Communication method and device, communication chip, storage medium and computer program product

Abstract

The invention provides a communication method and device, a communication chip, a storage medium and a computer program product, belongs to the field of communication, and is used for improving the accuracy of a wave beam, used for communicating with a terminal, of access network equipment predicted by an AI model. The method comprises the following steps: when the beam performance of a beam predicted by a terminal by using a beam prediction model is less than or equal to a threshold value, the terminal sends M beams with the beam performance at the first M in N beams obtained by measurement to an access network device, and sends a first position of the M beams to a model management function entity, so that the access network device can carry out beam prediction on the M beams based on the M beams. And sending a second beam, used for communicating with the terminal, of the access network equipment to a model management functional entity, so that the model management functional entity can update the beam prediction model based on the first position and the identification information of the second beam. In this way, the accuracy of the transmission beam, predicted by the updated beam prediction model, of the access network equipment for communicating with the terminal can be improved.

Description

Technical Field

[0001] The present application relates to the field of communications, and specifically to a communication method, device, communication chip, storage medium, and computer program product. Background Art

[0002] Beam management (BM) is a technology used in the new radio (NR) of fifth-generation (5G) mobile communications technology to dynamically select the direction and frequency of communication beams based on channel quality. It aims to optimize signal transmission and communication quality by precisely controlling the direction and strength of signal transmission. The beam management process primarily includes the following six steps: beam selection, beam measurement, beam reporting, beam switching, beam indication, and beam recovery. During the beam measurement and beam reporting processes, a terminal determines the transmit beam that an access network device will use to communicate with the terminal based on the measurement results of multiple beams corresponding to the access network device, and then sends the transmit beam to the access network device.

[0003] Currently, artificial intelligence (AI) technology has been introduced in beam management. For example, in AI-based spatial beam prediction methods, the AI model can learn the transmission characteristics of different beams in the current environment and, based on the terminal's environment, predict the probability that each transmit beam used by the access network device will be the optimal transmit beam for communicating with the terminal. For another example, in AI-based time-domain prediction methods, the AI model can analyze the terminal's beam measurement results at historical moments to predict the terminal's optimal beam at future moments, allowing the terminal to adjust its beam direction based on this information. In other words, during the beam measurement process, the AI model can predict the transmit beam that the access network device will use to communicate with the terminal. However, this approach may result in the predicted transmit beam not being the optimal one, thereby reducing the communication quality between the terminal and the access network device. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a communication method, device, communication chip, storage medium and computer program product to improve the accuracy of the beam predicted by the AI model for the access network device to communicate with the terminal.

[0005] The embodiment of the present application is implemented as follows: In a first aspect, embodiments of the present application provide a communication method. This method can be executed by a terminal, or by a component of the terminal, such as a processor, chip, chip system, or circuit, or by a logic module or software that implements all or part of the terminal's functions. The following description uses the method executed by a terminal as an example. The method includes: obtaining the beam performance of a first beam, and when the beam performance of the first beam is less than or equal to a threshold, sending a first beam indication message to an access network device, and sending a first position indication message to a model management function entity; wherein the first beam is a beam used by the access network device to communicate with the terminal, as predicted by a beam prediction model based on a first position of the terminal, the first beam indication message is used to indicate information of M beams measured by the terminal, the M beams being beams with beam performance in the top M of the N beams measured, the N beams being all beams used by the access network device for communication, the first position indication message is used to indicate the above-mentioned first position, the model management function entity is used to update the beam prediction model based on the first position and identification information of the second beam, the second beam being a beam actually used for communication between the access network device and the terminal among the M beams, N being a positive integer, and M being a positive integer less than or equal to N.

[0006] Based on the method of the first aspect, a terminal can input its first location into a beam prediction model to obtain the beam predicted by the beam prediction model for the access network device to use for communication with the terminal. This means that the terminal does not need to measure all beams used by the access network device for communication and determine the beam used by the access network device for communication with the terminal based on the measurement results. This allows the terminal to more quickly obtain the beam used by the access network device for communication with the terminal. Furthermore, compared to models that predict beams based on other information (such as the terminal's environment or historical beam measurement results), the model that predicts beams based on terminal location has higher prediction accuracy due to the strong correlation between location and beam pointing. Furthermore, the solution is simpler to implement, allowing the terminal to more promptly obtain the beam used by the access network device for communication with the terminal. For example, in traffic scenarios (such as autonomous driving), the rapid movement of vehicles requires that beam selection must be completed in an extremely short time. Inputting the terminal's location into the beam prediction model allows the vehicle to more quickly and promptly obtain the beam used by the access network device for communication with the terminal. Furthermore, in order to improve the accuracy of the prediction of the beam prediction model, the terminal can compare the beam performance of the beam predicted by the beam prediction model with the threshold when using the beam prediction model, and when the beam performance is less than or equal to the threshold, that is, when the beam may have an inaccurate prediction problem, send the M beams with beam performance in the top M of the N beams measured to the access network device, and send their first position to the model management functional entity, so that the access network device can send the second beam used by the access network device to the model management functional entity based on the M beams, so that the model management functional entity can update the beam prediction model based on the first position and the identification information of the second beam, such as associating the first position and the identification information of the second beam as a sample to update the beam prediction model. In this way, when the prediction result obtained by the terminal using the beam prediction model is inaccurate, a more accurate beam can be obtained for communication between the access network device and the terminal by actually measuring the beam, and the model management functional entity can update the beam prediction model based on the more accurate beam and the first position of the terminal, thereby improving the accuracy of the transmission beam predicted by the updated beam prediction model for the access network device to communicate with the terminal. In addition, in traffic scenarios (such as autonomous driving scenarios), this method can enable the model management functional entity to continuously collect samples for updating the beam prediction model. This dynamic update mechanism can ensure that the beam prediction model can adapt to environmental changes, so that the beam prediction model can maintain a high level of prediction accuracy. For example: in an urban environment, building obstruction and multipath effects may cause large fluctuations in signal strength. By dynamically updating the beam prediction model, the beam selection can be adjusted in real time to ensure the stability and efficiency of communication.

[0007] In one possible implementation, before sending the first beam indication message to the access network device, the method described in the first aspect also includes: sending a configuration information request message to the access network device, the configuration information request message being used to request the access network device to send information for measuring all beams used by the access network device for communication; receiving a configuration information response message from the access network device, the configuration information response message being used to indicate information for measuring N beams; and based on the configuration information response message, measuring N beams and determining M beams. That is, during the application phase of the beam prediction model, the access network device does not need to periodically broadcast information for measuring N beams, but instead the terminal requests information for measuring N beams on demand. In this way, the power consumption of the access network device can be reduced.

[0008] In one possible implementation, before obtaining the beam performance of the first beam, the method according to the first aspect further includes: receiving model activation information from an access network device, and obtaining the first beam by inputting the first position into a beam prediction model based on the model activation information, wherein the model activation information instructs the terminal to activate the beam prediction model. In this way, switching between obtaining the beam through beam measurement and obtaining the beam through the beam prediction model can be achieved through the model activation message.

[0009] In one possible implementation, the model activation information is carried in a system information block (SIB) message. That is, the model activation information can be reused in an existing message. This improves resource utilization and reduces transmission delay.

[0010] In one possible implementation, the model activation information is indicated by a first value of a first preset reserved bit in a SIB message, where the first preset reserved bit is any one of multiple reserved bits in the SIB message. In this way, the existing structure of the SIB message can be used to transmit the model activation information, thereby reducing the difficulty of transmitting the model activation information via the SIB message.

[0011] In one possible implementation, the beam prediction model is obtained from a model management functional entity, which is used to manage the beam prediction models corresponding to different access network devices. That is, all terminals within the coverage of different access network devices can request beam prediction models from the model management functional entity. In this way, it is convenient to uniformly manage multiple beam prediction models corresponding to different access network devices. In addition, the model management functional entity can be used to generate beam prediction models corresponding to different access network devices. In this case, the access network device does not need to generate the corresponding beam prediction model by itself, so that there is no need to equip the access network device with high computing power hardware resources, thereby reducing costs; and the beam prediction model corresponding to the access network device can be generated for the deployed access network device.

[0012] In one possible implementation, after obtaining the beam performance of the first beam, the method of the first aspect further includes: if the beam performance of the first beam is greater than a threshold, sending a second beam indication message to the access network device, where the second beam indication message is used to indicate the first beam. That is, the access network device only uses the beam predicted by the beam prediction model if the beam performance is greater than the threshold. This ensures communication quality between the terminal and the access network device when using the beam predicted by the beam prediction model.

[0013] In one possible implementation, after sending the second beam indication message to the access network device, the method of the first aspect further includes: receiving an updated model activation message from the access network device, the updated model activation message being used to instruct the terminal to activate the updated beam prediction model; in response to the updated model activation message, obtaining a third beam through the updated beam prediction model, the third beam being the output result of inputting the first position into the updated beam prediction model; and sending a third beam indication message to the access network device, the third beam indication message being used to indicate the third beam. In this way, the terminal can use the updated beam prediction model to predict the beam used by the access network device for communicating with the terminal, and send the beam to the access network device, so that the access network device uses the beam to communicate with the terminal, thereby improving the communication quality between the access network device and the terminal.

[0014] In one possible implementation, after sending a first beam indication message to the access network device, or after sending a second beam indication message to the access network device, the method described in the first aspect further includes: receiving an update model activation message from the access network device, and obtaining an updated beam prediction model based on the update model activation message, wherein the update model activation message is used to instruct the terminal to activate the updated beam prediction model. After obtaining the updated beam prediction model, the terminal can use the updated beam prediction model after its position changes and its changed position falls within the network coverage of the access network device. In this way, the accuracy of the beam predicted by the terminal using the beam prediction model can be improved.

[0015] In one possible implementation, before obtaining the beam performance of the first beam, the method described in the first aspect also includes: receiving beam measurement activation information from the access network device, sending a fourth beam indication message to the access network device in response to the beam measurement activation information, and sending location measurement information to the location management function entity; wherein the beam measurement activation information is used to instruct the terminal to send K beams to the access network device based on the measurement results of the N beams, and send information for obtaining the location of the terminal, the K beams being the beams with beam performance in the top K among the measured N beams, the fourth beam indication message being used to indicate the information of the K beams measured by the terminal, the location measurement information being used to indicate the time difference or angle between the signal sent by the access network device and the terminal, the time difference or angle being used to obtain the second location of the terminal, the second location and the identification information of the fourth beam being used to train a candidate beam prediction model, the fourth beam being the beam actually used for communication between the access network device and the terminal among the K beams, the candidate beam prediction model being a beam prediction model that has not yet completed training, and K being a positive integer less than or equal to N. That is, during the training phase of the beam prediction model, the terminal can send K beams obtained through beam measurement to the access network device based on the beam measurement activation information, and send location measurement information to the location management function entity, so that the access network device can select a beam to communicate with the terminal based on the K beams, and send the identification information of the beam to the model management function entity for training the candidate beam prediction model. The location management function entity can also calculate the second location of the terminal based on the location measurement information, and send the second location to the model management function entity for training the candidate beam prediction model. In this way, training samples corresponding to the terminal for training the candidate beam prediction model can be collected.

[0016] In one possible implementation, the beam measurement activation information is carried in a SIB message. That is, the beam measurement activation information can be reused in an existing message. This improves resource utilization and reduces transmission delay.

[0017] In one possible implementation, the beam measurement enabling information is indicated by a second value of a second preset reserved bit in the SIB message. The second preset reserved bit is any one of multiple reserved bits in the SIB message. This allows the beam measurement enabling information to be sent using the existing structure of the SIB message, thereby reducing the difficulty of sending the beam measurement enabling information via the SIB message.

[0018] In a second aspect, embodiments of the present application provide a communication method. This method can be executed by an access network device, or by a component of the access network device, such as a processor, chip, chip system, or circuit of the access network device. It can also be implemented by a logic module or software that implements all or part of the functions of the access network device. The following description uses the method executed by an access network device as an example. The method includes: when the beam performance of the first beam is less than or equal to a threshold, receiving a first beam indication message from the terminal; in response to the first beam indication message, sending an update beam indication message to a model management function entity; wherein the first beam is a beam used by an access network device to communicate with the terminal, as predicted by a beam prediction model based on a first position of the terminal, the first beam indication message is used to indicate information of M beams measured by the terminal, the M beams being beams with beam performance in the top M of the measured N beams, the N beams being all beams used by the access network device for communication, the update beam indication message is used to indicate a second beam, the second beam being a beam actually used for communication between the access network device and the terminal among the M beams, the model management function entity is used to update the beam prediction model based on the second beam, N is a positive integer, and M is a positive integer less than or equal to N.

[0019] Based on the method of the second aspect, it can be known that when the beam performance of the beam predicted by the terminal using the beam prediction model is less than or equal to the threshold, it indicates that the beam may have an inaccurate prediction problem. In this case, the terminal sends the M beams whose beam performance is in the top M among the N beams obtained by measurement to the access network device, so that the access network device determines the second beam for communicating with the terminal based on the M beams, and sends the second beam to the model management function entity, so that the model management function entity updates the beam prediction model based on the second beam. In this way, when the prediction result obtained by the terminal using the beam prediction model is inaccurate, a more accurate beam can be obtained for communication between the access network device and the terminal by actually measuring the beam, and the model management function entity can update the beam prediction model based on the beam, thereby improving the accuracy of the transmission beam predicted by the updated beam prediction model for the access network device to communicate with the terminal.

[0020] In one possible implementation, before receiving the first beam indication information from the terminal, the method described in the second aspect also includes: receiving a configuration information request message from the terminal, the configuration information request message being used to request the access network device to send information for measuring all beams used by the access network device for communication; and in response to the configuration information request message, sending a configuration information response message to the terminal, the configuration information response message being used to indicate information for measuring N beams.

[0021] In one possible implementation, before receiving the first beam indication information from the terminal, the method described in the second aspect also includes: receiving first model status indication information from the model management function entity, the first model status indication information being used to indicate that the beam prediction model has completed training; in response to the first model status indication information, broadcasting model activation information, the model activation information being used to instruct the terminal to activate the beam prediction model.

[0022] In a possible implementation, the model activation information is carried in a SIB message.

[0023] In a possible implementation, the model activation information is indicated by a first value of a first preset reserved bit in the SIB message, where the first preset reserved bit is any one of multiple reserved bits in the SIB message.

[0024] In one possible implementation, before receiving the first beam indication information from the terminal, the method described in the second aspect further includes: receiving second model status indication information from the model management function entity, where the second model status indication information is used to indicate that the beam prediction model has been updated; and in response to the second model status indication information, broadcasting an updated model activation message, where the updated model activation message is used to instruct the terminal to activate the updated beam prediction model. In this way, when the beam prediction model update is complete, the model management function entity can trigger the access network device to instruct terminals within its network coverage area to activate the updated beam prediction model.

[0025] In one possible implementation, before receiving the first beam indication information from the terminal, the method described in the second aspect further includes: receiving third model status indication information from the model management function entity, where the third model status indication information is used to indicate that the beam prediction model has not completed training; and in response to the third model status indication information, broadcasting beam measurement enablement information, where the beam measurement enablement information is used to instruct the terminal to send K beams to the access network device based on the measurement results of the N beams, as well as information for obtaining the location of the terminal, where the K beams are the beams with the top K beam performance among the measured N beams, where K is a positive integer less than or equal to N. In this way, when the beam prediction model has not completed training, the model management function entity can trigger the access network device to instruct terminals within its network coverage area to obtain K beams using beam measurement.

[0026] In one possible implementation, after broadcasting the beam measurement activation information, the method described in the second aspect also includes: receiving a fourth beam indication message from the terminal, the fourth beam indication message being used to indicate information of K beams measured by the terminal; in response to the fourth beam indication message, sending a training beam indication message to the model management function entity, the training beam indication message being used to indicate a fourth beam, the fourth beam being the beam among the K beams actually used for communication between the access network device and the terminal, and the fourth beam being used to train a candidate beam prediction model, the candidate beam prediction model being a beam prediction model that has not completed training.

[0027] In one possible implementation, the beam measurement enabling information is carried in a SIB message.

[0028] In one possible implementation, the beam measurement enabling information is indicated by a second value of a second preset reserved bit in the SIB message, where the second preset reserved bit is any one of multiple reserved bits in the SIB message.

[0029] In addition, the technical effects of the method described in the second aspect can also refer to the technical effects of the method described in the first aspect, and will not be repeated here.

[0030] In a third aspect, an embodiment of the present application provides a communication method, which can be executed by a model management function entity, or by a component of the model management function entity, such as a processor, chip, chip system, or circuit of the model management function entity, or by a logic module or software that can implement all or part of the model management function entity. The following is an example of the method being executed by the model management function entity. The method includes: obtaining the state of a beam prediction model, and sending first model state indication information, second model state indication information, or third model state indication information to an access network device based on the state of the beam prediction model; wherein the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the location of the terminal, the first model state indication information is used to indicate that the beam prediction model has completed training, the second model state indication information is used to indicate that the beam prediction model has completed updating, and the third model state indication information is used to indicate that the beam prediction model has not completed training.

[0031] Based on the method of the third aspect, the model management function entity can trigger the access network device to instruct terminals within its network coverage to obtain the beam the access network device uses to communicate with the terminal, based on the state of the beam prediction model. This enables switching of the beam acquisition method used by the terminal (e.g., obtaining a beam using the beam prediction model or obtaining a beam by measuring the beam) at different stages of the beam prediction model.

[0032] In one possible implementation, after sending the first model status indication information to the access network device, the method described in the third aspect also includes: receiving an updated beam indication message from the access network device, the updated beam indication message including the identification information of the terminal and the identification information of the second beam, the second beam being the beam actually used for communication between the access network device and the terminal among the M beams, the M beams being the beams with beam performance in the top M among the measured N beams, the N beams being all beams used for communication by the access network device, N being a positive integer, and M being a positive integer less than or equal to N; receiving a first position indication message from the terminal, the first position indication message including the first position of the terminal and the identification information of the terminal; obtaining an updated sample based on the updated beam indication message and the first position indication message, the updated sample being used to update the beam prediction model, and the updated sample including the identification information of the first position and the second beam. In this way, the model management function entity can accurately and quickly obtain the updated sample.

[0033] In one possible implementation, after sending the third model status indication information to the access network device, the method described in the third aspect further includes: receiving a training beam indication message from the access network device, the training beam indication message including the identification information of the terminal and the identification information of the fourth beam, the fourth beam being the beam actually used for communication between the access network device and the terminal among the K beams, the K beams being the beams with beam performance in the top K among the measured N beams, the N beams being all beams used for communication by the access network device, N being a positive integer, and K being a positive integer less than or equal to N; receiving a second location indication message from the location management function entity, the second location indication message including the identification information of the terminal and the second location of the terminal; obtaining a training sample based on the training beam indication message and the second location indication message, the training sample including the identification information of the second location and the fourth beam, and the training sample being used to train a candidate beam prediction model, the candidate beam prediction model being a beam prediction model that has not yet completed training. In this way, the model management function entity can accurately and quickly obtain the training sample.

[0034] In a fourth aspect, a communication method is provided, the method comprising: an access network device executing the method described in the second aspect, and a model management function entity executing the method described in the third aspect.

[0035] In a fifth aspect, a communication device is provided. The communication device includes: a module for executing the method described in any one of aspects 1 to 3, such as a transceiver module and a processing module. For example, the transceiver module is configured to indicate the transceiver function of the communication device, and the processing module is configured to perform functions of the communication device other than the transceiver function.

[0036] Optionally, the transceiver module may include a sending module and a receiving module, wherein the sending module is used to implement the sending function of the communication device described in the fifth aspect, and the receiving module is used to implement the receiving function of the communication device described in the fifth aspect.

[0037] Optionally, the communication device described in the fifth aspect may further include a storage module, wherein the storage module stores a program or instruction. When the processing module executes the program or instruction, the communication device can execute the method described in any one of the first to third aspects.

[0038] It can be understood that the communication device described in the fifth aspect can be a terminal device or a network device, or a chip (system) or other parts or components that can be set in the terminal device or the network device, or a device that includes the terminal device or the network device. This application does not limit this.

[0039] In addition, the technical effects of the communication device described in the fifth aspect can refer to the technical effects of the method described in any one of the implementation methods of the first aspect to the third aspect, and will not be repeated here.

[0040] In a sixth aspect, a communication device is provided, comprising: a processor, wherein when the processor executes computer instructions, the communication device executes the method described in any possible implementation manner of the first to third aspects.

[0041] In one possible design solution, the communication device described in the sixth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in the sixth aspect to communicate with other communication devices.

[0042] In one possible design, the communication device described in aspect 6 may further include a memory. The memory may be integrated with the processor or provided separately. The memory may be used to store the computer program and / or data involved in the method described in any one of aspects 1 to 3.

[0043] In an embodiment of the present application, the communication device described in the sixth aspect can be the terminal device or network device described in any one of the first to third aspects, or a chip (system) or other parts or components that can be set in the terminal device or the network device, or a device that includes the terminal device or the network device.

[0044] In addition, the technical effects of the communication device described in the sixth aspect can refer to the technical effects of the method described in any one of the implementation methods of the first to third aspects, and will not be repeated here.

[0045] In a seventh aspect, a communication device is provided, comprising: a processor coupled to a memory, the processor configured to execute a computer program stored in the memory, so that the communication device performs the method described in any possible implementation of the first to third aspects.

[0046] In one possible design solution, the communication device described in the seventh aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in the seventh aspect to communicate with other communication devices.

[0047] In an embodiment of the present application, the communication device described in the seventh aspect can be the terminal device or network device described in any one of the first to third aspects, or a chip (system) or other parts or components that can be set in the terminal device or the network device, or a device that includes the terminal device or the network device.

[0048] In addition, the technical effects of the communication device described in the seventh aspect can refer to the technical effects of the method described in any one of the implementation methods of the first aspect to the third aspect, and will not be repeated here.

[0049] In an eighth aspect, a communication device is provided, comprising: a processor and a memory; the memory is used to store a computer program, and when the processor executes the computer program, the communication device executes the method described in any one of the implementation methods of the first to third aspects.

[0050] In one possible design solution, the communication device described in the eighth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in the eighth aspect to communicate with other communication devices.

[0051] In an embodiment of the present application, the communication device described in the eighth aspect may be the terminal device or network device described in any one of the first to third aspects, or a chip (system) or other parts or components that can be set in the terminal device or the network device, or a device that includes the terminal device or the network device.

[0052] In addition, the technical effects of the communication device described in the eighth aspect can refer to the technical effects of the method described in any one of the implementation methods of the first aspect to the third aspect, and will not be repeated here.

[0053] In the ninth aspect, a communication chip is provided, comprising: a logic circuit and a communication interface, wherein the logic circuit is used to execute computer instructions, and the communication interface is used for the communication chip to communicate with other devices or chips, and when the logic circuit executes the computer instructions, the method described in any one of the implementation methods of the first to third aspects is implemented.

[0054] In a tenth aspect, a communication system is provided, which includes: an access network device for executing the method described in the second aspect, and a model management function entity for executing the method described in the third aspect.

[0055] In the eleventh aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are run on a computer, the computer executes the method described in any possible implementation method of the first to third aspects.

[0056] In the twelfth aspect, a computer program product is provided, comprising a computer program or instructions, which, when executed on a computer, enables the computer to execute the method described in any one of the possible implementations of the first to third aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings.

[0058] Figure 1 A schematic diagram of the architecture of the fifth-generation mobile communication system 5GS provided in an embodiment of the present application; Figure 2 Schematic diagram of the communication system architecture provided in the embodiment of the present application Figure 1 ; Figure 3 Schematic diagram of the communication system architecture provided in the embodiment of the present application Figure 2 ; Figure 4 Schematic diagram of the communication method provided in this embodiment Figure 1 ; Figure 5 A schematic diagram of the structure of the beam prediction model provided in an embodiment of the present application; Figure 6 Schematic diagram of the communication method provided in this embodiment Figure 2 ; Figure 7 Schematic diagram of the communication method provided in this embodiment Figure 3 ; Figure 8 Schematic diagram of the structure of the communication device provided in the application embodiment Figure 1 ; Figure 9 Schematic diagram of the structure of the communication device provided in the application embodiment Figure 2 . DETAILED DESCRIPTION

[0059] For ease of understanding, the technical terms involved in the embodiments of this application are first introduced below.

[0060] 1. 5G Mobile Communication System (5G System, 5GS) Figure 1 This is a schematic diagram of the 5GS architecture, as shown in Figure 1 As shown, 5GS includes: access network (AN) and core network (CN), and may also include: terminals.

[0061] The terminal may be a terminal with transceiver functions, or a chip or chip system that can be installed in the terminal. The terminal may also be called terminal equipment, user equipment (UE), access terminal, subscriber unit (subscriber unit), user station, mobile station (MS), mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent, or user device. The terminal in the embodiments of the present application can be a mobile phone, a cellular phone, a smart phone, a tablet computer, a wireless data card, a personal digital assistant (PDA), a wireless modem, a handheld device (handset), a laptop computer, a machine type communication (MTC) terminal, a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, an in-vehicle terminal, a road side unit (RSU) with terminal function, a mobile Internet device (MID), etc. The terminal of the present application may also be an onboard module, onboard module, onboard component, onboard chip or onboard unit built into the vehicle as one or more components or units. The embodiments of the present application do not limit the type or category of the terminal device.

[0062] The AN implements access-related functions, providing network access for authorized users in a specific area and determining transmission links of varying quality for user data based on user level and service requirements. The AN forwards control signals and user data between terminals and the CN. The AN may include access network equipment, also known as radio access network (RAN) equipment. The CN is primarily responsible for maintaining mobile network subscription data and providing terminal devices with functions such as session management, mobility management, policy management, and security authentication. CN mainly includes the following: user plane function (UPF), authentication server function (AUSF), access and mobility management function (AMF), session management function (SMF), network slice selection function (NSSF), network exposure function (NEF), network repository function (NRF), policy control function (PCF), unified data management (UDM), unified data storage (UDR), application function (AF), and location management function (LMF).

[0063] like Figure 1 As shown in the figure, the UE accesses the 5G network through the RAN equipment, and the UE communicates with the AMF through the N1 interface (referred to as N1); the RAN communicates with the AMF through the N2 interface (referred to as N2); the RAN communicates with the UPF through the N3 interface (referred to as N3); the SMF communicates with the UPF through the N4 interface (referred to as N4), and the UPF accesses the data network (DN) through the N6 interface (referred to as N6). In addition, Figure 1The control plane functions shown in the figure, such as AUSF, AMF, SMF, NSSF, NEF, NRF, PCF, UDM, UDR, and AF, interact using service-based interfaces. For example, the service-based interface provided by AUSF includes Nausf; the service-based interface provided by AMF includes Namf; the service-based interface provided by SMF includes Nsmf; the service-based interface provided by NSSF includes Nnssf; the service-based interface provided by NEF includes Nnef; the service-based interface provided by NRF includes Nnrf; the service-based interface provided by PCF includes Npcf; the service-based interface provided by UDM includes Nudm; the service-based interface provided by UDR includes Nudr; the service-based interface provided by AF includes Naf; and the service-based interface provided by LMF includes Nlmf.

[0064] A RAN device may be a device that provides access to a terminal device. For example, a RAN device may include an access network device or a base station in a next-generation mobile communication system. Alternatively, the network device may be named in other ways in the next-generation mobile communication system, all of which are within the scope of protection of the embodiments of this application, and this application does not impose any restrictions thereon. Alternatively, the RAN device may include a 5G device, such as a gNB in an NR system, or one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, or a network node constituting a gNB, a transmission and reception point (TRP or transmission point, TP), or a transmission measurement function (TMF), such as a baseband unit (BBU), a centralized unit (CU), a distributed unit (DU), an RSU with base station functionality, a wired access gateway, or a 5G core network. Alternatively, RAN equipment may also include access points (APs) in wireless fidelity (WiFi) systems, wireless relay nodes, wireless backhaul nodes, various forms of macro base stations, micro base stations (also known as small stations), relay stations, access points, wearable devices, and vehicle-mounted devices.

[0065] The LMF provides terminal positioning services and is primarily responsible for tasks related to acquiring, processing, storing, and distributing location data. By working in conjunction with various positioning systems (such as the Global Positioning System (GPS), the BeiDou satellite navigation system, and mobile communication base stations), the LMF accurately acquires the location information of various devices (such as base stations and terminals). The AMF, SMF, NSSF, NEF, NRF, UDM, UDR, and AF mentioned above can be found in the relevant descriptions in the existing technology and will not be repeated here.

[0066] It should be understood that the above naming is defined only to facilitate the distinction between different functions and should not constitute any limitation to this application. This application does not exclude the possibility of adopting other naming in 5G networks and other future networks. For example, in future communication networks, some or all of the above network elements may continue to use 5G terminology, or may adopt other names.

[0067] Regarding the aforementioned problem that in the beam measurement process, the method of using an AI model to predict the transmission beam used by the access network device to communicate with the terminal may result in the predicted transmission beam not being the optimal transmission beam, thereby reducing the communication quality between the terminal and the access network device. The embodiment of the present application proposes an AI model that can predict the beam used by the access network device to communicate with the terminal based on the location of the terminal, that is, the terminal can obtain the beam used by the access network device to communicate with the terminal predicted by the beam prediction model by inputting its location into the AI model. And in the process of using the AI model to predict the transmission beam used by the access network device to communicate with the terminal, when it is determined that the beam predicted by the AI model is inaccurate, the terminal obtains at least one beam used by the access network device to communicate with the terminal by means of beam measurement, and sends the information of the at least one beam and the location of the terminal to the model management function entity to update the AI model, thereby improving the accuracy of the beam used by the access network device to communicate with the terminal predicted by the updated AI model.

[0068] The technical solutions in the present application will be described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only a part of the embodiments of the present application, rather than all of the embodiments. The following embodiments can be used as examples to more clearly illustrate the technical solutions of the present application, and are not intended to limit the scope of protection of the present application. It will be understood by those skilled in the art that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other.

[0069] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as vehicle-to-everything (V2X) communication systems, device-to-device (D2D) communication systems, Internet of Vehicles communication systems, fourth-generation (4G) mobile communication systems such as long-term evolution (LTE) systems, 5G mobile communication systems such as NR systems, and future communication systems.

[0070] This application will present various aspects, embodiments, or features around systems that may include multiple devices, components, modules, etc. It should be understood that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. Furthermore, combinations of these aspects may also be used.

[0071] It should be noted that in the embodiments of this application, words such as "exemplary" and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. At the same time, relational terms such as "first" and "second" in the description of this application are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a set of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device.

[0072] In the embodiments of this application, the terms "information," "signal," "message," "channel," and "signaling" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0073] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field will know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0074] In order to facilitate understanding of the embodiments of the present application, first Figure 2 The communication system shown in FIG. 1 is used as an example to describe in detail the communication system applicable to the embodiment of the present application. Figure 2 A schematic diagram of the architecture of a communication system applicable to the communication method provided in an embodiment of the present application.

[0075] like Figure 2 As shown, the communication system can apply the above-mentioned 5GS, and the communication system mainly includes: terminals, access network equipment and model management functional entities.

[0076] The terminal may be one or more, such as a first terminal, a second terminal, and a third terminal. For details about the terminal, please refer to the relevant introduction in the aforementioned "1.5GS", which will not be repeated here.

[0077] The access network device may be one or more, such as a first access network device, a second access network device, and a third access network device. The access network device may be an access network device in the above-mentioned 5GS, such as a RAN device. For details, please refer to the relevant introduction in the above-mentioned "1.5GS" and will not be repeated here.

[0078] The model management function entity can be used to perform at least one of the following operations: training an AI model, updating an AI model, storing an AI model, or managing an AI model. The model management function entity can also provide AI model download services for terminals or access network devices. The model management function entity can also be referred to as a "model management server," "model server," "model cloud server," or other names. The model management function entity can be located in a core network or access network device. The model management function entity can be a standalone device, such as a server, cloud server, computer, personal computer (PC), or laptop; or, the model management function entity can be integrated with other devices. For example, when the model management function entity is located in the core network, the model management function entity can be integrated with core network elements (such as UPF, PCF, or network data analytics function (NWDAF)).

[0079] Optionally, the communication system further includes a LMF entity. The LMF entity can be described in detail in the aforementioned "1.5GS" and will not be described in detail here.

[0080] For example, Figure 3 As shown, Figure 3 The communication system shown includes multiple terminals, R access network devices, a model management function entity and an LMF entity, that is, in the communication system, there are R cells, each cell includes an access network device and multiple terminals, and the terminal can be a single-antenna terminal; the model management function entity is used to provide services related to the beam prediction model for multiple terminals and R access network devices, and the LMF entity is used to provide positioning services for multiple terminals, and R is a positive integer.

[0081] In the above-mentioned communication system, the terminal can combine the prediction results of the beam prediction model with the actual communication effect of the beam. When the beam performance of the beam predicted by the beam prediction model based on its location is less than a threshold, the terminal sends M beams measured by the terminal to the access network device, and sends its location to the model management functional entity, so that the access network device determines a beam for communicating with the terminal based on the M beams, and indicates the beam to the model management functional entity, so that the model management functional entity updates the beam prediction model based on the terminal's location and the beam, thereby improving the accuracy of the transmission beam predicted by the updated beam prediction model for the access network device to communicate with the terminal.

[0082] It should be understood that the above content is an exemplary description of the embodiments of the present application and is not intended to limit the embodiments of the present application. Figure 4-Figure 7 Description of the illustrated embodiment.

[0083] For ease of understanding, the following first introduces the training process of the beam prediction model.

[0084] For the training process of the beam prediction model, the model management functional entity can first obtain (or collect) samples for training the candidate beam prediction model. After the number of samples reaches the sample threshold, all the obtained samples are used to train the candidate beam prediction model to obtain the beam prediction model.

[0085] For example, the model management function entity can obtain the location of each terminal within the network service range of the access network device and the beam used by the access network device to communicate with the terminal, and use the location and the beam as a training sample to obtain multiple training samples. Figure 4 , taking the position and beam corresponding to a terminal as an example, the process of obtaining a training sample is introduced.

[0086] above Figure 4Schematic diagram of the communication method provided in this embodiment Figure 1 The method can be used for communication between terminals, access network equipment, LMF entities and model management function entities in the above communication system.

[0087] like Figure 4 As shown, the above communication method includes: S401: The model management function entity sends model status indication information to the access network device. Correspondingly, the access network device receives the model status indication information from the model management function entity.

[0088] The model status indication information is used to indicate that the beam prediction model has not completed training. The model status indication information can be a preset or protocol-predefined state variable, such as 0 or 1, and can be set according to actual conditions without limitation.

[0089] The beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the terminal's location.

[0090] The incomplete training of the beam prediction model can be understood as: there is currently no beam prediction model corresponding to the access network device; in other words, the terminal within the network coverage of the access network device currently needs to measure the beam corresponding to the access network device to determine the beam used by the access network device to communicate with the terminal.

[0091] The model management function entity may send model status indication information to the access network device when the access network device starts to be deployed.

[0092] S402: In response to the model status indication information, the access network device broadcasts beam measurement enabling information.

[0093] The beam measurement activation information is used to instruct the terminal to send K beams to the access network device based on the measurement results of N beams, and send information used to obtain the location of the terminal, where N is a positive integer and K is a positive integer less than or equal to N.

[0094] The N beams are all beams used by the access network device for communication. The N beams may be predefined by the protocol or preset by the access network device, without limitation.

[0095] The K beams are the beams whose beam performance is in the top K among the measured N beams. The beam performance of the beam can characterize the communication quality of the access network device communicating with the terminal through the beam. The beam performance can be represented by the terminal measuring the signal strength and / or signal quality of the signal transmitted on the beam. The signal strength can be the reference signal received power (RSRP). The signal quality can be the reference signal received quality (RSRQ) and the signal to interference plus noise ratio (SINR). RSRP, RSRQ and SINR can be referred to the relevant introduction in the prior art and will not be repeated here.

[0096] Beam measurement enabling information can be carried in a system information block (SIB) message. That is, the access network device can send beam measurement enabling information through a SIB message. In addition, the beam measurement enabling information can be indicated by the value of a preset reserved bit in the SIB message, and the preset reserved bit is any reserved bit among multiple reserved bits in the SIB message. For example, the value of the preset reserved bit in the SIB message can be set to 0 or 1 to indicate the beam measurement enabling information. The beam measurement enabling information can also be carried in a master information block (MIB) message or a newly defined message, and can be flexibly set according to actual conditions without restriction.

[0097] After receiving the model status indication information, the access network device can determine that its corresponding beam prediction model has not completed training. In this case, the access network device can instruct the terminal within its network coverage to obtain K beams using beam measurement and send information for obtaining the location of the terminal to obtain the location of the terminal and the beam used by the access network device to communicate with the terminal. In addition, the access network device can periodically broadcast beam measurement activation information. The broadcast interval of the periodic broadcast of beam measurement activation information can be flexibly set according to actual conditions and is not restricted.

[0098] Furthermore, in this embodiment of the present application, the model management function entity may not send model status indication information to the access network device. That is, the model management function entity may not trigger the access network device to broadcast beam measurement activation information. Instead, when the access network device is deployed, a pre-set or protocol-predefined periodic broadcast of beam measurement activation information by the access network device is performed.

[0099] S403: In response to the beam measurement enabling information, the terminal obtains K beams obtained by measurement.

[0100] After receiving the beam measurement enabling information, the terminal can measure each of the N beams, and based on the measurement results of the N beams, obtain K beams for sending to the access network device.

[0101] Exemplarily, the access network device periodically broadcasts beam measurement configuration information, which may include information related to N beams (e.g., beam bandwidth, direction, center frequency, etc.) and information related to beam measurement (e.g., beam measurement period and duration, etc.). After receiving the beam measurement activation information, the terminal may obtain information related to the N beams and beam measurement information based on the beam measurement configuration information, and measure each of the N beams based on the information related to the N beams and beam measurement information. During the beam measurement process, the terminal may adjust the direction of the receiving beam to align it with each beam to be measured in the base station, receive the signal transmitted by the beam, and record the signal strength and / or signal quality of the signal. After measuring the signal strength and / or signal quality corresponding to each of the N beams, the terminal may determine, based on the signal strength and / or signal quality of each beam, K beams to be sent to the access network device. For example, the terminal may sort the N beams from best to worst according to their corresponding signal strength and / or signal quality, and determine the top K beams after sorting. When the terminal measures the signal strength and signal quality of the beam, the terminal may perform a weighted average of the measured signal strength and signal quality of the beam, and determine K beams based on the weighted average value corresponding to each beam.

[0102] In an embodiment of the present application, the access network device may send beam measurement configuration information to the terminal device via downlink control information (DCI), a SIB message, or radio resource control (RRC) signaling. Furthermore, the specific principles and implementations of the access network device sending the beam measurement configuration information and the terminal measuring the beam based on the beam measurement configuration information can be referenced in the prior art and are not further described herein.

[0103] S404: The terminal sends a beam indication message to the access network device. Correspondingly, the access network device receives the beam indication message from the terminal.

[0104] The beam indication message is used to indicate information about K beams measured by the terminal. The K beams can be one or more beams. When the K beams are one beam or multiple beams, the information carried in the first beam indication message is different, as described below.

[0105] When K is 1, the K beams may be the optimal beams with the best beam performance among the N beams. The beam indication message may include identification information of the terminal and identification information of the optimal beam. The identification information of the terminal may be the terminal's ID (identifier), international mobile subscriber identity (IMSI), or subscription permanent identifier (SUPI). The identification information of the optimal beam may be the index or identifier of the optimal beam.

[0106] When K is a positive integer greater than 1 and less than or equal to N, the beam indication message may include the terminal's identification information, the identification information of the K beams, and information indicating the beam performance of the K beams. The identification information of the K beams may be an index or identifier of each of the K beams, and the information indicating the beam performance of the K beams may be the signal strength and / or signal quality corresponding to each of the K beams. The beam identification information and the information indicating the beam performance of the beam are associated with each other. For example, the beam identification information and the information indicating the beam performance of the beam may be provided in the same information element.

[0107] After the terminal obtains K measured beams, it can send information about these K beams to the access network device. After receiving the beam indication message, the access network device can determine the beam used for communication with the terminal from the K beams indicated in the beam indication message. For example, when K is 1, the access network device can determine the beam indicated by the beam indication message as the beam used for communication with the terminal. Alternatively, when K is a positive integer greater than 1 and less than or equal to N, the access network device can determine a beam from the K beams for communication with the terminal based on the beam performance of the K beams (the signal strength and / or signal quality corresponding to each of the K beams) and the actual conditions of the access network device (such as network load and service demand). After determining the beam used for communication with the terminal from the K beams, the access network device uses the beam to communicate with the terminal and sends a training beam indication message to the model management function entity, so that the model management function entity uses the beam to update the candidate beam prediction model.

[0108] S405: In response to the beam indication message, the access network device sends a training beam indication message to the model management function entity. Correspondingly, the model management function entity receives the training beam indication message from the access network device.

[0109] The training beam indication message includes identification information of the terminal and identification information of the target beam.

[0110] The target beam is the beam actually used for communication between the access network device and the terminal among the K beams. The target beam is used to train the candidate beam prediction model, which is a beam prediction model that has not yet completed training.

[0111] S406: The terminal sends a positioning reference signal (PRS) request message to the LMF entity. Correspondingly, the LMF entity receives the PRS request message from the terminal.

[0112] The PRS request message is used to request a PRS. The PRS request message may include at least one of the following information: a PRS configuration identifier, a PRS configuration parameter, or PRS configuration information.

[0113] The PRS configuration identifier is an ID of a predefined set of PRS configuration parameters. The terminal can determine a set of PRS configuration parameters corresponding to its current environment based on the predefined sets of PRS configuration parameters.

[0114] PRS configuration parameters are at least one of the following PRS parameters: period variation, time offset, repetition count, bandwidth, comb pattern, and transmit power (or frequency) variation. The period variation is the amount by which the PRS period is varied; the time offset is the offset of the PRS in the time domain; the repetition count is the number of times the PRS is transmitted; the bandwidth is the frequency range used to transmit the PRS; the comb pattern refers to the distribution pattern of the PRS in the frequency domain; and the transmit power (or frequency) variation is the specific value by which the PRS transmit power or frequency changes compared to the initial configuration.

[0115] The PRS configuration information may be used to indicate the current service type or positioning accuracy of the terminal, and the PRS configuration information may be an index corresponding to the current service type or positioning accuracy of the terminal.

[0116] The PRS request message may be an LTE positioning protocol (Long Term Evolution Positioning Protocol, LPP) message. The LPP message may refer to the prior art and will not be described in detail here.

[0117] After receiving the beam measurement enablement information, the terminal may send a PRS request message to the LMF entity to obtain its location. In addition, after receiving the beam measurement enablement information, the terminal may perform S403 and S406 simultaneously, or perform S403 and S406 in sequence, such as performing S403 first and then S406, or performing S406 first and then S403, without limitation.

[0118] S407: In response to the PRS request message, the LMF entity sends a PRS configuration update request message to the access network device. Correspondingly, the access network device receives the PRS configuration update request message from the LMF entity.

[0119] The PRS configuration update request message is used to request updating of the PRS configuration and to send the PRS based on the updated PRS configuration. For details, please refer to the relevant introduction in the prior art and will not be repeated here.

[0120] S408: In response to the PRS configuration request message, the access network device sends a PRS to the terminal. Correspondingly, the terminal receives the PRS from the access network device.

[0121] PRS is used to perform positioning calculations. For details, please refer to the relevant introduction in the prior art and will not be repeated here.

[0122] S409: The terminal obtains location measurement information according to the PRS.

[0123] The location measurement information indicates the time difference of arrival (TDOA) or angle of arrival (AOA) between the PRS sent by the access network device and the terminal. This time difference or angle can be used to obtain the terminal's location.

[0124] In an embodiment of the present application, a receiver on the terminal can capture the PRS from the access network device through the RF front end and the digital signal processing unit; after the receiver captures the PRS, the terminal can start a measurement program to determine the TDOA of the PRS arriving at the terminal by calculating the time difference of the PRS arriving at the terminal, or determine the AOA of the PRS arriving at the terminal by analyzing the phase difference of the PRS on different antenna elements.

[0125] S4010: The terminal sends location measurement information to the LMF entity. Correspondingly, the LMF entity receives the location measurement information from the terminal.

[0126] That is, after obtaining the TDOA or AOA of the PRS from the access network device arriving at the terminal, the terminal can send the TDOA or AOA to the LMF entity.

[0127] S4011, the LMF entity calculates the location of the terminal based on the location measurement information.

[0128] LMF can calculate the terminal's location (denoted as location #1) based on the location of the access network device and the TDOA (or AOA) of the PRS reaching the terminal. The specific implementation principle can be referred to in the existing technology and will not be repeated here.

[0129] It can be understood that the specific implementation of the above S406-S411 can refer to the existing technology and will not be repeated here.

[0130] S4012: The LMF entity sends a location indication message to the model management function entity based on the location measurement result. Correspondingly, the model management function entity receives the location indication message from the LMF entity.

[0131] The location indication message may include identification information of the terminal and information indicating location #1. The information indicating location #1 may be the longitude and latitude corresponding to location #1 or location information of location #1 relative to the access network device, without limitation.

[0132] After the LMF entity obtains the location of the terminal based on the location measurement information, it can send the location of the terminal to the model management function entity, so that the model management function entity updates the candidate beam prediction model based on the location of the terminal.

[0133] In addition, in the embodiment of the present application, the terminal may also obtain its location through other means (such as GPS or satellite positioning) and send its location to the model management function entity. In this case, the terminal does not need to perform the above S406-S4012.

[0134] S4013: The model management function entity obtains training samples based on the beam indication message and the position indication message.

[0135] After receiving the beam indication message and the position indication message, the model management function entity can associate (or match) the identification information of the target beam in the beam indication message and the information indicating position #1 in the position indication message based on the terminal identification information in the beam indication message and the position indication message. In other words, the model management function entity can use the identification information of the target beam and position #1 as a training sample. This training sample can be used to train the candidate beam prediction model, and position #1 in the training sample can be used as input data, and the identification information of the target beam can be used as a standard value. In other words, this information can be regarded as the label corresponding to position #1.

[0136] It can be understood that the above S401-S4013 is a process of obtaining one sample for one terminal. For each terminal within the network coverage of the access network device, each terminal can obtain the training sample corresponding to the terminal through the above process.

[0137] When the number of samples obtained by the model management functional entity is greater than the sample threshold, the model management functional entity can divide the sample data into a training set and a test set according to a preset ratio (such as 7:3 or 8:2), and use the training set to train the candidate beam prediction model.

[0138] After the beam prediction model training is completed, the model management functional entity can use the test set to test the trained beam prediction model. If the accuracy of the beam prediction model is greater than the accuracy threshold (such as 80%, 75% or 70%), the beam prediction model is stored, and the terminals within the network coverage of the access network device use the beam prediction model; if the accuracy of the beam prediction model is less than or equal to the accuracy threshold, the training samples are continued to be obtained in the above manner, and the obtained training samples are used to continue training the beam prediction model. The training method for the candidate beam prediction model in the embodiment of the present application can reuse the model training method in the prior art, which will not be repeated here.

[0139] In addition, the beam prediction model in the embodiment of the present application can be a neural network model. Figure 5 As shown, the input data of the beam prediction model is the location of the terminal. The input data is processed by the neurons in the neural network model to obtain the output data of the beam prediction model, that is, the identification information of the beam used by the access network device to communicate with the terminal (such as the index or identification of the beam).

[0140] After the training of the beam prediction model corresponding to the access network device is completed, the terminal within the network coverage of the access network device can use the beam prediction model to predict the transmission beam used by the access network device to communicate with the terminal. And in the process of the terminal using the beam prediction model, when the terminal determines that the beam predicted by the beam prediction model is inaccurate, it can obtain at least one beam used by the access network device to communicate with the terminal by beam measurement, and send the at least one beam and the location of the terminal to the model management function entity to update the beam prediction model. Figure 6 Detailed introduction.

[0141] For example, Figure 6 Schematic diagram of the communication method provided in this embodiment Figure 2 The method can be used for communication between terminals, access network equipment and model management functional entities in the above communication system.

[0142] like Figure 6 As shown, the above communication method includes: S601: The terminal obtains beam performance of a first beam.

[0143] The first beam is a beam predicted by the beam prediction model based on the first position of the terminal, which is used by the access network device to communicate with the terminal. That is, the first beam can be used by the access network device to send a signal to the terminal.

[0144] The beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the terminal's location. The input data of the beam prediction model can be the terminal's location, and the output data can be identification information of the beam used by the access network device to communicate with the terminal. For example, if the terminal's location is location #a1, location #a1 is input into the beam prediction model, and the output data of the beam prediction model is identification #a1, then it can be indicated that the beam predicted by the beam prediction model is the beam indicated by identification #a1, that is, the beam indicated by identification #a1 can be used by the access network device to send signals to the terminal.

[0145] Different access network devices correspond to different beam prediction models. In other words, terminals within the network coverage of different access network devices can use different beam prediction models to predict beams. For example, a communication system includes three access network devices, namely access network device #b1, access network device #b2, and access network device #b3. Access network device #b1 corresponds to beam prediction model #b1, access network device #b2 corresponds to beam prediction model #b2, and access network device #b3 corresponds to beam prediction model #b3. Terminals within the network coverage of access network device #b1 can use beam prediction model #b1 to predict beams, terminals within the network coverage of access network device #b2 can use beam prediction model #b2 to predict beams, and terminals within the network coverage of access network device #b3 can use beam prediction model #b3 to predict beams.

[0146] Optionally, the beam prediction model is obtained from a model management functional entity, which is used to manage beam prediction models corresponding to different access network devices.

[0147] The model management function entity may store the correspondence between the network coverage of different access network devices and different beam prediction models. The model management function entity may determine the beam prediction model used by the terminal based on this correspondence and the terminal's location. For example, the model management function entity may determine the network coverage of the terminal based on the terminal's location; then, based on the network coverage, determine the beam prediction model corresponding to the network coverage, with the beam prediction model being the beam prediction model used by the terminal. Continuing with the above example, the network coverage range #b1 of access network device #b1 has a corresponding relationship with beam prediction model #b1, the network coverage range #b2 of access network device #b2 has a corresponding relationship with beam prediction model #b2, the network coverage range #b3 of access network device #b3 has a corresponding relationship with beam prediction model #b3, terminal #b is at position #b, and position #b is within the network coverage range #b2; when the model management functional entity determines that position #b is within the network coverage range #b2, it determines that terminal #b uses the beam prediction model #b2 corresponding to the network coverage range #b2 to predict the beam of access network device #b2 for communicating with terminal #b.

[0148] In an embodiment of the present application, the model management functional entity manages the beam prediction models corresponding to different access network devices, facilitating unified management of multiple beam prediction models corresponding to different access network devices. Furthermore, the model management functional entity can be used to generate beam prediction models corresponding to different access network devices. In this case, the access network devices do not need to generate their own corresponding beam prediction models, eliminating the need to equip the access network devices with high-computing hardware resources, thereby reducing costs. Furthermore, beam prediction models corresponding to already deployed access network devices can be generated for the access network devices.

[0149] Before using the beam prediction model, the terminal may request the beam prediction model from the model management function entity based on its location. That is, before the terminal obtains the beam performance of the first beam (i.e., S601), the method may further include: the terminal sending a model request message to the model management function entity, and the model management function entity correspondingly receiving the model request message from the terminal, wherein the model request message is used to request the beam prediction model corresponding to the first location where the terminal is located; in response to the model request message, the model management function entity sending a model response message to the terminal, and the terminal correspondingly receives the model response message from the model management function entity, wherein the model response message is used to indicate the beam prediction model.

[0150] The model request message may include identification information of the terminal and information indicating the first location. The identification information may be the terminal ID, IMSI, or SUPI. For details, reference may be made to the relevant descriptions in the prior art and will not be repeated here. The information indicating the first location may be the latitude and longitude corresponding to the first location.

[0151] The model response message may include information indicating the beam prediction model. The information indicating the beam prediction model may include an identifier or a download link of the beam prediction model.

[0152] After receiving the model request message, the model management function entity can determine the network coverage of the first location based on the information indicating the first location in the model request message, and determine the beam prediction model corresponding to the network coverage based on the network coverage, that is, the beam prediction model is the beam prediction model corresponding to the first location. After receiving the model response message, the terminal can obtain the beam prediction model based on the information indicating the beam prediction model in the model response message, such as downloading the beam prediction model corresponding to the identifier based on the identifier of the beam prediction model at the location where the beam prediction model is stored, or downloading the beam prediction model through a download link of the beam prediction model.

[0153] After obtaining the beam prediction model from the model management functional entity, the terminal can use the beam prediction model to predict the beam that the access network device will use to communicate with the terminal. Specifically, the terminal can input its first location into the beam prediction model to obtain the first beam output by the beam prediction model. The terminal is within the network coverage of the access network device. In other words, the terminal is within the cell where the access network device resides. In this case, the terminal can establish a communication connection with the access network device for communication.

[0154] The terminal's first location is the location where it subsequently communicates with the access network device, and this first location may be the location of the terminal when using the beam prediction model. There are various ways to obtain the first location, such as obtaining the first location through an LMF entity or obtaining the first location through satellite positioning. The following describes in detail how the terminal obtains the first location through the LMF entity.

[0155] When the terminal obtains its location through the LMF entity, it can request PRS from the LMF entity, and the LMF entity triggers the access network device to send PRS to the terminal; the terminal can measure the TDOA or AOA of the PRS reaching the terminal based on the PRS sent by the access network device, and obtain the first location based on the TODA or AOA.

[0156] Exemplarily, before the terminal obtains the beam performance of the first beam (i.e., S601), the method may further include: the terminal sends a PRS request message to the LMF entity, and accordingly, the LMF entity receives the PRS request message from the terminal, wherein the PRS request message is used to request PRS; in response to the PRS request message, the LMF entity sends a PRS configuration update request message to the access network device, and accordingly, the access network device receives the PRS configuration update request message from the LMF entity, wherein the PRS configuration update request message is used to request to update the configuration of the PRS; in response to the PRS configuration update request message, the access network device receives the PRS configuration update request message from the LMF entity, wherein the PRS configuration update request message is used to request to update the configuration of the PRS; The network access device sends a PRS to the terminal, and accordingly, the terminal receives the PRS from the access network device; the terminal obtains location measurement information based on the PRS, and sends the location measurement information to the LMF entity, and accordingly, the LMF entity receives the location measurement information from the terminal, wherein the location measurement information includes the TDOA or AOA of the PRS reaching the terminal; after receiving the location measurement information, the LMF entity calculates the terminal's location based on the TODA or AOA, and sends the location information to the terminal, and accordingly, the terminal receives the location information from the LMF entity, wherein the location information is used to indicate the first location of the terminal.

[0157] It can be understood that the specific implementation of the above terminal obtaining its location through the LMF entity is the same as the above Figure 4 In the embodiment shown, the terminal sends location measurement information to the LMF entity, and the specific implementation of the LMF entity calculating the terminal's location based on the location measurement information is similar. For details, please refer to the above-mentioned related introduction and will not be repeated here.

[0158] In an embodiment of the present application, the terminal requests PRS from the LMF entity and obtains its location based on the PRS, thereby improving the accuracy of the obtained location information, thereby improving the accuracy of the beam predicted using the beam prediction model.

[0159] The beam used by the access network device to communicate with the terminal can be understood as: the beam through which the access network device sends signals to the terminal. The beam is any one of all the transmission beams used by the access network device for communication.

[0160] The beam performance of the first beam can represent the communication quality between the access network device and the terminal via the first beam. This beam performance can be represented by the signal strength and / or signal quality of the signal transmitted on the first beam measured by the terminal. The signal strength can be RSRP. The signal quality can be RSRQ or SINR. RSRP, RSRQ, and SINR can be described in the relevant literature and will not be further elaborated here.

[0161] In an embodiment of the present application, after obtaining the beam prediction model and the first position, the terminal may use the first position as input data for the beam prediction model and input the first position into the beam prediction model to obtain the first beam. After obtaining the first beam using the first position and the beam prediction model, the terminal may measure the signal on the first beam to obtain the beam performance of the first beam.

[0162] S602: When the beam performance of the first beam is less than or equal to a threshold, the terminal sends a first beam indication message to the access network device. Correspondingly, the access network device receives the first beam indication message from the terminal.

[0163] The above thresholds can be set based on actual conditions. When the beam performance of a beam is characterized by the signal strength and signal quality of the signal transmitted on the beam, a threshold can be set based on the signal strength and signal quality. For example, the signal strength and signal quality can be normalized and weighted respectively, and the threshold can be set based on the normalized signal strength, signal quality, and weight. Alternatively, a threshold can be set for each of the signal strength and signal quality. If the signal strength or signal quality is less than the threshold, it indicates that the beam performance is less than or equal to the threshold.

[0164] If the beam performance of the first beam is less than or equal to the threshold, it may indicate that the communication quality of the access network device using the beam to communicate with the terminal is poor. This may be caused by inaccurate prediction of the beam prediction model.

[0165] The first beam indication message is used to indicate information of M beams measured by the terminal, where the M beams are the beams whose beam performance is in the top M among the N beams measured, and the N beams are all beams used for communication by the access network device, where M is an integer greater than 0 and less than or equal to N.

[0166] The M beams may be one or more beams. When the M beams are one beam or multiple beams, the information carried in the first beam indication message is different.

[0167] When M is 1, the M beams can be the optimal beams with the best beam performance among the N beams. The above-mentioned first beam indication message may include the identification information of the terminal, the identification information of the optimal beam and the measurement indication information; the identification information of the optimal beam can be the index or identification of the optimal beam, and the measurement indication information is used to indicate that the optimal beam is obtained through beam measurement.

[0168] When M is greater than 1 and less than or equal to N, the above-mentioned first beam indication message may include the identification information of the terminal, the identification information of M beams and the information used to indicate the beam performance of the M beams; the identification information of the M beams may be the index or identification of each beam in the M beams; and the identification information of the beam in the first beam indication message and the information used to indicate the beam performance of the beam have an associated relationship, such as the identification information of the beam and the information used to indicate the beam performance of the beam may be set in the same information element.

[0169] When the beam performance of the first beam is less than or equal to the threshold, the terminal can measure each of the N beams, and based on the measurement results of the N beams, determine the beams whose beam performance is in the top M among the N beams; after determining the M beams, the terminal can send first beam indication information for indicating the M beams to the access network device based on the M beams.

[0170] For example, an access network device corresponds to eight beams, where N is 8, the eight beams are beams #c1 to #c8, and M is 3. The beam prediction model predicts beam #c3, and the signal strength corresponding to beam #c3 is less than or equal to the threshold. The eight beams are sorted from highest to lowest according to their corresponding signal strengths, resulting in the following ranking: beam #c4, beam #5, beam #c6, beam #c3, beam #c2, beam #c1, beam #c7, and beam #c8. Based on this ranking, the top three beams in performance among the eight beams are: beam #c4, beam #5, and beam #c6. In this case, the terminal sends the access network device identification information for beam #c4, the signal strength corresponding to beam #c4, the identification information for beam #c5, the signal strength corresponding to beam #c5, the identification information for beam #c6, and the signal strength corresponding to beam #c6 via a first beam indication message.

[0171] S603: In response to the first beam indication message, the access network device sends an update beam indication message to the model management function entity. Correspondingly, the model management function entity receives the update beam indication message from the access network device.

[0172] The model management functional entity is used to update the beam prediction model based on the second beam (described below).

[0173] The updated beam indication message is used to indicate the second beam, and the updated beam indication message may include the identification information of the terminal and the identification information of the second beam. The second beam is the beam among the M beams actually used for communication between the access network device and the terminal. Exemplarily, when M is 1, the second beam is the above-mentioned optimal beam, that is, in this case, the access network device can use the beam indicated by the first beam indication message to communicate with the terminal. When M is greater than 1 and less than or equal to N, the access network device can determine a beam for communication between the access network device and the terminal from the M beams based on the beam performance of the M beams and the actual situation of the access network device (such as network load, business demand, etc.), that is, the second beam. The identification information of the second beam may be the index or identification of the second beam.

[0174] After receiving the first beam indication information, the access network device can determine the second beam used to communicate with the terminal based on the first beam indication information, and when it is determined that the M beams are obtained by the terminal through beam measurement, the identification information of the second beam and the identification of the terminal are sent to the model management function entity, so that the model management function entity updates the beam prediction model based on the second beam.

[0175] In addition, when M is 1, the access network device can determine that the beam indicated by the first beam indication information is obtained through beam measurement based on the measurement indication information carried in the first beam indication information; when M is greater than 1 and less than or equal to N, the access network device can determine that the beam is obtained through beam measurement based on the number of beams indicated by the first beam indication information being multiple.

[0176] S604: The terminal sends a first location indication message to the model management function entity. Correspondingly, the model management function entity receives the first location indication message from the terminal.

[0177] The first location indication message is used to indicate a first location. The first location indication message may include identification information of the terminal and the first location of the terminal, such as the longitude and latitude of the first location.

[0178] The model management function entity is used to update the beam prediction model based on the first position and the identification information of the second beam.

[0179] After receiving the updated beam indication message and the first position indication message, the model management function entity can associate (or match) the identification information of the second beam in the updated beam indication message with the first position in the first position indication message based on the identification information of the terminal in the updated beam indication message and the first position indication message, that is, the identification information of the first position and the second beam can be used as an update sample for updating the beam prediction model. That is, the above method can also include: the model management function entity obtains an update sample based on the updated beam indication message and the first position indication message, the update sample is used to update the beam prediction model, and the update sample includes the identification information of the first position and the second beam (such as the index or identifier of the second beam).

[0180] In the above-mentioned update sample, the first position can be used as input data for updating the beam prediction model, and the identification information of the second beam can be used as a standard value, that is, the identification information can be regarded as a label corresponding to the first position.

[0181] The above S604 and S602 can be performed simultaneously or in a certain order, such as performing S602 first and then S604, or performing S604 first and then S602, without limitation.

[0182] In summary, in an embodiment of the present application, when the beam performance of a beam predicted by a beam prediction model is less than or equal to a threshold, the terminal sends M beams whose beam performance is in the top M among the N beams obtained by measurement to the access network device, and sends the first position thereof to the model management function entity. This enables the access network device to send the second beam used by the access network device for communicating with the terminal to the model management function entity based on the M beams, so that the model management function entity can update the beam prediction model based on the first position and the second beam, such as by associating the identification information of the first position and the second beam as a sample to update the beam prediction model. In this way, when the prediction result obtained by the terminal using the beam prediction model is inaccurate, a more accurate beam can be obtained for communication between the access network device and the terminal by actually measuring the beam, and the model management function entity can update the beam prediction model based on the more accurate beam and the first position of the terminal, thereby improving the accuracy of the transmission beam predicted by the updated beam prediction model for the access network device to communicate with the terminal.

[0183] In addition, during the use of the beam prediction model, each terminal within the network coverage of the access network device can use the location of the terminal and the beam used by the access network device to communicate with the terminal as an update sample when the beam performance of the beam predicted by the beam prediction model is less than or equal to a threshold. When the number of update samples obtained by the model management functional entity is greater than the update sample number threshold, the model management functional entity can update the beam prediction model based on the collected update samples and store the updated beam prediction model, such as replacing the beam prediction model before the update with the updated beam prediction model. The way in which the model management functional entity uses update samples to update the beam prediction model can reuse the method of updating the model through samples in the existing technology without limitation.

[0184] Optionally, in combination with the above embodiment, before the terminal sends the first beam indication message (i.e., S602) to the access network device, the above method may also include: the terminal sends a configuration information request message to the access network device, and accordingly, the access network device receives the configuration information request message from the terminal, wherein the configuration information request message is used to request the access network device to send information for measuring all beams used by the access network device for communication; in response to the configuration information request message, the access network device sends a configuration information response message to the terminal, and accordingly, the terminal receives the configuration information response message from the access network device, wherein the configuration information response message is used to indicate information for measuring N beams; the terminal measures the N beams based on the configuration information response message, and determines the above-mentioned M beams.

[0185] All beams used by the access network device for communication are the above-mentioned N beams.

[0186] The information used to measure N beams may include relevant information of the N beams (such as the bandwidth, direction, center frequency, etc. of the beams) and relevant information of beam measurement (such as the period and duration of beam measurement, etc.). Figure 4 The beam measurement configuration information in the illustrated embodiments is similar and can be understood by reference to each other, and will not be repeated here.

[0187] In the embodiment of the present application, during the application phase of the beam prediction model, the access network device may not periodically broadcast information for measuring N beams (as described above). Figure 4 The beam measurement configuration information in the embodiment shown in FIG. 1 is used to enable the terminal to request information for measuring N beams as needed. For example, if the beam performance of the first beam is less than or equal to a threshold, the terminal requests information for measuring N beams from the access network device. This reduces power consumption of the access network device.

[0188] Furthermore, the configuration information request message may include the terminal's identification information and the beam performance (signal strength and / or signal quality) of the first beam. In this case, after receiving the configuration information request message, the access network device may determine that the beam performance of the first beam is less than or equal to a threshold, and based on this determination, determine to send a configuration information response message to the terminal. In other words, when the beam performance of the first beam is less than or equal to the threshold, the terminal may trigger the access network device to send information for measuring N beams by sending a configuration information request message to the access network device.

[0189] In addition, when M is 1, the first beam indication message may not carry the measurement indication information. That is, the terminal may instruct the access network device to send M beams to the access network device using a beam measurement method through a configuration request message. This can reduce the terminal's communication overhead.

[0190] Optionally, in combination with the above embodiment, before the terminal obtains the beam performance of the first beam (i.e., S601), the above method may further include: the model management function entity obtains the status of the beam prediction model, and the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the terminal's location; the model management function entity sends first model status indication information to the access network device according to the status of the beam prediction model, and accordingly, the access network device receives the first model status indication information from the model management function entity, wherein the first model status indication information is used to indicate that the beam prediction model has completed training; in response to the first model status indication information, the access network device broadcasts model activation information, and accordingly, the terminal receives the model activation information from the access network device, wherein the model activation information is used to instruct the terminal to activate the beam prediction model; the terminal obtains the first beam by inputting the first position into the beam prediction model according to the model activation information.

[0191] The state of the beam prediction model is that the beam prediction model has completed training. The model management function entity can obtain the state of the beam prediction model having completed training when the beam prediction model has completed training.

[0192] When the beam prediction model is trained, the model management function entity can indicate to the access network device that the corresponding beam prediction model has been trained. The access network device can then broadcast model activation information to instruct terminals within the access network device's network coverage to use the beam prediction model. This enables switching between beam measurement and beam prediction model acquisition.

[0193] Furthermore, model activation information is carried in a System Information Block (SIB) message. This means that existing messages can be reused to send model activation information. This improves resource utilization and reduces transmission latency. Of course, model activation information can also be sent via a new message. The specific method can be set based on actual circumstances and is not limited.

[0194] Furthermore, the model activation information is indicated by a first value of a first preset reserved bit in the SIB message, where the first preset reserved bit is any reserved bit among multiple reserved bits in the SIB message.

[0195] The first value may be 1 or 0. For example, when the value of the first preset reserved bit is 1, or when the first preset reserved bit is flag 1, the terminal is instructed to enable the beam prediction model. The first value may also be other values, which can be set according to actual circumstances without limitation.

[0196] In the embodiments of the present application, any reserved bit can be selected from multiple reserved bits in the SIB message, and the value of the reserved bit can be used to instruct the terminal to enable the beam prediction model (i.e., model activation information). In this way, the existing structure of the SIB message can be used to implement the transmission of the model activation information, thereby reducing the difficulty of transmitting the model activation information through the SIB message.

[0197] Optionally, in combination with the above embodiment, after the terminal obtains the beam performance of the first beam (i.e., S601), the above method may further include: when the beam performance of the first beam is greater than a threshold, the terminal sends a second beam indication message to the access network device, and accordingly, the access network device receives the second beam indication message from the terminal, wherein the second beam indication message is used to indicate the above-mentioned first beam.

[0198] The beam performance of the first beam being greater than the threshold may indicate that the communication quality of the access network device using the beam to communicate with the terminal meets the requirements.

[0199] The second beam indication message is used to indicate the above-mentioned first beam, which can be understood as: the second beam indication message is used to indicate that the beam used by the access network device to communicate with the terminal is the first beam.

[0200] If the beam performance of the first beam exceeds a threshold, the terminal can send the first beam to the access network device for use. That is, after receiving the first beam, the access network device can use the first beam to communicate with the terminal. This ensures communication quality between the terminal and the access network device when using the beam predicted by the beam prediction model.

[0201] After the terminal sends the second beam indication message to the access network device, if the beam prediction model is updated, the access network device can instruct the terminal to enable the updated beam prediction model to switch the beam for communication between the access network device and the terminal based on the beam predicted by the updated beam prediction model. Alternatively, the terminal can download the updated beam prediction model and use the updated beam prediction model to predict the beam used by the access network device to communicate with it after it moves within the network coverage of the access network.

[0202] In one possible implementation, after the terminal sends a second beam indication message to the access network device, the above method may further include: the model management function entity obtains the status of a beam prediction model, where the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the terminal's location; the model management function entity sends second model status indication information to the access network device based on the status of the beam prediction model, and accordingly, the access network device receives the second model status indication information from the model management function entity, wherein the second model status indication information is used to indicate that the beam prediction model has been updated; in response to the second model status indication information, the access network device broadcasts an update model enablement message, and accordingly, the terminal receives an update model enablement message from the access network device, wherein the update model enablement message is used to instruct the terminal to enable the updated beam prediction model; in response to the update model enablement message, the terminal obtains a third beam through the updated beam prediction model, where the third beam is the output result of inputting the first position into the updated beam prediction model; the terminal sends a third beam indication message to the access network device, and accordingly, the access network device receives the third beam indication message from the terminal, wherein the third beam indication message is used to indicate the third beam.

[0203] The state of the beam prediction model is that the beam prediction model has completed updating. The model management functional entity can obtain the state that the beam prediction model has completed updating when the beam prediction model has completed updating.

[0204] Before using the updated beam prediction model, the terminal may request the updated beam prediction model from the model management functional entity. For example, the terminal may send the terminal's location and identification information to the model management functional entity to request the updated beam prediction model. It can be understood that the specific implementation of the terminal requesting the updated beam prediction model from the model management functional entity is similar to the specific implementation of the terminal requesting the beam prediction model from the model management functional entity. The difference is that the models obtained by the terminal are different, that is, one is the model before the update and the other is the model after the update. The specific implementation of the terminal requesting the updated beam prediction model from the model management functional entity can be understood by referring to the relevant introduction in the aforementioned S601 and will not be repeated here.

[0205] The third beam may be the same as or different from the first beam.

[0206] When the beam prediction model is updated, the model management function entity can indicate to the access network device that the corresponding beam prediction model has been updated. This allows the access network device to broadcast an updated model activation message, instructing terminals connected to the access network device to use the updated beam prediction model. Because the updated beam prediction model has higher prediction accuracy than the pre-update beam prediction model (i.e., the beam prediction model already used by the terminal), the terminal can use the updated beam prediction model to predict the beam that the access network device will use for communication with the terminal and send the beam to the access network device, enabling the access network device to use the beam, thereby improving the communication quality between the access network device and the terminal.

[0207] In addition, before sending a third beam indication message to the access network device, the terminal may first determine whether the third beam is the same as the first beam. If the third beam is different from the first beam, the terminal may send a third beam indication message to the access network device. Alternatively, after the access network device receives the third beam indication message from the terminal, the access network device may directly switch the beam used for communication with the terminal from the first beam to the third beam. The access network device may also first determine whether the third beam is the same as the first beam. If the third beam is different from the first beam, the terminal may switch the beam used for communication with the terminal from the first beam to the third beam. The specific configuration can be flexibly set based on actual conditions and is not limited.

[0208] In another possible implementation, after the terminal sends a second beam indication message to the access network device, the above method may also include: the model management function entity obtains the status of the beam prediction model, and the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the location of the terminal; the model management function entity sends second model status indication information to the access network device according to the status of the beam prediction model, and accordingly, the access network device receives the second model status indication information from the model management function entity, wherein the second model status indication information is used to indicate that the beam prediction model has been updated; in response to the second model status indication information, the access network device broadcasts an update model enablement message, and accordingly, the terminal receives an update model enablement message from the access network device, wherein the update model enablement message is used to instruct the terminal to enable the updated beam prediction model; the terminal obtains the updated beam prediction model according to the update model enablement message.

[0209] The specific implementation of the status of the beam prediction model and the terminal obtaining the updated beam prediction model can be referred to the above related introduction and will not be repeated here.

[0210] When the beam prediction model is updated, the model management function entity can indicate to the access network device that the beam prediction model corresponding to the access network device has been updated, so that the access network device can broadcast an update model activation message to instruct the terminal connected to the access network device to use the updated beam prediction model. After obtaining the updated beam prediction model, the terminal can use the updated beam prediction model after its position changes and its changed position falls within the network coverage of the access network device, that is, after it moves within the network coverage of the access network device. In this way, the accuracy of the beam predicted by the terminal using the beam prediction model can be improved. In addition, the process of the terminal using the updated beam prediction model is similar to the process of the terminal using the beam prediction model. For details, please refer to the aforementioned related introduction and will not be repeated here.

[0211] Optionally, in combination with the above embodiment, after the terminal sends the first beam indication message (i.e., S602) to the access network device, the above method may further include: the model management function entity obtains the status of the beam prediction model, and the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the location of the terminal; the model management function entity sends second model status indication information to the access network device according to the status of the beam prediction model, and accordingly, the access network device receives the second model status indication information from the model management function entity, wherein the second model status indication information is used to indicate that the beam prediction model has been updated; in response to the second model status indication information, the access network device broadcasts an update model enablement message, and accordingly, the terminal receives an update model enablement message from the access network device, wherein the update model enablement message is used to instruct the terminal to enable the updated beam prediction model; the terminal obtains the updated beam prediction model according to the update model enablement message.

[0212] It can be understood that when the terminal completes the update of the beam prediction model, the specific implementation of obtaining the updated beam prediction model can refer to the above related introduction, which will not be repeated here.

[0213] Optionally, in combination with the above embodiments, before the terminal obtains the beam performance of the first beam and when the terminal is located at a second location within the network coverage of the access network device, training samples for training the candidate beam prediction model can be collected from the terminal, that is, the terminal can send its location to the model management functional entity, and obtain the K beams used by the access network device to communicate with the terminal through beam measurement, and send the information of the K beams to the access network device, so that the access network device determines a beam for communicating with the terminal from the K beams, and sends the beam to the model management functional entity for training the candidate beam prediction model.

[0214] Exemplarily, the above method may further include: The model management function entity obtains the status of a beam prediction model, where the beam prediction model is used to predict the beam used by the access network device to communicate with the terminal based on the location of the terminal.

[0215] The model management functional entity sends third model status indication information to the access network device based on the status of the beam prediction model. Correspondingly, the access network device receives the third model status indication information from the model management functional entity, wherein the third model status indication information is used to indicate that the beam prediction model has not completed training.

[0216] In response to the third model state indication information, the access network device broadcasts beam measurement enablement information, and accordingly, the terminal receives the beam measurement enablement information from the access network device, wherein the beam measurement enablement information is used to instruct the terminal to send K beams to the access network device based on the measurement results of N beams, and send information for obtaining the position of the terminal, where the K beams are the beams whose beam performance is in the top K among the N beams measured, and K is a positive integer less than or equal to N.

[0217] In response to the beam measurement enabling information, the terminal sends a fourth beam indication message to the access network device. Accordingly, the access network device receives the fourth beam indication message from the terminal, wherein the fourth beam indication message is used to indicate the information of K beams measured by the terminal.

[0218] In response to the fourth beam indication message, the access network device sends a training beam indication message to the model management function entity. Accordingly, the model management function entity receives the training beam indication message from the access network device. The training beam indication message is used to indicate the fourth beam, and the training beam indication message includes the identification information of the terminal and the identification information of the fourth beam. The fourth beam is the beam among the K beams actually used for communication between the access network device and the terminal. The fourth beam is used to train a candidate beam prediction model, and the candidate beam prediction model is a beam prediction model that has not completed training.

[0219] The terminal sends location measurement information to the LMF entity, and accordingly, the LMF entity receives the location measurement information from the terminal, wherein the location measurement information is used to indicate the time difference or angle for the signal sent by the access network device to reach the terminal, and the time difference or angle is used to obtain the second position of the terminal. The second position and the fourth beam are used to train the candidate beam prediction model. The fourth beam is the beam among the K beams actually used for communication between the access network device and the terminal, and the candidate beam prediction model is a beam prediction model that has not completed training.

[0220] In response to the location measurement information, the LMF entity sends a second location indication message to the model management function entity. Accordingly, the model management function entity receives the second location indication message from the location management function entity, wherein the second location indication message includes the identification information of the terminal and the second location of the terminal.

[0221] The model management function entity obtains a training sample based on the training beam indication message and the second position indication message. The training sample includes identification information of the second position and the fourth beam, and the training sample is used to train a candidate beam prediction model, which is a beam prediction model that has not completed training.

[0222] The above-mentioned third model state indication information, second model state indication information and first model state indication information can be represented by preset or predefined state variables. For example, the state control variable 0 can be used to indicate that the beam prediction model has not completed training (i.e., the third model state indication information), the state variable 1 can be used to indicate that the beam prediction model has completed training (i.e., the first model state indication information), and the state variable 2 can be used to indicate that the beam prediction model has not completed training (i.e., the second model state indication information).

[0223] During the training phase of the beam prediction model, the terminal can send K beams obtained through beam measurement to the access network device based on the beam measurement activation information, and send location measurement information to the location management function entity, so that the access network device can select a beam to communicate with the terminal based on the K beams, and send the identification information of the beam to the model management function entity for training the candidate beam prediction model. The location management function entity can also calculate the second location of the terminal based on the location measurement information, and send the second location to the model management function entity for training the candidate beam prediction model. In this way, training samples corresponding to the terminal for training the candidate beam prediction model can be collected.

[0224] Furthermore, the beam measurement activation information is carried in the SIB message. This means that the beam measurement activation information can be sent using an existing message. This improves resource utilization and reduces transmission latency. Of course, the beam measurement activation information can also be sent using a new message. The specific method can be set based on actual circumstances and is not limited.

[0225] Furthermore, the beam measurement enabling information is indicated by a second value of a second preset reserved bit in the SIB message, where the second preset reserved bit is any reserved bit among multiple reserved bits in the SIB message.

[0226] The second value may be 1 or 0. For example, when the value of the second preset reserved bit is 0, or when the second preset reserved bit is flag 0, the terminal is instructed to enable beam measurement. The second value may also be other values, which can be set according to actual circumstances without limitation.

[0227] In an embodiment of the present application, any reserved bit can be selected from multiple reserved bits in an SIB message, and the value of the reserved bit can be used to indicate to the terminal the method for enabling beam measurement (i.e., beam measurement enabling information). In this way, the existing structure of the SIB message can be used to transmit the beam measurement enabling information, thereby reducing the difficulty of transmitting the beam measurement enabling information via the SIB message. In addition, the second preset reserved bit can be the same as the first preset reserved bit, that is, the beam measurement enabling information and the model enabling information can be indicated by different values of a reserved bit in the SIB message. For example, the value of a reserved bit in the SIB message is 1 to indicate to the terminal that the beam prediction model (i.e., model enabling information) is enabled, and the value of the reserved bit is 0 to indicate to the terminal that the beam measurement method (i.e., beam measurement enabling information) is enabled. In this way, reserved bits in the SIB message can be conserved.

[0228] It can be understood that the specific implementation of the training phase of the beam prediction model in the embodiment of the present application can refer to the aforementioned Figure 4 The relevant introduction of the embodiment shown in the figure is understood, and the "third model state indication information", "fourth beam indication message", "fourth beam", "second position indication message", and "second position" in the embodiment of the present application correspond to Figure 4 "Model state indication information", "beam indication message", "target beam", "position indication message", "position #1" in the embodiment shown.

[0229] In addition, the "AI model" mentioned in the above embodiments can also be replaced by a "machine learning (ML) model", that is, the beam prediction model in the above embodiments can also be an ML model without limitation.

[0230] It can also be understood that in the various embodiments of the present application, unless otherwise specified and there is no logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0231] The above is a general introduction to the communication method provided by the embodiment of the present application in combination with the method embodiment. For ease of understanding, the above method is introduced below using a specific scenario.

[0232] Figure 7 Schematic diagram of the communication method provided in this embodiment Figure 3 This method is applicable to Figure 2The communication system shown primarily involves interactions between a terminal, a base station (the aforementioned access network equipment), an LMF entity, and a model management function entity. In this scenario, a terminal uses beam prediction model #1 to predict beam #1, which the base station will use for communication with the terminal. When the beam performance of beam #1 is less than or equal to a threshold, the terminal obtains beam #2 through beam measurement and sends beam #2 to the base station, enabling the base station to use beam #2 for communication with the terminal. The terminal also sends beam #2 to the model management function entity to update beam prediction model #1. The terminal also sends its location to the model management function entity via the LMF entity to update beam prediction model #1. When the beam performance of beam #1 is greater than the threshold, the terminal sends beam #1 to the base station, enabling the base station to communicate with the terminal via beam #1.

[0233] like Figure 7 As shown, the above communication method includes: S701: The model management function entity sends a state variable 1 to the base station. Correspondingly, the base station receives the state variable 1 from the model management function entity.

[0234] State variable 1 is used to indicate that the beam prediction model #1 corresponding to the base station has completed training. State variable 1 and beam prediction model #1 correspond to the aforementioned Figure 6 The first model state indication information and the beam prediction model in the illustrated embodiment.

[0235] S702: The base station broadcasts a SIB message according to state variable 1.

[0236] The preset reserved bit in the SIB message has a value of 1, which is used to instruct the terminal to enable the beam prediction model (i.e., the aforementioned Figure 6 Model enabling information in the embodiment shown).

[0237] S703: In response to the SIB message, the terminal sends a PRS request message to the LMF entity. Correspondingly, the LMF entity receives the PRS request message from the terminal.

[0238] S704: In response to the PRS request message, the LMF entity sends a PRS configuration update request message to the base station. Correspondingly, the base station receives the PRS configuration update request message from the LMF entity.

[0239] S705: In response to the PRS configuration update request message, the base station sends a PRS to the terminal. Correspondingly, the terminal receives the PRS from the base station.

[0240] S706: The terminal obtains location measurement information according to the PRS.

[0241] S707: The terminal sends location measurement information to the LMF entity. Correspondingly, the LMF entity receives the location measurement information from the terminal.

[0242] S708: The LMF entity calculates the location of the terminal based on the location measurement information.

[0243] S709: The LMF entity sends location information to the terminal. Correspondingly, the terminal receives the location information from the LMF entity.

[0244] The location information is used to indicate the location #1 of the terminal, which corresponds to the aforementioned Figure 6 The first position in the embodiment shown.

[0245] S7010: The terminal sends message #1 to the model management function entity. Correspondingly, the model management function entity receives message #1 from the terminal.

[0246] Message #1 is used to request the beam prediction model corresponding to the location #1 where the terminal is located. The message #1 includes the terminal ID and information indicating the location #1. Message #1 corresponds to the aforementioned Figure 6 Model request message in the illustrated embodiment.

[0247] S7011: The model management function entity sends message #2 to the terminal. Correspondingly, the terminal receives message #2 from the model management function entity.

[0248] Message #2 is used to indicate the beam prediction model #1. This message #2 corresponds to the aforementioned Figure 6 The model response message in the illustrated embodiment.

[0249] S7012: The terminal inputs position #1 into beam prediction model #1 to obtain beam #1.

[0250] Beam #1 corresponds to the aforementioned Figure 6 The first beam in the embodiment shown.

[0251] S7013: The terminal measures the signal strength of the signal transmitted on beam #1.

[0252] After measuring the signal strength of the signal transmitted on beam #1, the terminal can determine the relationship between the signal strength and the threshold. If the signal strength is greater than the threshold, the beam #1 can be sent to the base station so that the base station uses beam #1 to communicate with the terminal (i.e., case 1, S7014-S7015 below); if the signal strength is less than or equal to the threshold, the beam can be obtained through beam measurement, and the beam can be sent to the base station, and the terminal's location #1 can be sent to the model management function entity (i.e., case 2, S7016-S7023 below).

[0253] S7014: When the signal strength is greater than the threshold, the terminal sends message #3 to the base station. Correspondingly, the base station receives message #3 from the terminal.

[0254] Message #3 includes identification information of beam #1, such as the index or identification of beam #1. Message #3 corresponds to the aforementioned Figure 6 Second beam indication message in the illustrated embodiment.

[0255] S7015. Based on message #3, the base station determines that the transmitting beam corresponding to position #1 is beam #1.

[0256] That is, after receiving message #3, the base station can use beam #1 to communicate with the terminal.

[0257] S7016: When the signal strength is less than or equal to the threshold, the terminal sends message #4 to the base station. Correspondingly, the base station receives message #4 from the terminal.

[0258] Message #4 is used to request the base station to send information for measuring the beam corresponding to the base station, and message #4 includes signal strength. This message #4 corresponds to the aforementioned Figure 6 Configuration information request message in the illustrated embodiment.

[0259] S7017: In response to message #4, the base station sends message #5 to the terminal. Correspondingly, the terminal receives message #5 from the base station.

[0260] Message #5 is used to indicate the information of measuring N beams, which are all beams used by the base station for communication. Message #5 corresponds to the above Figure 6 Configuration information response message in the illustrated embodiment.

[0261] S7018: The terminal obtains beam #2 by measuring N beams according to message #5.

[0262] Measuring the N beams may be understood as measuring the signal strength of a signal transmitted on each of the N beams.

[0263] Beam #2 is the beam with the highest signal strength among the N beams. Figure 6 The second beam in the embodiment shown.

[0264] S7019: The terminal sends message #6 to the base station. Correspondingly, the base station receives message #6 from the terminal.

[0265] Message #6 includes the terminal ID and identification information of beam #2.

[0266] S7020, based on message #6, the base station determines that the transmitting beam corresponding to position #1 is beam #2.

[0267] Message #6 corresponds to the above Figure 6 The first beam indication message in the embodiment shown.

[0268] That is, after receiving message #6, the base station can use beam #2 to communicate with the terminal. Based on message #4, the base station can determine that beam #2 is the beam obtained by the terminal through beam measurement and send the identification information of beam #2 and the terminal ID to the model management function entity.

[0269] S7021: The base station sends message #7 to the model management function entity. Correspondingly, the model management function entity receives message #7 from the base station.

[0270] Message #7 includes the terminal ID and the identification information of beam #2. Figure 6 Update beam indication message in the illustrated embodiment.

[0271] S7022: The terminal sends message #8 to the model management function entity. Correspondingly, the model management function entity receives message #8 from the terminal.

[0272] Message #8 includes the terminal ID and location #1. This message #8 corresponds to the aforementioned Figure 6 A first position indication message in the illustrated embodiment.

[0273] S7023, the model management function entity matches the information used to indicate beam #2 and the information used to indicate position #1 according to message #7 and message #8.

[0274] That is, the model management function entity can obtain an updated sample according to message #7 and message #8, where the updated sample includes identification information of position #1 and beam #2.

[0275] S7024: When the number of collected update samples is greater than the update sample number threshold, the model management function entity updates the beam prediction model #1 based on the collected update samples to obtain an updated beam prediction model #1.

[0276] S7025, the model management functional entity stores the updated beam prediction model #1.

[0277] S7026: The model management function entity sends the state variable 2 to the base station. Correspondingly, the base station receives the state variable 2 from the model management function entity.

[0278] State variable 2 is used to indicate that the beam prediction model corresponding to the base station has been updated. The state variable 2 corresponds to the aforementioned Figure 6 The second model state indication information in the illustrated embodiment.

[0279] S7027, the base station broadcasts message #9 according to state variable 2.

[0280] Message #9 is used to instruct the terminal to activate the updated beam prediction model #1. Message #9 corresponds to the aforementioned Figure 6 The update model in the illustrated embodiment enables messages.

[0281] S7028: In response to message #9, the terminal sends message #10 to the model management function entity. Correspondingly, the model management function entity receives message #10 from the terminal.

[0282] Message #10 is used to request the beam prediction model corresponding to the location #1 where the terminal is located. This message #10 includes the terminal ID and information indicating the location #1. Message #10 can refer to the aforementioned Figure 6 Model request message in the illustrated embodiment.

[0283] S7029: The model management function entity sends message #11 to the terminal. Correspondingly, the terminal receives message #11 from the model management function entity.

[0284] Message #11 is used to indicate the updated beam prediction model #1. Figure 6 The model response message in the illustrated embodiment.

[0285] S7030, the terminal inputs position #1 into the updated beam prediction model #1 to obtain beam #3.

[0286] Beam #3 corresponds to the aforementioned Figure 6 The third beam in the embodiment shown.

[0287] S7031: The terminal sends message #12 to the base station. In response, the base station receives message #12 from the terminal.

[0288] Message #12 is used to indicate the beam #3. Figure 6 A third beam indication message in the illustrated embodiment.

[0289] S7032, based on message #12, the base station determines that the transmitting beam corresponding to position #1 is beam #3.

[0290] That is, after receiving message #12, the base station can switch the beam for communicating with the terminal from beam #1 to beam #3, that is, the base station can use beam #3 to communicate with the terminal.

[0291] It is understood that the specific implementation of the above S701-S7032 can refer to the above Figure 6The relevant introduction of the embodiment shown is not repeated here. The above S701-S7023 are the operations in the application phase of the beam prediction model #1, and the above S7024-S7032 are the operations in the update phase of the beam prediction model #1.

[0292] Furthermore, S701-S7032 described above can also be used in traffic scenarios. In such traffic scenarios, the terminal can be installed on a vehicle, such as an onboard module, onboard module, onboard component, onboard chip, or onboard unit built into the vehicle as one or more components or units. Base stations and LMF entities can be deployed in key areas such as urban roads, highways, and transportation hubs. In such traffic scenarios (such as autonomous driving), the rapid movement of vehicles requires that beam selection be completed extremely quickly. By inputting the terminal's location into the model prediction beam, the vehicle can more quickly and timely obtain the access network equipment's beam for communication with the terminal. Furthermore, this approach enables the model management function entity to continuously collect samples for updating the beam prediction model. This dynamic update mechanism ensures that the beam prediction model can adapt to environmental changes, maintaining high prediction accuracy. For example, in urban environments, building obstruction and multipath effects can cause significant fluctuations in signal strength. By dynamically updating the beam prediction model, beam selection can be adjusted in real time, ensuring stable and efficient communication.

[0293] It can also be understood that the above S701-S7032 is only an example. When the signal strength is less than or equal to the threshold, the terminal can also measure N beams and send multiple measured beams to the access network device, so that the access network device can determine the beam used by the access network device to communicate with the terminal from the multiple beams, and send the identification information of the beam to the model management function entity.

[0294] Combination of the above Figure 4-Figure 7 The communication method provided by the embodiment of the present application is described in detail. Figure 8 A communication device for executing the communication method provided in an embodiment of the present application is described in detail.

[0295] Figure 8 This is a schematic diagram of the structure of the communication device provided in the embodiment of the present application. Figure 1 For example, Figure 8 As shown, the communication device 800 includes: a processing module 801 and a transceiver module 802. For ease of description, Figure 8 Only the main components of the communication device are shown.

[0296] Among them, the transceiver module 802 is used to perform the above Figure 4-Figure 7 The processing module 801 is used to perform the above-mentioned Figure 4-Figure 7Other functions in addition to the sending and receiving functions in the method shown.

[0297] Optionally, the transceiver module 802 may include a sending module ( Figure 8 Not shown) and the receiving module ( Figure 8 (not shown). The sending module is used to implement the sending function of the communication device 800, and the receiving module is used to implement the receiving function of the communication device 800.

[0298] Optionally, the communication device 800 may further include a storage module ( Figure 8 When the processing module 801 executes the program or instruction, the communication device 800 can execute the above-mentioned Figure 4-Figure 7 Functions of a terminal or network device in the method shown.

[0299] It can be understood that the communication device 800 can be a terminal or a network device, or a chip (system) or other parts or components that can be set in a terminal or a network device, or a device that includes a terminal or a network device. This application does not limit this.

[0300] In addition, the technical effects of the communication device 800 can be referred to Figure 4-Figure 7 The technical effects of the communication method shown will not be described in detail here.

[0301] Figure 9 Schematic diagram of the structure of the communication device provided in the embodiment of the present application Figure 2 For example, the communication device may be a terminal or a network device (such as an access network device or a model management function entity), or a chip (system) or other component or assembly that can be set in a terminal or a network device. Figure 9 As shown, the communication device 900 may include a processor 901. Optionally, the communication device 900 may also include a memory 902 and / or a transceiver 903. The processor 901 is coupled to the memory 902 and the transceiver 903, such as by a communication bus. It can be understood that the communication device 900 in the embodiment of the present application and the above-mentioned communication device 800 are communication devices in two different embodiments, that is, the communication device 800 is Figure 8 In the embodiment shown, the communication device 900 is Figure 9 The communication device in the embodiment shown.

[0302] The following combination Figure 9 The components of the communication device 900 are described in detail. Processor 901 is the control center of communication device 900 and can be a single processor or a collective term for multiple processing elements. For example, processor 901 can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs). Furthermore, when communication device 900 is a terminal or access network device, processor 901 can also be a communication chip.

[0303] Optionally, the processor 901 can execute various functions of the communication device 900, such as executing the above-mentioned method, by running or executing a software program stored in the memory 902 and calling data stored in the memory 902. For example, when the communication device 900 is a terminal, the processor 901 can perform operations such as obtaining beam performance of a first beam and determining a relationship between the beam performance of the first beam and a threshold; when the communication device 900 is an access network device, the processor 901 can perform operations such as determining a second beam from M beams; when the communication device 900 is a model management function entity, the processor 901 can perform operations such as obtaining update samples and obtaining training samples.

[0304] In a specific implementation, as an embodiment, the processor 901 may include one or more CPUs, such as Figure 9 CPU0 and CPU1 are shown in FIG.

[0305] In a specific implementation, as an embodiment, the communication device 900 may also include multiple processors, such as Figure 9 901 and an alternative processor 904 are shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0306] The memory 902 is used to store the software program for executing the solution of the present application, and the execution is controlled by the processor 901. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0307] Alternatively, the memory 902 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 902 may be integrated with the processor 901 or exist independently and accessed through the interface circuit ( Figure 9 (not shown) is coupled to the processor 901, which is not specifically limited in this embodiment of the present application.

[0308] Transceiver 903 is used for communication with other communication devices. For example, when communication device 900 is a terminal, transceiver 903 can be used to communicate with access network equipment, LMF entities, or model management function entities; when communication device 900 is an access network device, transceiver 903 can be used to communicate with terminals or model management function entities; when communication device 900 is a model management function entity, transceiver 903 can be used to communicate with access network equipment, LMF entities, or terminals.

[0309] Optionally, the transceiver 903 may include a receiver and a transmitter ( Figure 9 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0310] Optionally, the transceiver 903 may include a transmitter, a receiver, a radio frequency circuit, an antenna, and an input and output device ( Figure 9 (Not shown separately in the figure). The transmitter is used to implement the transmission function; the receiver is used to implement the reception function; the radio frequency circuit is mainly used to convert baseband signals into radio frequency signals and process radio frequency signals; the antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves; the input and output devices may include a touch screen, display, or keyboard; the input and output devices are mainly used to receive data input by the user and output data to the user. It should be noted that some types of terminal devices may not have input and output devices.

[0311] When data needs to be sent, the processor performs baseband processing on the data to be sent and outputs the baseband signal to the RF circuit. Then, the RF circuit performs RF processing on the baseband signal and sends the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the terminal device, the RF circuit receives the RF signal through the antenna. The RF circuit converts the RF signal into a baseband signal and outputs the baseband signal to the processor. The processor converts the baseband signal into data and processes the data. In an actual terminal device product, there may be one or more processors and one or more memories. The memory may also be referred to as a storage medium or a storage device, etc. The memory may be set independently of the processor or integrated with the processor, and the embodiments of the present application do not limit this.

[0312] In the embodiment of the present application, the antenna and radio frequency circuit with transceiver functions can be regarded as the transceiver module of the terminal device, and the processor with processing function can be regarded as the processing module of the terminal device.

[0313] Optionally, the transceiver 903 may be integrated with the processor 901 or may exist independently and communicate with the processor 901 through the interface circuit ( Figure 9 (not shown) is coupled to the processor 901, which is not specifically limited in this embodiment of the present application.

[0314] When the communication device 900 is a communication chip, the transceiver 903 may be the chip's input and output interfaces. The input interface is used to implement a receiving function, and the output interface is used to implement a transmitting function. The processor may be a processing module, microprocessor, or integrated circuit integrated on the chip. In the above method embodiments, the transmitting operation of the network device or terminal device may be understood as an output of the chip, and the receiving operation of the network device or terminal device in the above method embodiments may be understood as an input of the chip.

[0315] It is understandable that Figure 9 The structure of the communication device 900 shown in the figure does not constitute a limitation on the communication device. The actual communication device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0316] In addition, the technical effects of the communication device 900 can refer to the technical effects of the methods described in the above method embodiments, and will not be repeated here.

[0317] It should be understood that the processor in the embodiments of the present application may also be other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general processor may be a microprocessor or any conventional processor, etc.

[0318] It should also be understood that the memory in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), EEPROM, or flash memory. The volatile memory may be RAM, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).

[0319] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0320] An embodiment of the present application also provides a communication chip, including: a logic circuit and a communication interface, the logic circuit is used to execute computer instructions, and the communication interface is used for the communication chip to communicate with other devices or chips. When the logic circuit executes the computer instructions, the above method is implemented.

[0321] An embodiment of the present application further provides a computer-readable storage medium, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer is caused to execute the above method.

[0322] An embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed on a computer, causes the computer to execute the above method.

[0323] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other.

[0324] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0325] The above detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments derived by persons of ordinary skill in the art based on the embodiments in the present application without creative effort shall fall within the scope of protection of the present application.

[0326] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0327] It should also be noted that, in the description of this application, unless otherwise specified or limited, the term "connection" should be understood in a broad sense. For example, it can mean a fixed connection, a detachable connection, or an integral connection; it can mean an electrical connection; it can mean a direct connection, an indirect connection through an intermediate medium, or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0328] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0329] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method comprises: Obtaining beam performance of a first beam, where the first beam is a beam used by an access network device to communicate with the terminal, as predicted by a beam prediction model based on a first position of the terminal; When the beam performance of the first beam is less than or equal to a threshold, sending a first beam indication message to the access network device, where the first beam indication message is used to indicate information of M beams measured by the terminal, where the M beams are beams with beam performance ranking in the top M among the N beams measured, and the N beams are all beams used for communication by the access network device, where N is a positive integer and M is a positive integer less than or equal to N. A first position indication message is sent to a model management function entity, where the first position indication message is used to indicate the first position. The model management function entity is used to update the beam prediction model based on the first position and identification information of the second beam, where the second beam is the beam among the M beams actually used for communication between the access network device and the terminal.

2. The method according to claim 1, characterized in that Before sending the first beam indication message to the access network device, the method further includes: Sending a configuration information request message to the access network device, where the configuration information request message is used to request the access network device to send information for measuring all the beams; receiving a configuration information response message from the access network device, where the configuration information response message is used to indicate information for measuring the N beams; Based on the configuration information response message, the N beams are measured and the M beams are determined.

3. The method according to claim 1, characterized in that Before obtaining the beam performance of the first beam, the method further includes: receiving model activation information from the access network device, where the model activation information is used to instruct the terminal to activate the beam prediction model; The first beam is obtained by inputting the first position into the beam prediction model according to the model activation information.

4. The method according to claim 3, characterized in that The model activation information is carried in a system information block (SIB) message.

5. The method according to claim 4, characterized in that The model activation information is indicated by a first value of a first preset reserved bit in the SIB message, where the first preset reserved bit is any one of multiple reserved bits in the SIB message.

6. The method according to claim 1, characterized in that The beam prediction model is obtained from the model management functional entity, and the model management functional entity is used to manage the beam prediction models corresponding to different access network devices.

7. The method according to claim 1, characterized in that After obtaining the beam performance of the first beam, the method further includes: In a case where the beam performance of the first beam is greater than the threshold, a second beam indication message is sent to the access network device, where the second beam indication message is used to indicate the first beam.

8. The method according to claim 7, characterized in that After sending the second beam indication message to the access network device, the method further includes: receiving an update model activation message from the access network device, where the update model activation message is used to instruct the terminal to activate the updated beam prediction model; In response to the update model enable message, obtaining a third beam through the updated beam prediction model, where the third beam is an output result of inputting the first position into the updated beam prediction model; A third beam indication message is sent to the access network device, where the third beam indication message is used to indicate the third beam.

9. The method according to any one of claims 1 to 7, characterized in that After sending the first beam indication message to the access network device, or after sending the second beam indication message to the access network device, the method further includes: receiving an update model activation message from the access network device, where the update model activation message is used to instruct the terminal to activate the updated beam prediction model; According to the update model activation message, the updated beam prediction model is obtained.

10. The method according to any one of claims 1 to 7, characterized in that Before obtaining the beam performance of the first beam, the method further includes: receiving beam measurement enabling information from the access network device, where the beam measurement enabling information is used to instruct the terminal to send K beams to the access network device based on measurement results of the N beams, and to send information used to obtain a position of the terminal, where the K beams are beams with top K beam performance among the N beams obtained by measurement, where K is a positive integer less than or equal to N; In response to the beam measurement enabling information, sending a fourth beam indication message to the access network device, where the fourth beam indication message is used to indicate information of the K beams obtained by the terminal measurement; Send location measurement information to the location management function entity, where the location measurement information is used to indicate the time difference or angle for the signal sent by the access network device to reach the terminal, and the time difference or angle is used to obtain the second position of the terminal. The second position and the identification information of the fourth beam are used to train a candidate beam prediction model, where the fourth beam is the beam among the K beams actually used for communication between the access network device and the terminal, and the candidate beam prediction model is the beam prediction model that has not completed training.

11. The method according to claim 10, characterized in that The beam measurement enabling information is carried in the SIB message.

12. The method according to claim 11, characterized in that The beam measurement enabling information is indicated by a second value of a second preset reserved bit in the SIB message, where the second preset reserved bit is any one of multiple reserved bits in the SIB message.

13. A communication method, characterized in that: The method comprises: Receiving, when beam performance of a first beam is less than or equal to a threshold, a first beam indication message from a terminal, where the first beam is a beam used by an access network device for communicating with the terminal, as predicted by a beam prediction model based on a first position of the terminal, the first beam indication message is used to indicate information of M beams measured by the terminal, where the M beams are beams with beam performance ranking among the top M among N measured beams, and the N beams are all beams used by the access network device for communication, where N is a positive integer and M is a positive integer less than or equal to N; In response to the first beam indication message, an updated beam indication message is sent to the model management function entity, wherein the updated beam indication message is used to indicate a second beam, where the second beam is the beam among the M beams actually used for communication between the access network device and the terminal, and the model management function entity is used to update the beam prediction model based on the second beam.

14. The method according to claim 13, characterized in that Before receiving the first beam indication information from the terminal, the method further includes: receiving a configuration information request message from the terminal, where the configuration information request message is used to request the access network device to send information for measuring all the beams; In response to the configuration information request message, a configuration information response message is sent to the terminal, where the configuration information response message is used to indicate information for measuring the N beams.

15. The method according to claim 13, characterized in that Before receiving the first beam indication information from the terminal, the method further includes: receiving first model status indication information from the model management function entity, where the first model status indication information is used to indicate that the beam prediction model has completed training; In response to the first model status indication information, model activation information is broadcast, where the model activation information is used to instruct the terminal to activate the beam prediction model.

16. The method according to claim 15, characterized in that The model activation information is carried in a system information block (SIB) message.

17. The method according to claim 16, characterized in that The model activation information is indicated by a first value of a first preset reserved bit in the SIB message, where the first preset reserved bit is any one of multiple reserved bits in the SIB message.

18. The method according to any one of claims 13 to 17, characterized in that Before receiving the first beam indication information from the terminal, the method further includes: receiving second model status indication information from the model management function entity, where the second model status indication information is used to indicate that the beam prediction model has completed updating; In response to the second model status indication information, an updated model activation message is broadcast, where the updated model activation message is used to instruct the terminal to activate the updated beam prediction model.

19. The method according to any one of claims 13 to 17, wherein: Before receiving the first beam indication information from the terminal, the method further includes: receiving third model status indication information from the model management function entity, where the third model status indication information is used to indicate that the beam prediction model has not completed training; In response to the third model state indication information, beam measurement enabling information is broadcast, and the beam measurement enabling information is used to instruct the terminal to send K beams to the access network device based on the measurement results of the N beams, and send information for obtaining the position of the terminal, the K beams being the beams whose beam performance is in the top K among the N beams obtained by measurement, and K is a positive integer less than or equal to N.

20. The method according to claim 19, characterized in that After broadcasting the beam measurement enabling information, the method further includes: receiving a fourth beam indication message from the terminal, where the fourth beam indication message is used to indicate information of K beams measured by the terminal; In response to the fourth beam indication message, a training beam indication message is sent to the model management function entity, where the training beam indication message is used to indicate a fourth beam, where the fourth beam is the beam among the K beams actually used for communication between the access network device and the terminal, and where the fourth beam is used to train a candidate beam prediction model, where the candidate beam prediction model is the beam prediction model that has not completed training.

21. The method according to claim 19, wherein The beam measurement enabling information is carried in the SIB message.

22. The method according to claim 21, characterized in that The beam measurement enabling information is indicated by a second value of a second preset reserved bit in the SIB message, where the second preset reserved bit is any one of multiple reserved bits in the SIB message.

23. A communication method, characterized in that: The method comprises: Obtaining a state of a beam prediction model, the beam prediction model being used to predict a beam used by an access network device to communicate with the terminal based on a location of the terminal; According to the status of the beam prediction model, first model status indication information, second model status indication information, or third model status indication information is sent to the access network device, the first model status indication information is used to indicate that the beam prediction model has completed training, the second model status indication information is used to indicate that the beam prediction model has completed updating, and the third model status indication information is used to indicate that the beam prediction model has not completed training.

24. The method according to claim 23, wherein After sending the first model status indication information to the access network device, the method further includes: receiving an updated beam indication message from the access network device, where the updated beam indication message includes identification information of the terminal and identification information of a second beam, where the second beam is a beam among M beams actually used for communication between the access network device and the terminal, the M beams are beams with beam performance ranking in the top M among N beams obtained by measurement, and the N beams are all beams used for communication by the access network device, where N is a positive integer and M is a positive integer less than or equal to N; receiving a first location indication message from the terminal, where the first location indication message includes a first location of the terminal and identification information of the terminal; According to the updated beam indication message and the first position indication message, an updated sample is obtained, where the updated sample is used to update the beam prediction model, and the updated sample includes identification information of the first position and the second beam.

25. The method according to claim 23 or 24, characterized in that After sending the third model status indication information to the access network device, the method further includes: receiving a training beam indication message from the access network device, where the training beam indication message includes identification information of the terminal and identification information of a fourth beam, where the fourth beam is a beam among the K beams actually used for communication between the access network device and the terminal, the K beams are beams with beam performance in the top K among the measured N beams, and the N beams are all beams used for communication by the access network device, where N is a positive integer and K is a positive integer less than or equal to N; receiving a second location indication message from a location management function entity, where the second location indication message includes identification information of the terminal and a second location of the terminal; According to the training beam indication message and the second position indication message, a training sample is obtained, where the training sample includes identification information of the second position and the fourth beam, and the training sample is used to train a candidate beam prediction model, where the candidate beam prediction model is the beam prediction model that has not completed training.

26. A communication device, characterized in that: The apparatus comprises: a module for executing the method according to any one of claims 1-25.

27. A communication device, characterized in that: The communication device comprises: a processor; when the processor executes computer instructions, the communication device executes the method according to any one of claims 1 to 25.

28. A communication chip, characterized in that: The communication chip includes: a logic circuit and a communication interface, the logic circuit is used to execute computer instructions, and the communication interface is used for the communication chip to communicate with other devices or chips. When the logic circuit executes the computer instructions, the method described in any one of claims 1 to 25 is implemented.

29. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a computer program or instructions, which, when executed on a computer, causes the computer to perform the method according to any one of claims 1 to 25.

30. A computer program product, characterized in that The computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a communication device, the method according to any one of claims 1 to 25 is executed.

Images