message is used to instruct the calibration of the first AI model. The specific value of the second preset threshold is not limited in this embodiment; the second preset threshold is less than or equal to 1 and greater than or equal to 0.

[0186] For example, the second accuracy rate is the average or weighted average of the at least one accuracy rate.

[0187] In this embodiment, the network device can determine the accuracy of the first AI model, thereby facilitating the monitoring of the first AI model. Furthermore, the network device can determine the reliability of the optimal reference signal resource predicted by the first AI model based on its accuracy. If the accuracy of the first AI model does not meet a preset threshold, the network device can instruct the terminal device to perform further measurements, thereby facilitating the determination of suitable communication resources.

[0188] For example, in the method of Figure 6, the network device can determine the accuracy of the first AI model itself. Before the network device determines the accuracy of the first AI model itself, the network device can instruct the terminal device to determine and report a first correspondence, so as to determine the first accuracy of the first AI model based on the first correspondence, as shown in Figure 7.

[0189] Figure 7 is a schematic flowchart of a communication method provided in an embodiment of this application. The method in Figure 7 is applied to a communication system, such as the communication system shown in Figure 1, Figure 2, or Figure 3. The network device in Figure 7 is, for example, the network device 110 in Figure 1, the core network device in Figure 2, the access network node, or the access network node in Figure 3. The terminal device in Figure 7 is, for example, the terminal device in Figure 1, Figure 2, or Figure 3. The method in Figure 7 includes the following steps.

[0190] 701, Send the second instruction information to the terminal device.

[0191] The network device sends a second indication message to the terminal device, and correspondingly, the terminal device receives the second indication message from the network device. This second indication message is used to indicate a first value M. Alternatively, the second indication message is used to indicate a first determination method and the first value M. Here, the first value M is the number of probability intervals included in the first correspondence, that is, the first value M is used to determine M probability intervals. M is a positive integer greater than 1. The first determination method is the method for determining the first correspondence. The first correspondence is described in steps 510 or 610.

[0192] For example, when the second indication information is used to indicate the first determination method, the second indication information includes the first determination method, or the second indication information is used to indicate the index of the first determination method in the set of determination methods. The set of determination methods includes at least one method for determining the first correspondence.

[0193] For example, the first determination method includes: determining the first correspondence based on M probability intervals and a second optimal reference signal resource and a third optimal reference signal resource in each of at least one third reference signal resource set. Each third reference signal resource set includes at least one reference signal resource.

[0194] 702, Configure at least one third reference signal resource set for the terminal device.

[0195] To determine the first correspondence, after determining the first value M and the first determination method, the terminal device can further determine the second optimal reference signal resource and the third optimal reference signal resource in each of at least one third reference signal resource set. The measured value of the channel state information corresponding to the second optimal reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set. In other words, the network device needs to configure at least one third reference signal resource set for the terminal device, enabling the terminal device to perform measurements based on this at least one third reference signal resource set to determine the second optimal reference signal resource in each third reference signal resource set.

[0196] In some embodiments, the probability corresponding to the third best reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model. That is, the network device can configure at least one sixth reference signal resource set to the terminal device, enabling the terminal device to measure the channel state information of each reference signal resource in each sixth reference signal resource set, thereby determining the third best reference signal resource in each third reference signal resource set based on the first AI model and the measured channel state information of each reference signal resource in each sixth reference signal resource set.

[0197] For example, each of the at least one third reference signal resource set includes at least one reference signal resource. Each of the at least one sixth reference signal resource set includes at least one reference signal resource. Each of the at least one sixth reference signal resource set corresponds to a third reference signal resource set. The signal angle corresponding to each reference signal resource in the sixth reference signal resource set is greater than the signal angle corresponding to each reference signal resource in the corresponding third reference signal resource set. In other words, when the signal angle corresponding to the sixth reference signal resource set is the same as the signal angle corresponding to the corresponding third reference signal resource set, the number of reference signal resources included in the sixth reference signal resource set is less than the number of reference signal resources included in the corresponding third reference signal resource set. In this case, the network device configures the at least one sixth reference signal resource set and the at least one third reference signal resource set for the terminal device.

[0198] For example, when the reference signal resources are beams, the reference signal resources in the sixth set of reference signal resources are wide beams, and the reference signal resources in the third set of reference signal resources are corresponding narrow beams. The wide and narrow beams are described in Figure 4.

[0199] For example, the signal angle corresponding to each reference signal resource in the sixth reference signal resource set is the same as the signal angle corresponding to each reference signal resource in the corresponding third reference signal resource set, and the number of reference signal resources included in the sixth reference signal resource set is less than or equal to the number of reference signal resources included in the corresponding third reference signal resource set. For example, the sixth reference signal resource set is a subset of the corresponding third reference signal resource set. For example, the reference signal resources in the third reference signal resource set are narrow beams.

[0200] 703, determine the first correspondence.

[0201] The terminal device determines a first correspondence. This first correspondence is determined based on M probability intervals and the second and third best reference signal resources in each of the at least one third reference signal resource set. See the description in step 510 for details.

[0202] In some embodiments, the terminal device determines M probability intervals based on a first value M. The terminal device performs measurements based on at least one third reference signal resource set to determine a second optimal reference signal resource in each third reference signal resource set. The measured value of the channel state information corresponding to the second optimal reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set. The terminal device determines a third optimal reference signal resource in each third reference signal resource set based on a first AI model and at least one sixth reference signal resource. The probability corresponding to the third optimal reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model. The terminal device also determines the first correspondence based on the M probability intervals, the second optimal reference signal resource in each third reference signal resource set, and the third optimal reference signal resource. See Figure 9 for a detailed implementation description.

[0203] In some embodiments, steps 701-703 are the training process for determining the first correspondence, and steps 704-713 are the inference process using the first correspondence; alternatively, steps 701-704 are the training process for determining the first correspondence, and steps 705-713 are the inference process using the first correspondence. If the first AI model is not updated, steps 701-703 do not need to be repeated. After the first AI model is updated, steps 701-703 can be repeated to determine the correspondence between the probability interval to which the updated first AI model belongs and the accuracy.

[0204] Optionally, steps 704-713 are optional and can be performed or not.

[0205] 704, sends the fourth instruction message to the network device.

[0206] The terminal device sends a fourth indication message to the network device. Correspondingly, the network device receives the fourth indication message from the terminal device. This fourth indication message is used to indicate the first correspondence.

[0207] In some embodiments, the fourth indication information includes M probability intervals and the accuracy corresponding to each of the M probability intervals. Alternatively, the fourth indication information includes the accuracy corresponding to each of the M probability intervals. Alternatively, the fourth indication information includes L probability intervals and the accuracy corresponding to each of the L probability intervals. L is a positive integer, and L is less than M. The accuracy corresponding to each of the L probability intervals is greater than or equal to the accuracy corresponding to the other probability intervals in the M probability intervals excluding the L probability intervals. Alternatively, the accuracy corresponding to each of the L probability intervals is greater than or equal to a first accuracy threshold, and the specific value of this first accuracy threshold is not limited in this embodiment.

[0208] For example, the first accuracy threshold is pre-configured. Alternatively, the first accuracy threshold is indicated to the terminal device by the network device.

[0209] For example, the network device sends a tenth indication information to the terminal device, the tenth indication information being used to indicate the first accuracy threshold.

[0210] 705. Configure the fifth reference signal resource set for the terminal device. This fifth reference signal resource set is described in step 510.

[0211] Optionally, the angle corresponding to each reference signal resource in the fifth reference signal resource set may be greater than the angle corresponding to each reference signal resource in the first reference signal resource set. Alternatively, the fifth reference signal resource set may be a subset of the first reference signal resource set.

[0212] 706, Determine the probability corresponding to the first optimal reference signal resource in the first reference signal resource set.

[0213] The terminal device performs measurements based on a fifth set of reference signal resources to determine the measured value of channel state information corresponding to each reference signal resource in the fifth set of reference signal resources. The terminal device uses the measured value of the channel state information corresponding to each reference signal resource in the fifth set of reference signal resources as input to a first AI model to obtain the output of the first AI model. The output of the first AI model includes the probability corresponding to at least one reference signal resource in the first set of reference signal resources, where the at least one reference signal resource includes the first optimal reference signal resource. The output of the first AI model also includes identification information for each reference signal resource among the at least one reference signal resource.

[0214] For example, the channel state information may include RSRP or SINR, etc.

[0215] For example, the first reference signal resource set may be a virtual set. In other words, the network device may not have configured the first reference signal resource set to the terminal device.

[0216] 707, sends the fifth instruction message to the network device.

[0217] The terminal device sends a fifth indication message to the network device. Correspondingly, the network device receives the fifth indication message from the terminal device. This fifth indication message is used to indicate the probability corresponding to the first optimal reference signal resource. For example, the fifth indication message is also used to indicate the identification information of the first optimal reference signal resource.

[0218] 708. Determine the first accuracy rate based on the probability corresponding to the first optimal reference signal resource and the first correspondence.

[0219] The network device determines the probability interval to which the probability corresponding to the first optimal reference signal resource belongs based on the probability corresponding to the first optimal reference signal resource. Based on the first correspondence, the network device determines the accuracy corresponding to the probability interval to which the probability corresponding to the first optimal reference signal resource belongs, thereby determining the first accuracy of the first AI model.

[0220] Optionally, the network device determines the communication resources for communicating with the terminal device based on a first accuracy rate and a first preset threshold. In this embodiment, the value of the first preset threshold is not limited; the first preset threshold is less than or equal to 1 and greater than or equal to 0.

[0221] When the first accuracy rate is greater than or equal to a first preset threshold, the network device determines a first optimal reference signal resource as the resource for communicating with the terminal device. That is, the network device transmits data to the terminal device through the first optimal reference signal resource. When the first accuracy rate is less than the first preset threshold, the network device executes step 709.

[0222] 709, Send the first configuration information to the terminal device.

[0223] The network device sends first configuration information to the terminal device, and correspondingly, the terminal device receives the first configuration information from the network device. This first configuration information is used to configure a second set of reference signal resources, which includes at least one reference signal resource.

[0224] For example, each reference signal resource in the second set of reference signal resources is a narrow beam.

[0225] 710, Determine the measurement results corresponding to the second reference signal resource set.

[0226] After configuring the second reference signal resource set, the terminal device performs measurements based on all or part of the reference signal resources in the second reference signal resource set to determine the measured values ​​of the channel state information corresponding to some or all of the reference signal resources in the second reference signal resource set.

[0227] 711, Send the eighth instruction message to the network device.

[0228] The terminal device sends an eighth indication message to the network device. Correspondingly, the network device receives the eighth indication message from the terminal device. This eighth indication message is used to indicate the measured value of the channel state information corresponding to each reference signal resource in the second reference signal resource set. Alternatively, the eighth indication message is used to indicate the identification information of the best reference signal resource in the second reference signal resource set. Alternatively, the eighth indication message is used to indicate the identification information and the corresponding measured values ​​of the channel state information of K reference signal resources in the second reference signal resource set, where K is a positive integer. The measured value of the channel state information corresponding to the best reference signal resource in the second reference signal resource set is greater than or equal to the measured values ​​of the channel state information corresponding to the other reference signal resources in the second reference signal resource set besides the best reference signal resource. The measured values ​​of the channel state information corresponding to the K reference signal resources in the second reference signal resource set are greater than or equal to the measured values ​​of the channel state information corresponding to the other reference signal resources in the second reference signal resource set besides the K reference signal resources.

[0229] 712. Determine the second accuracy rate based on at least one accuracy rate of the first AI model.

[0230] The network device determines a second accuracy rate based on at least one accuracy rate of the first AI model. For example, the second accuracy rate is the average or weighted average of the at least one accuracy rate. Each of the at least one accuracy rates is determined according to the first correspondence, and the first accuracy rate belongs to the at least one accuracy rate. When the second accuracy rate is less than a second preset threshold, the network device executes step 713. This application embodiment does not limit the specific value of the second preset threshold; the second preset threshold is less than or equal to 1, and greater than or equal to 0.

[0231] 713, send the seventh instruction message to the terminal device.

[0232] The network device sends a seventh instruction message to the terminal device. Correspondingly, the terminal device receives the seventh instruction message from the network device. This seventh instruction message is used to instruct the first AI model to be calibrated.

[0233] Optionally, the terminal device calibrates the first AI model based on the seventh instruction information and determines a second correspondence between the probability and accuracy determined by the calibrated first AI model. The terminal device may also report the second correspondence to the network device so that the network device can monitor the first AI model.

[0234] In this embodiment, the terminal device determines and reports a first correspondence, enabling the network device to determine the accuracy of the probability corresponding to the optimal reference signal resource determined by the first AI model each time, based on the first correspondence. This allows the network device to determine whether the optimal reference signal resource determined by the first AI model is reliable, thus facilitating the monitoring of the first AI model. Furthermore, if the accuracy of the first AI model does not meet a preset threshold, the network device can instruct the terminal device to perform further measurements, thereby facilitating the determination of suitable communication resources.

[0235] For example, in the method of Figure 5, the terminal device can determine the accuracy of the first AI model itself. Before the terminal device determines the accuracy of the first AI model itself, the terminal device can determine a first correspondence according to the instructions of the network device, and then determine the first accuracy of the first AI model according to the first correspondence, as shown in Figure 8.

[0236] Figure 8 is a schematic flowchart of a communication method provided in an embodiment of this application. The method in Figure 8 is applied to a communication system, such as the communication system shown in Figure 1, Figure 2, or Figure 3. The network device in Figure 8 is, for example, the network device 110 in Figure 1, the core network device in Figure 2, the access network node, or the access network node in Figure 3. The terminal device in Figure 8 is, for example, the terminal device in Figure 1, Figure 2, or Figure 3. The method in Figure 8 includes the following steps.

[0237] 801. Send the second instruction information to the terminal device. The implementation of step 801 is similar to that of step 701, and will not be described again here.

[0238] 802, Send the ninth instruction message to the terminal device.

[0239] The network device sends a ninth indication message to the terminal device. Correspondingly, the terminal device receives the ninth indication message from the network device. This ninth indication message is used to indicate the accuracy of the first AI model reported by the terminal device.

[0240] Optionally, step 802 is optional and can be omitted.

[0241] 803. Configure at least one third reference signal resource set for the terminal device. The implementation of step 803 is similar to that of step 702, and will not be described again here.

[0242] Step 804: Determine the first correspondence. The implementation of step 804 is similar to that of step 703, and will not be repeated here.

[0243] In some embodiments, steps 801-804 are the training process for determining the first correspondence, and steps 805-813 are the inference process using the first correspondence. If the first AI model is not updated, steps 801-804 do not need to be repeated. After the first AI model is updated, steps 801-804 can be repeated to determine the correspondence between the probability interval to which the updated first AI model belongs and the accuracy.

[0244] Optionally, steps 805-813 are optional and can be performed or not.

[0245] Step 805: Configure the fifth reference signal resource set for the terminal device. The implementation of step 805 is similar to that of step 705, and will not be described again here.

[0246] Optionally, the angle corresponding to each reference signal resource in the fifth reference signal resource set is greater than the angle corresponding to each reference signal resource in the first reference signal resource set, or the fifth reference signal resource set is a subset of the first reference signal resource set.

[0247] 806. Determine the probability corresponding to the first optimal reference signal resource in the first reference signal resource set. The implementation of step 806 is similar to that of step 706, and will not be described again here.

[0248] 807. Determine the first accuracy rate based on the probability corresponding to the first optimal reference signal resource and the first correspondence relationship.

[0249] The terminal device determines the probability interval to which the probability corresponding to the first optimal reference signal resource belongs based on the probability corresponding to the first optimal reference signal resource. Based on the first correspondence, the terminal device determines the accuracy corresponding to the probability interval to which the probability corresponding to the first optimal reference signal resource belongs, thereby determining the first accuracy of the first AI model. The specific implementation is similar to step 708 and will not be repeated here.

[0250] 808, sends the first instruction message to the network device.

[0251] The terminal device sends a first indication message to the network device. Correspondingly, the network device receives the first indication message from the terminal device. This first indication message indicates a first accuracy rate. Alternatively, the first indication message requests the configuration of a second set of reference signal resources. This second set of reference signal resources includes at least one reference signal resource.

[0252] When the first indication information is used to indicate a first accuracy, the first indication information is also used to indicate the identification information of a first optimal reference signal resource.

[0253] Optionally, if the first accuracy is less than or equal to a first preset threshold, the terminal device sends a first indication message to the network device, which is used to request the configuration of a second set of reference signal resources. If the first accuracy is greater than the first preset threshold, the terminal device sends a third indication message to the network device, which is used to indicate the identification information of the first optimal reference signal resource. In other words, the terminal device determines whether the accuracy of the first AI model meets expectations based on the first accuracy and the first preset threshold, thereby determining whether further measurement is needed. The specific value of the first preset threshold is not limited in this embodiment; the first preset threshold is less than or equal to 1 and greater than or equal to 0.

[0254] For example, the first reference signal resource set and the second reference signal resource set may be the same or different.

[0255] It should be understood that two sets of reference signal resources being identical includes the following: every reference signal resource included in the two sets of reference signal resources is the same. Two sets of reference signal resources being different includes the following: at least one reference signal resource included in the two sets of reference signal resources is different.

[0256] 809, send the first configuration information to the terminal device.

[0257] The network device sends first configuration information to the terminal device, and correspondingly, the terminal device receives the first configuration information from the network device. This first configuration information is used to configure a second set of reference signal resources, which includes at least one reference signal resource.

[0258] For example, each reference signal resource in the second set of reference signal resources is a narrow beam.

[0259] Optionally, when the first indication information is used to indicate a first accuracy rate, the network device performs different steps by comparing the first accuracy rate and a first preset threshold. Specifically, when the first accuracy rate is greater than the first preset threshold, the network device determines a first optimal reference signal resource as the resource for communicating with the terminal device. That is, the network device transmits data to the terminal device through the first optimal reference signal resource. This application embodiment does not limit the specific value of the first preset threshold; the first preset threshold is less than or equal to 1 and greater than or equal to 0. When the first accuracy rate is less than or equal to the first preset threshold, the network device executes step 809.

[0260] Optionally, if the first indication information is used to request the configuration of the second set of reference signal resources, the network device directly executes step 809.

[0261] 810, Determine the measurement results corresponding to the second reference signal resource set.

[0262] 811, Send the eighth instruction message to the network device.

[0263] Steps 810 and 811 are similar to the corresponding steps in steps 710 and 711, and will not be repeated here.

[0264] 812. Determine the second accuracy rate based on at least one accuracy rate of the first AI model.

[0265] 813, send the seventh instruction information to the terminal device.

[0266] Optionally, step 812 is performed by a network device or a terminal device. When step 812 is performed by a network device, steps 812 and 813 are similar to steps 712 and 713, and will not be described again here. When step 812 is performed by a terminal device, the terminal device determines a second accuracy rate based on at least one accuracy rate of the first AI model. For example, the second accuracy rate is the average or weighted average of the at least one accuracy rate. Each of the at least one accuracy rates is determined according to the first correspondence, and the first accuracy rate belongs to the at least one accuracy rate. When the second accuracy rate is less than a second preset threshold, the terminal device calibrates the first AI model. The specific value of the second preset threshold is not limited in this embodiment; the second preset threshold is less than or equal to 1, and the second preset threshold is greater than or equal to 0. When step 812 is performed by a terminal device, step 813 is not performed.

[0267] For example, after calibrating the first AI model, the terminal device determines a second correspondence between the probability interval to which the probabilities determined by the calibrated first AI model belong and the accuracy rate. Based on this second correspondence, the terminal device determines the accuracy rate of the calibrated first AI model.

[0268] In this embodiment, after determining the first correspondence, the terminal device can determine the accuracy of the probability corresponding to the best reference signal resource determined by the first AI model each time, thereby determining whether the best reference signal resource determined by the first AI model is reliable, and thus facilitating the monitoring of the first AI model. Simultaneously, the terminal device can report the accuracy of the first AI model to the network device, thereby facilitating the network device's monitoring of the first AI model. Alternatively, the terminal device can request the network device to configure a set of reference signal resources based on the accuracy of the first AI model, thereby facilitating the determination of suitable communication resources.

[0269] Figure 9 is a schematic flowchart of a method for determining a first correspondence provided in an embodiment of this application. The method in Figure 9 is applied to a terminal device in a communication system, such as the terminal device in the communication system shown in Figure 1, Figure 2, or Figure 3. The method in Figure 9 includes the following steps.

[0270] 910, determine M probability intervals.

[0271] The terminal device determines M probability intervals based on a first value M. M is a positive integer greater than 1. The value ranges of each of the M probability intervals do not overlap. The value range of each of the M probability intervals is either a continuous range or a discrete value interval (i.e., each probability interval includes at least one discrete value). The minimum value included in the M probability intervals is greater than or equal to 0, and the maximum value included in the M probability intervals is less than or equal to 1.

[0272] For example, if the value range of each of the M probability intervals is a continuous range, the value range of the m-th probability interval among the M probability intervals is: Where m = 1, 2, ..., M. In other words, the minimum value in the m-th probability interval is greater than... The maximum value in the m-th probability interval is Alternatively, the range of values ​​for the m-th probability interval among the M probability intervals is: Where m = 1, 2, ..., M. In other words, the minimum value in the m-th probability interval is... The maximum value in the m-th probability interval is less than

[0273] For example, if each of the M probability intervals is a discrete value interval, the value included in the m-th probability interval of the M probability intervals is determined according to M, or the value included in each probability interval is pre-configured.

[0274] For example, suppose M is 11, and the 11 probability intervals include the following values: 0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.

[0275] 920, determine the second best reference signal resource and the third best reference signal resource in each of at least one third reference signal resource set.

[0276] In this context, the measured value of the channel state information corresponding to the second best reference signal resource in each third reference signal resource set is the maximum value among the measured values ​​of the channel state information corresponding to each reference signal resource in each third reference signal resource set. The probability corresponding to the third best reference signal resource in each third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model. This first AI model is described in Figures 5 to 8.

[0277] It should be understood that the probability corresponding to a reference signal resource is the probability that the reference signal resource is the best reference signal resource in the set of reference signal resources to which it belongs. The meaning of "the probability corresponding to the best reference signal resource is the maximum value among the probabilities corresponding to each reference signal resource in the set to which the best reference signal resource belongs" is similar to the meaning of "the probability corresponding to the best reference signal resource is greater than the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs," and "the probability corresponding to the best reference signal resource is greater than or equal to the probabilities corresponding to other reference signal resources in the set to which the best reference signal resource belongs," and they can be used interchangeably. The meaning of "the measured value of the channel state information corresponding to the best reference signal resource is the maximum value of the channel state information corresponding to each reference signal resource in the reference signal resource set to which the best reference signal resource belongs" is similar to the meaning of "the measured value of the channel state information corresponding to the best reference signal resource is greater than the measured value of the channel state information corresponding to the other reference signal resources in the reference signal resource set to which the best reference signal resource belongs" and "the measured value of the channel state information corresponding to the best reference signal resource is greater than or equal to the measured value of the channel state information corresponding to the other reference signal resources in the reference signal resource set to which the best reference signal resource belongs". They can be used interchangeably.

[0278] Optionally, the terminal device performs measurements based on each of the N third reference signal resource sets to determine the measured value of the channel state information corresponding to each reference signal resource in each third reference signal resource set. N is a positive integer. Based on the measured value of the channel state information corresponding to each reference signal resource in each third reference signal resource set, the terminal device determines a second optimal reference signal resource in each third reference signal resource set. That is, the terminal device determines N second optimal reference signal resources, which correspond to the N third reference signal resource sets. Each third reference signal resource set includes at least one reference signal resource. At least two of the N third reference signal resource sets are different. The two reference signal resource sets being different includes: the two reference signal resource sets containing at least one different reference signal resource.

[0279] In some embodiments, prior to step 920, the network device configures at least one third reference signal resource set for the terminal device.

[0280] Optionally, the terminal device determines the third best reference signal resource and the probability corresponding to the third best reference signal resource in each set of third reference signal resources based on at least one sixth reference signal resource and the first AI model.

[0281] In some embodiments, the terminal device performs measurements based on each of the N sixth reference signal resource sets to determine the measured value of the channel state information corresponding to each reference signal resource in each sixth reference signal resource set. The relationship between the N sixth reference signal resource sets and the N third reference signal resource sets is described in step 702.

[0282] For example, prior to step 920, the network device configures at least one sixth reference signal resource set for the terminal device.

[0283] In some embodiments, the terminal device uses the measured value of the channel state information corresponding to each reference signal resource in the nth sixth reference signal resource set out of N sixth reference signal resource sets as input to a first AI model to obtain the output of the first AI model. The output of the first AI model includes the probability corresponding to the third best reference signal resource in the nth sixth reference signal resource set out of the N sixth reference signal resource sets. That is, the terminal device determines N third best reference signal resources and the probability of each third best reference signal resource, where the N third best reference signal resources correspond to N sets of third reference signal resources.

[0284] 930. Based on M probability intervals and the second and third best reference signal resources in each third reference signal resource set, determine the first correspondence.

[0285] The terminal device determines the probability interval to which the probability corresponding to each of the N third-best reference signal resources belongs. In other words, the terminal device determines the third-best reference signal resources included in each of the M probability intervals.

[0286] When each of the M probability intervals is a continuous value interval, the terminal device directly determines the probability interval to which the probability corresponding to each third best reference signal resource belongs based on the probability corresponding to each third best reference signal resource.

[0287] When each of the M probability intervals is a discrete value interval, the terminal device processes the probability corresponding to each third optimal reference signal resource by retaining p decimal places, thereby determining the probability interval to which the probability corresponding to each third optimal reference signal resource belongs. A discrete value included in the probability interval to which the probability corresponding to the third optimal reference signal resource belongs is equal to the value of the probability corresponding to the third optimal reference signal resource after retaining p decimal places. Each of the M probability intervals includes at least one discrete value. p is a positive integer. The value of p is determined based on the number of decimal places of the discrete value included in each probability interval. For example, if the discrete value included in each probability interval has 1 decimal place, then p = 1; if the discrete value included in each probability interval has 2 decimal places, then p = 2; and so on.

[0288] For example, the process of retaining p decimal places includes: direct truncation, rounding, and up-rounding. Direct truncation includes directly retaining the first p decimal places of the probability corresponding to the third best reference signal resource. Rounding includes retaining the first p decimal places of the probability corresponding to the third best reference signal resource when the value at the (p+1)th decimal place is less than or equal to 4; and retaining the first p decimal places of the probability corresponding to the third best reference signal resource when the value at the (p+1)th decimal place is greater than 4, and incrementing the value at the pth decimal place by 1. The upward retention process includes: when the probability corresponding to the third best reference signal resource includes at least p+1 decimal places (i.e., the value of at least one decimal place after the pth decimal place is not 0), retaining the first p decimal places of the probability corresponding to the third best reference signal resource, and incrementing the value of the pth decimal place by 1; when the probability corresponding to the third best reference signal resource includes at most p decimal places (i.e., the value of the decimal places after the pth decimal place is 0), retaining the first p decimal places of the probability corresponding to the third best reference signal resource.

[0289] For example, assuming p = 1 and the probability corresponding to the third best reference signal resource is 0.13, the value obtained by directly discarding the probability of the third best reference signal resource to retain p decimal places is 0.1, the value obtained by rounding the probability of the third best reference signal resource to retain p decimal places is 0.1, and the value obtained by rounding the probability of the third best reference signal resource to retain p decimal places upwards is 0.2. Similarly, assuming p = 1 and the probability corresponding to the third best reference signal resource is 0.16, the value obtained by directly discarding the probability of the third best reference signal resource to retain p decimal places is 0.1, the value obtained by rounding the probability of the third best reference signal resource to retain p decimal places is 0.2, and the value obtained by rounding the probability of the third best reference signal resource to retain p decimal places upwards is 0.2.

[0290] The terminal device determines the accuracy for each probability interval based on the number of third-best reference signal resources included in each of the M probability intervals, the identification information of each third-best reference signal resource included in each probability interval, and the identification information of the second-best reference signal resource corresponding to each third-best reference signal resource included in each probability interval. Each third-best reference signal resource and its corresponding second-best reference signal resource belong to the same set of third reference signal resources.

[0291] In some embodiments, the accuracy A corresponding to the m-th probability interval among the M probability intervals is... m Satisfy the following formula:

[0292] in, This represents the identification information of the i-th third-best reference signal resource in the m-th probability interval. Indicates and The identification information of the corresponding second best reference signal resource. m This represents the number of third-optimal reference signal resources included in the m-th probability interval, i = 0, 1, ..., I. m I m It is a natural number. Equation (2) above means: In and When they are the same, The value is 1. and At the same time, The value is 0. Equation (1) above represents the accuracy A corresponding to the m-th probability interval. m For I m indivual The sum of and I m The ratio. The I m indivual The sum represents the number of third-best reference signal resources that are identical to the corresponding second-best reference signal resource in the m-th probability interval.

[0293] After determining M probability intervals and the accuracy corresponding to each probability interval, the terminal device determines the first correspondence. This first correspondence is the relationship between each probability interval and its corresponding accuracy. The embodiments of this application do not limit the form in which the first correspondence is represented; for example, it can be represented as an array, matrix, function, list, etc.

[0294] In some embodiments, the terminal device sending the first correspondence to the network device may include: the terminal device sending M probability intervals and the accuracy rate corresponding to each probability interval. Alternatively, the terminal device sending the accuracy rate corresponding to each probability interval, i.e., the terminal device sending M accuracy rates. The network device determines the M probability intervals based on the first value M, and determines the first correspondence based on the accuracy rate corresponding to each probability interval.

[0295] In some embodiments, sending a first correspondence between a terminal device and a network device may include: the terminal device sending L probability intervals and the accuracy corresponding to each of the L probability intervals. L is a positive integer, and L is less than M. The accuracy corresponding to each of the L probability intervals is greater than or equal to the accuracy corresponding to the other probability intervals among the M probability intervals excluding the L probability intervals.

[0296] In some embodiments, the accuracy corresponding to each of the L probability intervals is greater than or equal to a first accuracy threshold. The specific value of this first accuracy threshold is not limited in this application embodiment. In other words, the terminal device determines the L probability intervals based on the accuracy corresponding to the M probability intervals and the first accuracy threshold, and sends the L probability intervals and the accuracy corresponding to each probability interval to the network device.

[0297] In some embodiments, the first accuracy threshold is indicated by a network device. That is, the network device sends a tenth indication message to the terminal device, the tenth indication message being used to indicate the first accuracy threshold. Alternatively, the first accuracy threshold is pre-configured.

[0298] In this embodiment, the terminal device determines the accuracy corresponding to M probability intervals based on the best reference signal resources determined by measurement and the best reference signal resources determined by prediction from the third set of reference signal resources, thereby determining the first correspondence. The accuracy of the first AI model determined based on this first correspondence is relatively high. Furthermore, in this method, the network device does not need to configure a large number of reference signal resources for the terminal device each time to determine the accuracy of the first AI model, but only needs to collect the corresponding data when determining the first correspondence, so that the accuracy of the first AI model can be directly determined based on the first correspondence in subsequent steps, thus reducing resource waste.

[0299] Figures 10 and 11 are schematic diagrams of possible communication devices provided in embodiments of this application. These communication devices can be used to implement the functions of terminal devices or network devices in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be the network device 110 shown in Figure 1, or the terminal device 120 or terminal device 130 shown in Figure 1. Alternatively, the communication device can be the terminal device or network device shown in Figures 2 to 9.

[0300] As shown in Figure 10, the communication device 1000 includes a processing unit 1010 and a transceiver unit 1020. The communication device 1000 is used to implement the functions of the network device in the method embodiments shown in Figures 5 to 9 above.

[0301] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG5: the processing unit 1010 is used to determine the first accuracy of the first AI model. The processing unit 1010 is used to execute step 510 in FIG5. The transceiver unit 1020 is used to send first indication information to the network device. The transceiver unit 1020 is used to execute step 520 in FIG5. The first AI model, the first accuracy, and the first indication information are similar to those in FIG5, and will not be described again here.

[0302] When the communication device 1000 is used to implement the function of the network device in the method embodiment shown in FIG5: the transceiver unit 1020 is used to receive the first instruction information.

[0303] When the communication device 1000 is used to implement the functions of the network device in the method embodiment shown in FIG6: the processing unit 1010 is used to determine the first accuracy of the first AI model. The processing unit 1010 is used to execute step 610 in FIG6. The transceiver unit 1020 is used to send the first configuration information to the terminal device. The transceiver unit 1020 is used to execute step 620 in FIG6. The first AI model, the first accuracy, and the first configuration information are similar to those in FIG6, and will not be described again here.

[0304] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG6: the transceiver unit 1020 is used to receive the first configuration information.

[0305] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG7: the processing unit 1010 is used to determine the first correspondence relationship, and the processing unit 1010 is used to execute step 703 in FIG7. The transceiver unit 1020 is used to send the fourth indication information to the network device. The transceiver unit 1020 is used to execute step 704 in FIG7. The first correspondence relationship and the fourth indication information are similar to the first correspondence relationship and the fourth indication information in FIG7, and will not be described again here.

[0306] In some embodiments, when the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG7: the processing unit 1010 is further used to execute steps 706 and 710 in FIG7. The transceiver unit 1020 is further used to execute steps 707 and 711 in FIG7.

[0307] When the communication device 1000 is used to implement the functions of the network device in the method embodiment shown in FIG7: the processing unit 1010 is used to determine the first accuracy of the first AI model. The processing unit 1010 is used to execute step 708 in FIG7. The transceiver unit 1020 is used to send the first configuration information to the terminal device. The transceiver unit 1020 is used to execute step 709 in FIG7. The first AI model, the first accuracy, and the first configuration information are similar to those in FIG7, and will not be described again here.

[0308] In some embodiments, when the communication device 1000 is used to implement the functions of the network device in the method embodiment shown in FIG7: the processing unit 1010 is further used to execute step 712 in FIG7. The transceiver unit 1020 is further used to execute steps 701, 702, 705, and 713 in FIG7.

[0309] When the communication device 1000 is used to implement the functions of the terminal device in the method embodiment shown in FIG8: the processing unit 1010 is used to execute steps 804, 806, 807, and 810 in FIG8. The transceiver unit 1020 is used to execute steps 808 and 811 in FIG8.

[0310] When the communication device 1000 is used to implement the functions of the network device in the method embodiment shown in FIG8: the processing unit 1010 is used to execute step 812 in FIG8. The transceiver unit 1020 is used to execute steps 801-803, 805, 809, and 813 in FIG8.

[0311] When the communication device 1000 is used to implement the function of the terminal device in the method embodiment shown in FIG9: the processing unit 1010 is used to execute steps 910-930 in FIG9.

[0312] For a more detailed description of the processing unit 1010 and the transceiver unit 1020, please refer to the relevant descriptions in the method embodiments shown in Figures 5 to 9.

[0313] As shown in Figure 11, the communication device 1100 includes a processing circuit 1110. Further, the communication device 1100 may also include the processing circuit 1110 and a communication circuit 1120. The processing circuit 1110 and the communication circuit 1120 are coupled to each other. The processing circuit may be one or more processors, or all or part of the circuitry within one or more processors used for control or processing functions. It is understood that when the communication device 1100 is a network device or a terminal device, the communication circuit 1120 may be a transceiver circuit, a transceiver, or an input / output interface. When the communication device 1100 is a chip for a network device or a terminal device, the communication circuit 1120 may be an input / output interface or an input / output circuit. Optionally, the communication device 1100 may also include a memory 1130 for storing instructions executed by the processor 1110, or storing input data required by the processor 1110 to execute instructions, or storing data generated after the processor 1110 executes instructions.

[0314] When the communication device 1100 is used to implement the method shown in Figures 5 to 9, the processing circuit 1110 is used to implement the function of the processing unit, and the communication circuit 1120 is used to implement the function of the transceiver unit.

[0315] When the aforementioned communication device is a chip applied to a terminal, the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receives information from other modules (such as radio frequency modules or antennas) in the terminal, which is information sent to the terminal by the base station; or, the terminal chip sends information to other modules (such as radio frequency modules or antennas) in the terminal, which is information sent to the base station by the terminal.

[0316] When the aforementioned communication device is a module applied to a base station (or network equipment), the base station module implements the functions of the base station in the above method embodiments. The base station module receives information from other modules (such as radio frequency modules or antennas) in the base station, information sent by the terminal to the base station; or, the base station module sends information to other modules (such as radio frequency modules or antennas) in the base station, information sent by the base station to the terminal. Here, the base station module can be the baseband chip of the base station, or a DU (Digital Unit) or other modules. The DU can be a DU under an Open Radio Access Network (O-RAN) architecture.

[0317] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), graphics processing units, neural processing units, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0318] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, compact disc read-only memory (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. The processor and storage medium can also exist as discrete components in the base station or terminal.

[0319] This application also provides a communication system, which includes the network device and terminal device described in the embodiments of this application.

[0320] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions or program code that, when executed on a computing device, cause the computing device to perform the methods provided above.

[0321] This application also provides a computer program product, which may be a software or program product containing instructions capable of running on a computing device or stored on any usable medium. When the instructions are executed on the computing device, the computing device performs the methods provided above, or performs the functions of the apparatus provided above.

[0322] This application also provides a chip including at least one processor, which, when program instructions are executed by the at least one processor, causes the at least one processor to perform the methods provided above.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] 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.

[0327] 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.

[0328] 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 contributing part, 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.

[0329] 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 by comprising: The method comprises the following steps: determining a first accuracy of a first artificial intelligence (AI) model, the first accuracy being used to represent an accuracy of a probability corresponding to a first best reference signal resource in a first reference signal resource set determined by the first AI model, the first AI model being used to determine a probability that each reference signal resource in the first reference signal resource set is a best reference signal resource in the first reference signal resource set, the probability corresponding to the first best reference signal resource being a maximum value among probabilities corresponding to each reference signal resource in the first reference signal resource set, the first reference signal resource set comprising at least one reference signal resource; sending first indication information, the first indication information being used to indicate the first accuracy, or the first indication information being used to request configuration of a second reference signal resource set, the second reference signal resource set comprising at least one reference signal resource.

2. The method of claim 1, wherein, The method further comprises the following steps: determining the probability corresponding to the first best reference signal resource according to the first AI model; determining the first accuracy according to a first correspondence relationship and the probability corresponding to the first best reference signal resource, the first correspondence relationship being used to indicate a correspondence relationship between a probability interval to which a probability determined by the first AI model belongs and an accuracy of the first AI model.

3. The method according to claim 1 or 2, characterized in that, The method further comprises the following steps: determining M probability intervals according to a first numerical value M, a minimum value in the M probability intervals being greater than or equal to 0, a maximum value in the M probability intervals being less than or equal to 1, M being an integer greater than 1; determining a second best reference signal resource and a third best reference signal resource in each third reference signal resource set of at least one third reference signal resource set, the second best reference signal resource in each third reference signal resource set corresponding to a maximum value among measurement values of channel state information corresponding to each reference signal resource in the third reference signal resource set, the third best reference signal resource in each third reference signal resource set corresponding to a maximum value among probabilities corresponding to each reference signal resource in the third reference signal resource set determined by the first AI model; determining the first correspondence relationship according to the M probability intervals, the second best reference signal resource and the third best reference signal resource in each third reference signal resource set.

4. The method of claim 3, wherein, The method further comprises the following steps: determining a probability interval to which the probability corresponding to the third best reference signal resource in each third reference signal resource set belongs. According to the number of third best reference signal resources included in each probability interval in the M probability intervals, identification information of each third best reference signal resource included in each probability interval, and identification information of a second best reference signal resource corresponding to each third best reference signal resource included in each probability interval, an accuracy corresponding to each probability interval is determined, and each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belong to a same third reference signal resource set.

5. The method according to claim 3 or 4, characterized in that, The method further includes: receiving second indication information, the second indication information being used to indicate the first number M, or the second indication information being used to indicate a first determination manner and the first number M; wherein the first number M is a number of probability intervals included in the first correspondence relationship, and the first determination manner is a manner of determining the first correspondence relationship.

6. The method according to any one of claims 1 to 5, characterized in that, In a case where the first indication information is used to indicate the first accuracy, the first indication information is further used to indicate identification information of the first best reference signal resource.

7. The method according to any one of claims 1 to 5, characterized in that, In a case where the first indication information is used to request configuration of a second reference signal resource set, the sending of the first indication information includes: in a case where the first accuracy is less than or equal to a first preset threshold, sending the first indication information; The method further includes: in a case where the first accuracy is greater than a first preset threshold, sending third indication information, the third indication information being used to indicate identification information of the first best reference signal resource.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: determining a second accuracy according to at least one accuracy of the first AI model, the at least one accuracy including the first accuracy; in a case where the second accuracy is less than or equal to a second preset threshold, calibrating the first AI model.

9. A communication method characterized by comprising: including: determining a first accuracy of a first AI model, the first accuracy being used to represent an accuracy of a probability corresponding to a first best reference signal resource in a first reference signal resource set determined by the first AI model, the first AI model being used to determine a probability that each reference signal resource in the first reference signal resource set is a best reference signal resource in the first reference signal resource set, the probability corresponding to the first best reference signal resource being a maximum value in probabilities corresponding to each reference signal resource in the first reference signal resource set, and the first reference signal resource set including at least one reference signal resource; sending first configuration information, the first configuration information being used to configure a second reference signal resource set, and the second reference signal resource set including at least one reference signal resource.

10. The method of claim 9, wherein, The determining of the first accuracy of the first AI model includes: determining the first accuracy according to a first correspondence relationship and the probability corresponding to the first best reference signal resource, the first correspondence relationship being used to indicate a correspondence relationship between a probability interval to which a probability determined by the first AI model belongs and an accuracy of the first AI model.

11. The method of claim 10, wherein, The method further includes: receive fourth indication information, the fourth indication information being used to indicate the first correspondence relationship; and / or, receive fifth indication information, the fifth indication information being used to indicate a probability corresponding to the first best reference signal resource.

12. The method according to claim 10 or 11, characterized in that, The first correspondence relationship is determined based on M probability intervals, a second best reference signal resource in each of at least one third reference signal resource set, and a third best reference signal resource in each of the at least one third reference signal resource set. The minimum value in the M probability intervals is greater than or equal to 0, the maximum value in the M probability intervals is less than or equal to 1, M is an integer greater than 1, the measurement value of the channel state information corresponding to the second best reference signal resource in each of the third reference signal resource set is the maximum value among the measurement values of the channel state information corresponding to each reference signal resource in each of the third reference signal resource set, and the probability corresponding to the third best reference signal resource in each of the third reference signal resource set is the maximum value among the probabilities corresponding to each reference signal resource in each of the third reference signal resource set determined by the first AI model.

13. The method of claim 12, wherein, The accuracy rate corresponding to each probability interval is determined based on the number of third best reference signal resources included in each of the M probability intervals, the identification information of each third best reference signal resource included in each of the M probability intervals, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in each of the M probability intervals. The probability corresponding to the third best reference signal resource in each of the third reference signal resource set belongs to one of the M probability intervals, and the third best reference signal resource and the second best reference signal resource corresponding to the third best reference signal resource belong to the same third reference signal resource set.

14. The method of claim 9, wherein, The method further includes: receiving sixth indication information, the sixth indication information being used to indicate the first accuracy rate.

15. The method according to any one of claims 9 to 14, characterized in that, The method further includes: sending second indication information, the second indication information being used to indicate a first number M or the second indication information being used to indicate a first determination manner and the first number M; The first number M is the number of probability intervals included in the first correspondence relationship, the first determination manner is a manner of determining the first correspondence relationship, the first correspondence relationship is used to indicate a correspondence relationship between a probability interval to which a probability determined by the first AI model belongs and an accuracy rate of the first AI model, and M is an integer greater than 1.

16. The method according to any one of claims 9 to 15, characterized in that, The sending of the first configuration information includes: in a case where the first accuracy rate is less than or equal to a first preset threshold, sending the first configuration information; The method further includes: in a case where the first accuracy rate is greater than the first preset threshold, transmitting data through the first best reference signal resource.

17. The method according to any one of claims 9 to 16, characterized in that, The method further includes: determining a second accuracy rate according to at least one accuracy rate of the first AI model, the at least one accuracy rate including the first accuracy rate; In a case where the second accuracy is less than or equal to a second preset threshold, seventh indication information is sent, the seventh indication information being used to indicate that the first AI model is calibrated.

18. A method of communication, comprising: Comprise: A first correspondence relationship is determined, the first correspondence relationship being used to indicate a correspondence relationship between a probability interval to which a probability corresponding to a best reference signal resource determined by a first AI model belongs and an accuracy of the first AI model, the first AI model being used to determine a probability that each reference signal resource in a fourth reference signal resource set is a best reference signal resource in the fourth reference signal resource set, the accuracy of the first AI model being used to represent an accuracy of the probability determined by the first AI model, the fourth reference signal resource set comprising at least one reference signal resource; Fourth indication information is sent, the fourth indication information being used to indicate the first correspondence relationship.

19. The method of claim 18, wherein, The determination of the first correspondence relationship comprises: According to a first numerical value M, M probability intervals are determined, a minimum value in the M probability intervals being greater than or equal to 0, a maximum value in the M probability intervals being less than or equal to 1, M being an integer greater than 1; Second best reference signal resources and third best reference signal resources in each third reference signal resource set in at least one third reference signal resource set are determined, a measurement value of channel state information corresponding to the second best reference signal resource in each third reference signal resource set being a maximum value in measurement values of channel state information corresponding to each reference signal resource in the third reference signal resource set, a probability corresponding to the third best reference signal resource in each third reference signal resource set being a maximum value in probabilities corresponding to each reference signal resource in the third reference signal resource set determined by the first AI model; The first correspondence relationship is determined according to the M probability intervals, the second best reference signal resources and the third best reference signal resources in each third reference signal resource set.

20. The method of claim 19, wherein, The determination of the first correspondence relationship according to the M probability intervals, the second best reference signal resources and the third best reference signal resources in each third reference signal resource set comprises: A probability interval to which a probability corresponding to the third best reference signal resource belongs is determined; According to a number of third best reference signal resources included in each probability interval in the M probability intervals, identification information of each third best reference signal resource included in each probability interval, and identification information of a second best reference signal resource corresponding to each third best reference signal resource included in each probability interval, an accuracy corresponding to each probability interval is determined, each third best reference signal resource and the second best reference signal resource corresponding to each third best reference signal resource belonging to a same third reference signal resource set.

21. The method according to claim 19 or 20, characterized in that, The method further comprises: Second indication information is received, the second indication information being used to indicate the first numerical value M, or the second indication information being used to indicate a first determination manner and the first numerical value M; The first number of values M is the number of probability intervals included in the first correspondence relationship, and the first determination manner is a manner of determining the first correspondence relationship.

22. The method of any one of claims 18-21, wherein, The method further includes: According to the first AI model, determining a probability corresponding to a first best reference signal resource in a first reference signal resource set, the probability corresponding to the first best reference signal resource being a maximum value among probabilities corresponding to each reference signal resource in the first reference signal resource set, the first reference signal resource set including at least one reference signal resource; Sending fifth indication information, the fifth indication information being used for indicating the probability corresponding to the first best reference signal resource.

23. A method of communication, comprising: Including: Receiving fourth indication information, the fourth indication information being used for indicating a first correspondence relationship, the first correspondence relationship being used for indicating a correspondence relationship between a probability interval to which a probability corresponding to a best reference signal resource determined by a first AI model belongs and an accuracy rate of the first AI model, the first AI model being used for determining a probability that each reference signal resource in a fourth reference signal resource set is a best reference signal resource in the fourth reference signal resource set, the accuracy rate of the first AI model being used for characterizing an accuracy rate of the probability determined by the first AI model, the fourth reference signal resource set including at least one reference signal resource.

24. The method of claim 23, wherein, The first correspondence relationship is determined based on M probability intervals, a second best reference signal resource and a third best reference signal resource in each third reference signal resource set of at least one third reference signal resource set; Wherein, the minimum value in the M probability intervals is greater than or equal to 0, the maximum value in the M probability intervals is less than or equal to 1, M is an integer greater than 1, the measurement value of the channel state information corresponding to the second best reference signal resource in each third reference signal resource set is the maximum value among measurement values of channel state information corresponding to each reference signal resource in each third reference signal resource set, and the probability corresponding to the third best reference signal resource in each third reference signal resource set is the maximum value among probabilities corresponding to each reference signal resource in each third reference signal resource set determined by the first AI model.

25. The method of claim 24, wherein, The accuracy rate corresponding to each probability interval is determined based on the number of third best reference signal resources included in each probability interval of the M probability intervals, the identification information of each third best reference signal resource included in the each probability interval, and the identification information of the second best reference signal resource corresponding to each third best reference signal resource included in the each probability interval; Wherein, the probability corresponding to the third best reference signal resource in each third reference signal resource set belongs to one of the M probability intervals, and the third best reference signal resource and the second best reference signal resource corresponding to the third best reference signal resource belong to the same third reference signal resource set.

26. The method of any one of claims 23-25, wherein, The method further includes: The second indication information is used for indicating the first value M, or the second indication information is used for indicating the first determination manner and the first value M. The first value M is a number of probability intervals included in the first correspondence relationship, and the first determination manner is a manner of determining the first correspondence relationship.

27. The method of any one of claims 23-26, wherein, The method further includes: receiving fifth indication information, the fifth indication information being used for indicating a probability corresponding to the first best reference signal resource, the probability corresponding to the first best reference signal resource being a maximum value in probabilities corresponding to each reference signal resource in a first reference signal resource set determined by the first AI model, the first reference signal resource set including at least one reference signal resource.

28. The method of claim 27, wherein, The method further includes: determining a first accuracy rate of the first AI model according to the first correspondence relationship and the probability corresponding to the first best reference signal resource, the first accuracy rate being used for representing an accuracy rate of the probability corresponding to the first best reference signal resource determined by the first AI model.

29. A communications device, characterized by A module for performing the method of any one of claims 1-8 or any one of claims 18-22.

30. A communications device, characterized by A module for performing the method of any one of claims 9-17 or any one of claims 23-28.

31. A communications device, characterized by The communication device includes at least one processor and a communication interface for information interaction between the communication device and other communication devices, and when program instructions are executed in the at least one processor, the communication device performs the method of any one of claims 1-8 or any one of claims 18-22.

32. A communications device, characterized by The communication device includes at least one processor and a communication interface for information interaction between the communication device and other communication devices, and when program instructions are executed in the at least one processor, the communication device performs the method of any one of claims 9-17 or any one of claims 23-28.

33. A communication system, characterized by The communication system includes the communication device of claim 31 and the communication device of claim 32.

34. A computer-readable storage medium, characterized in that, The computer readable medium stores program code for execution by a device, and when the program code is executed, the method of any one of claims 1-8 or any one of claims 18-22 is performed.

35. A computer readable storage medium, characterized in that, The computer readable medium stores program code for execution by a device, and when the program code is executed, the method of any one of claims 9-17 or any one of claims 23-28 is performed.

36. A computer program product, characterised in that, The computer program product includes program instructions, and when the program instructions are executed, the method of any one of claims 1-8 or any one of claims 18-22 is performed.

37. A computer program product, characterised in that, The computer program product includes program instructions, and when the program instructions are executed, the method of any one of claims 9-17 or any one of claims 23-28 is performed.

38. A chip, characterized by The chip comprises at least one processor, which, when program instructions are executed in the at least one processor, causes the chip to perform the method as claimed in any one of claims 1 to 8, or as claimed in any one of claims 18 to 22.

39. A chip, characterized by The chip comprises at least one processor, which, when program instructions are executed in the at least one processor, causes the chip to perform the method as claimed in any one of claims 9 to 17, or as claimed in any one of claims 23 to 28.

Images