Communication method, terminal, first device, system, and storage medium

Abstract

The present disclosure provides a communication method, a terminal, a first device, a system and a storage medium, wherein the method comprises: estimating, by an AI model, an L3-RSRP at a first time to obtain an estimated value; and sending the estimated value to the first device. The present disclosure improves the fusion of AI technology and communication mechanism, improves the availability and reliability of AI-based mobility management, and is conducive to improving the efficiency, performance and scalability of wireless networks.

Description

Technical Field

[0001] This disclosure relates to the field of communications, and in particular to communication methods, terminals, first devices, systems, and storage media. Background Technology

[0002] Currently, the application of artificial intelligence (AI) is becoming more and more widespread. AI-based mobility management can dynamically adapt to constantly changing network conditions and user needs, which helps to improve the overall performance of wireless networks. Summary of the Invention

[0003] To improve the availability and reliability of AI-based mobility management, embodiments of this disclosure provide a communication method, a terminal, a first device, a system, and a storage medium.

[0004] According to a first aspect of the present disclosure, a communication method is provided, the method being executed by a terminal, the method comprising:

[0005] Using an artificial intelligence (AI) model, the L3-RSRP (L3 Reference Signal Received Power) at the first moment is estimated, and the estimated value is obtained.

[0006] The estimated value is sent to the first device.

[0007] According to a second aspect of the present disclosure, a communication method is provided, the method being performed by a first device, the method comprising:

[0008] The estimated value sent by the receiving terminal is obtained by the terminal through an artificial intelligence (AI) model to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment.

[0009] Determine the truth value, which is the truth value of L3-RSRP at the first time step;

[0010] Based on the estimated value and the true value, the accuracy of the AI ​​model in predicting L3-RSRP is determined.

[0011] According to a third aspect of the present disclosure, a terminal is provided, comprising:

[0012] The processing module is configured to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment using an artificial intelligence (AI) model, and obtain the estimated value.

[0013] The transceiver module is configured to send the estimated value to the first device.

[0014] According to a fourth aspect of the present disclosure, a first device is provided, comprising:

[0015] The transceiver module is configured to receive an estimated value sent by the terminal, which is obtained by the terminal through an artificial intelligence (AI) model to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment.

[0016] The processing module is configured to determine the truth value, which is the truth value of L3-RSRP at the first time step;

[0017] The processing module is further configured to determine the accuracy of the AI ​​model's prediction of L3-RSRP based on the estimated value and the true value.

[0018] According to a fifth aspect of the present disclosure, a terminal is provided, comprising:

[0019] One or more processors;

[0020] The processor is used to execute the method described in any one of the first aspects.

[0021] According to a sixth aspect of the present disclosure, a first device is provided, comprising:

[0022] One or more processors;

[0023] The processor is used to execute the communication method described in any one of the second aspects.

[0024] According to a seventh aspect of the present disclosure, a communication system is provided, comprising:

[0025] A terminal, the terminal being configured to implement the communication method described in any one of the first aspects;

[0026] A first device, configured to implement the communication method described in any one of the second aspects.

[0027] According to an eighth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform a communication method as described in any one of the first or second aspects.

[0028] According to a ninth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, is used to implement the communication method described in any one of the first or second aspects.

[0029] In this embodiment of the disclosure, the integration of AI technology and communication mechanisms is improved, the availability and reliability of mobility management based on AI are enhanced, and the efficiency, performance and scalability of wireless networks are improved.

[0030] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0031] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0032] Figure 1 This is an exemplary schematic diagram of the architecture of a communication system provided according to embodiments of the present disclosure.

[0033] Figure 2 This is an exemplary interactive diagram of a communication method provided according to an embodiment of the present disclosure.

[0034] Figure 3A This is one of the exemplary flowcharts of a communication method provided according to an embodiment of the present disclosure.

[0035] Figure 3B This is a second exemplary flowchart of a communication method provided according to an embodiment of the present disclosure.

[0036] Figure 4A This is an exemplary schematic diagram of a non-sliding filtering method provided according to an embodiment of the present disclosure.

[0037] Figure 4B This is an exemplary schematic diagram of a sliding filter method provided according to an embodiment of the present disclosure.

[0038] Figure 4C This is an exemplary schematic diagram illustrating the derivation of the L3-RSRP filter value corresponding to time T according to the embodiments of this disclosure.

[0039] Figure 5A This is an exemplary block diagram of a terminal provided according to an embodiment of the present disclosure.

[0040] Figure 5B This is an exemplary block diagram of a first device provided according to an embodiment of the present disclosure.

[0041] Figure 6A This is an exemplary schematic diagram of a communication device provided according to an embodiment of the present disclosure.

[0042] Figure 6B This is an exemplary schematic diagram of a chip provided according to an embodiment of the present disclosure. Detailed Implementation

[0043] This disclosure provides a communication method, a terminal, a first device, a system, and a storage medium.

[0044] In a first aspect, embodiments of this disclosure propose a communication method executed by a terminal, the method comprising: estimating the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment using an artificial intelligence (AI) model to obtain an estimated value; and sending the estimated value to the first device.

[0045] The above embodiments improve the integration of AI technology and communication mechanisms, enhance the availability and reliability of AI-based mobility management, and help improve the efficiency, performance, and scalability of wireless networks.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, the predicted value and the true value are used by the first device to determine the accuracy of the AI ​​model's prediction of L3-RSRP, and the true value is the true value of L3-RSRP at the first time point.

[0047] In the above embodiments, the estimated value and the true value can be used by the first device to determine the accuracy of the AI ​​model's prediction of L3-RSRP, which improves the integration of AI technology and communication mechanisms, enhances the availability and reliability of mobility management based on AI, and helps improve the efficiency, performance and scalability of wireless networks.

[0048] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: sending first information to the first device; wherein the first information is used by the first device to determine the truth value.

[0049] In the above embodiments, the terminal can send first information to the first device so that the first device can calculate the truth value based on the first information. This improves the integration of AI technology and communication mechanism, enhances the availability and reliability of mobility management based on AI, and helps improve the efficiency, performance and scalability of wireless networks.

[0050] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following: the layer 3 filtering method used by the terminal; the number of layer 1 samples included in each layer 1 filtering window; a first beamforming gain value, wherein the first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal; and a second value, wherein the second value is the received power value of the terminal, the second value corresponding to the first value, and the first value is the transmitted power value of the first device.

[0051] In the above embodiments, the first information may include at least one of the above, which improves the accuracy of evaluating the AI ​​model's prediction of L3-RSRP and is beneficial to improving the efficiency, performance and scalability of wireless networks.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: measuring the L3-RSRP value corresponding to the first time moment to obtain a measured value; determining the measured value as the true value; and sending the true value to the first device.

[0053] In the above embodiments, the terminal can determine the truth value and send it to the first device, which improves the accuracy of the AI ​​model's prediction of L3-RSRP and is beneficial to improving the efficiency, performance and scalability of the wireless network.

[0054] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: receiving first indication information sent by the first device; wherein the first indication information is used to indicate the first moment.

[0055] In the above embodiments, the first device can send first indication information to the terminal to indicate the first moment, thereby improving the reliability and accuracy of determining the accuracy of the AI ​​model's prediction of L3-RSRP.

[0056] Secondly, embodiments of this disclosure propose a communication method executed by a first device. The method includes: receiving a predicted value sent by a terminal, the predicted value being obtained by the terminal through an artificial intelligence (AI) model predicting the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment; determining a true value, the true value being the true value of the L3-RSRP at the first moment; and determining the accuracy of the AI ​​model's prediction of the L3-RSRP based on the predicted value and the true value.

[0057] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: receiving first information sent by the terminal; wherein the first information is used by the first device to determine the truth value; determining the truth value includes: calculating the truth value based on the first information.

[0058] In conjunction with some embodiments of the second aspect, in some embodiments, the first information includes at least one of the following: the layer 3 filtering method used by the terminal; the number of layer 1 samples included in each layer 1 filtering window; a first beamforming gain value, wherein the first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal; and a second value, wherein the second value is the received power value of the terminal, the second value corresponding to the first value, and the first value is the transmitted power value of the first device.

[0059] In some embodiments, in conjunction with the second aspect, the method further includes: setting the layer 3 filter factor to 0; and determining that the first information does not include the layer 3 filtering method used by the terminal.

[0060] In the above embodiments, the first device can set the layer 3 filter factor to 0 and determine that the layer 3 filtering method used by the terminal may not be included in the first information, which simplifies the calculation process of determining the accuracy of the AI ​​model's prediction of L3-RSRP and has high availability.

[0061] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes any one of the following: determining a second beamforming gain value of the terminal based on a first beamforming gain value included in the first information, wherein the first beamforming gain value is the beamforming gain value corresponding to the Rx beam determined by the terminal; determining a second beamforming gain value of the terminal based on the first beamforming gain value included in the first information and a first offset range, wherein the first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal; determining a second beamforming gain value of the terminal based on a second value and a first value included in the first information; wherein the second value is the received power value of the terminal, the second value corresponds to the first value, and the first value is the transmitted power value of the first device.

[0062] In the above embodiments, the first device can use any of the above methods to determine the second beamforming gain value of the terminal, thereby improving the reliability of the determined true value.

[0063] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: receiving the truth value sent by the terminal.

[0064] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: sending first indication information to the receiving first device; wherein the first indication information is used to indicate the first moment.

[0065] Thirdly, this disclosure provides a terminal comprising: a processing module configured to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment using an artificial intelligence (AI) model, thereby obtaining an estimated value; and a transceiver module configured to send the estimated value to the first device.

[0066] Fourthly, this disclosure provides a first device, comprising: a transceiver module configured to receive a predicted value transmitted by a terminal, the predicted value being obtained by the terminal through an artificial intelligence (AI) model predicting the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment; a processing module configured to determine a true value, the true value being the true value of the L3-RSRP at the first moment; the processing module is further configured to determine the accuracy of the AI ​​model's prediction of the L3-RSRP based on the predicted value and the true value.

[0067] Fifthly, embodiments of this disclosure provide a terminal comprising: one or more processors; wherein the processors are configured to perform the method described in any one of the first aspects.

[0068] In a sixth aspect, embodiments of this disclosure provide a first device comprising: one or more processors; wherein the processors are configured to perform the communication method described in any one of the second aspects.

[0069] In a seventh aspect, embodiments of this disclosure provide a communication system, comprising: a terminal configured to implement the communication method described in any one of the first aspects; and a first device configured to implement the communication method described in any one of the second aspects.

[0070] Eighthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the communication method as described in either the first or second aspect.

[0071] In a ninth aspect, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, is used to implement the communication method described in any one of the first or second aspects.

[0072] It is understood that the aforementioned terminal, first device, communication system, and storage medium are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0073] This disclosure provides a communication method, a terminal, a first device, a system, and a storage medium. In some embodiments, the terms "communication method" and "information transmission method," "information processing method," etc., can be used interchangeably; the terms "communication device" and "information transmission device," "information processing device," etc., can be used interchangeably; and the terms "information transmission system," "information processing system," "communication system," etc., can be used interchangeably.

[0074] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0075] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0076] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0077] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the aforementioned," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0078] In the embodiments disclosed herein, "multiple" refers to two or more.

[0079] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0080] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0081] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0082] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0083] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0084] In some embodiments, the apparatus and device may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. In some cases, they may also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "entity", "body", etc.

[0085] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0086] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0087] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0088] Figure 1 This is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0089] like Figure 1 As shown, the communication system 100 includes a terminal 101 and a first device 102.

[0090] In some embodiments, terminal 101 includes, for example, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home, but is not limited thereto.

[0091] In some embodiments, the first device 102 may be a network device, such as at least one of an access network device and a core network device.

[0092] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system, but is not limited thereto.

[0093] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0094] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0095] In some embodiments, the core network equipment may be a single device, including a first network element, a second network element, etc., or it may be multiple devices or a group of devices, each including all or part of the first network element, the second network element, etc. Network elements may be virtual or physical. The core network may include, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0096] In some embodiments, the first device 102 may be a test equipment (TE) that can be used to test the performance of an AI model. In this embodiment of the disclosure, the first device 102 may be deployed independently to determine the accuracy of the Layer 3-Reference Signal Receiving Power (L3-RSRP) of the AI ​​model deployed on the terminal 101.

[0097] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0098] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0099] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0100] The following embodiments of this disclosure can be applied to Figure 1 The communication system 100 shown, or a part thereof, but not limited to it. Figure 1 The entities shown are illustrative; a communication system may include... Figure 1 All or part of the main body, or may include Figure 1 Other entities besides the main body, the number and form of each entity are arbitrary, each entity can be physical or virtual, the connection relationship between the entities is illustrative, the entities can be unconnected or connected, and the connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0101] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Futuregeneration radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0102] In some embodiments of wireless communication systems, seamless handover between cells is crucial for maintaining high-quality connectivity when users move between different coverage areas. Traditional methods for measuring RSRP (Receiving RSRP) for handover decisions often face significant challenges, including increased measurement overhead and potential delays in detecting the optimal handover opportunity. This is where AI mobility solutions come in, providing a transformative approach to RSRP estimation and handover management.

[0103] A key advantage of AI-driven mobility is its ability to reduce the measurement overhead associated with RSRP estimation. Traditional RSRP measurements involve frequent and resource-intensive signal strength checks, which consume valuable network resources and increase latency. In contrast, AI-driven mobility can minimize the need for continuous measurements by using predictive analytics. AI models can identify patterns and trends in signal behavior, enabling networks to make accurate switching decisions with fewer physical measurements. This not only conserves network resources but also improves overall system efficiency.

[0104] Improving RSRP estimation accuracy through AI mobility directly translates to better handover performance. By predicting signal strength fluctuations and more accurately identifying optimal handover points, AI mobility can significantly reduce the likelihood of connection interruptions and handover failures. This results in a more stable and reliable user experience, especially in high-mobility scenarios such as vehicular communication or congested urban environments.

[0105] Furthermore, AI-powered mobility can dynamically adapt to changing network conditions and user needs. For example, in areas with fluctuating traffic loads or changing environmental factors (such as urban canyons or rural terrain), AI models can adjust their predictions in real time to ensure optimal handover performance. This adaptability ensures that the network remains responsive and efficient under various operating conditions.

[0106] Artificial intelligence mobility represents a significant leap forward in RSRP estimation and handover management. By leveraging the power of artificial intelligence and machine learning, it provides a more efficient, accurate, and adaptive approach to maintaining seamless connectivity. Reduced measurement overhead and enhanced handover performance not only improve user satisfaction but also contribute to increased overall efficiency and scalability of wireless networks. With the ever-growing demand for high-speed, reliable connectivity, artificial intelligence mobility is becoming a crucial solution for modern communication systems.

[0107] To evaluate the mobility performance of artificial intelligence, it is necessary to verify the accuracy of the L3-RSRP predicted by the AI ​​model. This requires defining an accuracy definition and establishing a corresponding method for verifying the predicted RSRP.

[0108] Traditionally, L3-RSRP has been measured, rather than predicted.

[0109] The TE side knows the true value of L3-RSRP and has verified its accuracy in an Additive White Gaussian Noise (AWGN) channel. For AWGN channels, the channel does not change over time, and the transmit power is constant. However, in AI-driven mobility, the channel model changes to a fading channel, which, unlike traditional AWGN channels, is a time-varying channel. This change in the channel model makes it impossible for the TE side to define the true value, and therefore, to determine the accuracy of L3-RSRP.

[0110] To improve the availability and reliability of AI-based mobility management and accurately assess the accuracy of L3-RSRP predictions by AI models, this disclosure provides the following communication method, terminal, first device, system, and storage medium.

[0111] Figure 2 This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 2 As shown, the embodiments of this disclosure relate to a communication method, which includes:

[0112] In step S2101, the first device 102 sends the first instruction information to the terminal 101.

[0113] In some embodiments, terminal 101 receives first instruction information.

[0114] In some embodiments, the first device 102 may be a network device or a test device, and this disclosure does not limit it.

[0115] In some embodiments, the first indication information may be used to indicate a first moment.

[0116] In one example, the first moment may include one or more moments, and this disclosure does not limit the number of moments included in the first moment.

[0117] In one example, for a fading channel, because the channel changes over time, to compare L3-RSRP results, the first device 102 and the terminal 101 should be explicitly aligned for the specific time instance corresponding to the L3-RSRP reported by the terminal 101. Therefore, to ensure accurate synchronization, the first device 102 can align the timing of the L3-RSRP reporting results with that of the terminal 101. Exemplarily, the first device 102 can indicate one or more first moments using first indication information.

[0118] In one example, terminal 101 can determine, based on the first indication information, which moments' L3-RSRP estimates need to be obtained through the AI ​​model.

[0119] In one example, the first indication information can be used to indicate absolute time, such as indicating the specific point in time of the first moment.

[0120] In one example, the first indication information can be used to indicate relative time, such as indicating the time offset of the first moment relative to the current moment.

[0121] In one example, the first indication information may indicate at least one of the following: System Frame Number (SFN), Slot Number, and Symbol Index.

[0122] The above is merely an illustrative example, and this disclosure does not limit the content indicated by the first instruction information.

[0123] In some embodiments, the first device 102 may send a first indication message to the terminal 101 when it is necessary to evaluate the accuracy of the AI ​​model in predicting L3-RSRP.

[0124] In some embodiments, the first device 102 may send first instruction information to the terminal 101 when performing AI-based mobility management.

[0125] In some embodiments, the first device 102 may send first instruction information to the terminal 101 based on a request from the terminal 101.

[0126] In some embodiments, the first device 102 may send first instruction information to the terminal 101 when it is determined that the terminal 101 is in a specific scenario, such as vehicle communication, Internet of Things communication, or a congested urban environment.

[0127] In some embodiments, the first device 102 may send a first indication message to the terminal 101 if it is desired to reduce the possibility of connection interruption and / or handover failure.

[0128] The above is merely an illustrative example, and this disclosure does not limit the timing or conditions for triggering the first device 102 to send the first instruction information to the terminal 101.

[0129] In step S2102, terminal 101 obtains the estimated value.

[0130] In some embodiments, terminal 101 can estimate the L3-RSRP at the first moment by deploying an AI model, thereby obtaining an estimated value.

[0131] In one example, the first moment includes a moment, so terminal 101 can obtain the estimated value of L3-RSRP corresponding to that moment through the AI ​​model, that is, obtain an estimated value.

[0132] In one example, the first moment includes multiple moments, so terminal 101 can obtain the L3-RSRP prediction value corresponding to each of the multiple moments through the AI ​​model, that is, obtain multiple prediction values.

[0133] In one example, the AI ​​model can be used to infer or predict the L3-RSRP of terminal 101 at at least one moment on the fading channel.

[0134] In one example, the input parameters of the AI ​​model may include at least one of the following: the L3-RSRP measurement at the second time step; the type of terminal 101; and the channel quality parameters of the fading channel.

[0135] The second moment can include historical moments and / or the current moment.

[0136] Among them, the type of terminal 101 can be IoT device, passive IoT device, ordinary terminal, etc.

[0137] Among them, the channel quality parameters of the fading channel may include, but are not limited to, Channel Quality Indicator (CQI), Signal to Interference plus Noise Ratio (SINR), Block Error Rate (BLER), etc.

[0138] In one example, the output of the AI ​​model can be a prediction of the L3-RSRP at the first time step.

[0139] In step S2103, terminal 101 sends the estimated value to first device 102.

[0140] In some embodiments, the first device 102 receives an estimated value.

[0141] In one example, the first moment includes a moment when terminal 101 sends an estimated value to first device 102.

[0142] In one example, the first moment includes multiple moments, and terminal 101 sends multiple estimated values ​​to first device 102.

[0143] In step S2104, terminal 101 sends first information to first device 102.

[0144] In some embodiments, the first device 102 receives first information.

[0145] In some embodiments, the first information may be used by the first device 102 to determine the truth value.

[0146] Here, the ground truth is the ground truth of L3-RSRP at the first time step.

[0147] The first moment includes a moment, so the terminal 101 can determine the truth value of L3-RSRP at that moment, that is, determine a truth value.

[0148] The first moment includes multiple moments, so the terminal 101 can determine the truth value of L3-RSRP at each moment, that is, determine multiple truth values.

[0149] The name of the truth value is not limited and can be interchanged with "true value", "actual value", etc.

[0150] In some embodiments, the first information may include, but is not limited to, at least one of the following: the layer 3 filtering method used by terminal 101; the number of layer 1 samples included in each layer 1 filtering window; the first beamforming gain value; and the second value.

[0151] In one example, the layer 3 filtering method used by terminal 101 may include, but is not limited to, non-sliding filtering and sliding filtering.

[0152] For example, non-sliding filtering methods include Figure 4A As shown, every 5 Layer 1 (L1) samples can generate one L3-RSRP filter value.

[0153] For example, sliding filtering methods include... Figure 4B As shown, each new L1 sample generates one L3-RSRP filter value.

[0154] For example, the difference between non-sliding filtering and sliding filtering is that for a non-sliding window of L1 / L3 filtering, an L3-RSRP is generated for every 5 L1 samples. For a sliding window of L1 / L3 filtering, an L3RSRP is generated for every 1 L1 sample.

[0155] It is understandable that if the first device 102 does not know the Layer 3 filtering method used by the terminal 101, the first device 102 cannot calculate the true value of L3-RSRP. Therefore, the first information may include the L3 filtering method used by the terminal 101.

[0156] The name of the layer 3 filtering method is not limited and can be interchanged with "layer 1 filtering method" or "layer 1 and layer 3 filtering method".

[0157] In one example, if the first device 102 is a TE, it can set the layer 3 filtering factor to 0. In this case, the first information sent by the terminal 101 to the first device 102 may not include the layer 3 filtering method used by the terminal 101.

[0158] In one example, if the first device 102 is a network device, it can also set the layer 3 filtering factor to 0. Similarly, the first information sent by the terminal 101 to the first device 102 may not include the layer 3 filtering method used by the terminal 101.

[0159] In one example, if the first device 102 does not consider the layer 3 filtering factor, the first information sent by the terminal 101 to the first device 102 may not include the layer 3 filtering method used by the terminal 101.

[0160] The above is merely an illustrative example, and this disclosure does not limit whether the first information includes the layer 3 filtering method used by terminal 101.

[0161] In one example, some more capable terminals 101 can use fewer samples to predict L3-RSRP. For example, the number of Layer 1 samples used can be less than 5, say 3, so that the filtered L1-RSRP can be sent to the higher layers faster.

[0162] Accordingly, if the first device 102 is to calculate the true value of L3-RSRP, it should also be calculated based on the average value of the three Layer 1 samples.

[0163] Therefore, terminal 101 can send first information to first device 102, which may include the number of layer 1 samples included in each layer 1 filtering window; otherwise, the true value calculated by first device 102 will be inaccurate.

[0164] In one example, when the first device 102 calculates the true value, the beamforming gain value at the terminal 101 also needs to be considered. Therefore, in this embodiment of the disclosure, the terminal 101 can send first information to the first device 102, which may include a first beamforming gain value or a second value.

[0165] For example, the first beamforming gain value is the beamforming gain value corresponding to the received (Rx) beam determined by the terminal 101.

[0166] The first beamforming gain value can be used by the first device 102 to determine the second beamforming gain value of the terminal 101.

[0167] For example, the second value is the received power value of terminal 101, which corresponds to the first value, which is the transmitted power value of first device 102.

[0168] The second value can be determined by the first device 102 based on a predefined method and / or based on the implementation of the first device 102 itself. When the transmit power value of the first device 102 is the first value, the terminal 101 determines the receive power value at this time, i.e., the second value, and provides the second value to the first device 102.

[0169] The second value and the first value can be used by the first device 102 to calculate the second beamforming gain value of the terminal 101.

[0170] The above is merely an illustrative example, and this disclosure does not limit the content of the first information.

[0171] In some embodiments, when the terminal 101 determines that the true value is calculated by the first device 102, it sends first information to the first device 102.

[0172] In some embodiments, terminal 101 may send first information to first device 102 based on a request from first device 102.

[0173] In some embodiments, terminal 101 may send first information to first device 102 when the battery is low.

[0174] In some embodiments, terminal 101 may send first information to first device 102 in order to reduce the resource consumption of terminal 101.

[0175] The above is merely an illustrative example, and this disclosure does not limit the timing or conditions under which the terminal 101 sends the first information to the first device 102.

[0176] In step S2105, terminal 101 sends the truth value to first device 102.

[0177] In some embodiments, the first device 102 receives the truth value.

[0178] In one example, the first moment includes a moment when terminal 101 sends a truth value to first device 102.

[0179] In one example, the first moment includes multiple moments, and terminal 101 sends multiple truth values ​​to first device 102.

[0180] In some embodiments, terminal 101 measures the L3-RSRP value corresponding to the first moment, obtains the measured value, determines the measured value as the true value, and sends the true value to first device 102.

[0181] In one example, terminal 101 measures the L1-RSRP within a Layer 1 filter window corresponding to each time point included in the first time point, obtaining at least one Layer 1 sample included in the Layer 1 filter window. Based on the measured at least one Layer 1 sample included in the Layer 1 filter window, the L3-RSRP value corresponding to each Layer 1 sample is calculated, and the average value of the L3-RSRP values ​​within the Layer 1 filter window is taken to obtain the measurement value at each time point.

[0182] In some embodiments, steps S2104 and S2105 may be performed selectively.

[0183] Step S2106: The first device 102 determines the true value.

[0184] In some embodiments, the first device 102 may calculate the truth value based on the first information.

[0185] In one example, the first device 102 can determine the layer 3 filtering factor and / or the specific layer 1 samples to be selected based on the layer 3 filtering method used by the terminal 101, thereby calculating the true value.

[0186] In one example, the first device 102 can determine the number of layer 1 samples to be selected based on the number of layer 1 samples included in each layer 1 filtering window, thereby calculating the true value.

[0187] In one example, the first device 102 may determine the second beamforming gain value of the terminal 101 based on either the first or the second beamforming gain value, thereby calculating the true value.

[0188] In one example, the L3-RSRP after L3 filtering will depend on the previous filtering result and the new L3-RSRP measurement. Assuming two L3-RSRP samples are used to derive the filtered L3-RSRP, as follows... Figure 4C As shown.

[0189] Different L3 filtering methods affect the true value of the L3-RSRP calculated by the first device 102. For example, suppose the L3-RSRP corresponds to time T (i.e., the first moment is time T). To derive the true value of the L3-RSRP at time T, for non-slipping filtering, 10 L1 samples are used to generate the true value of the L3-RSRP at time T. For sliding filtering, 6 L1 samples are used to generate the true value of the L3-RSRP at time T. Therefore, the true value of L3-RSRP at time T is different in the sliding and non-slipping cases.

[0190] To ensure that the first device 102 accurately calculates the true value of L3-RSRP, the first device 102 can determine which layer 1 samples are needed to calculate the true value of L3-RSRP based on the layer 3 filtering method used by the terminal 101. For example, when the terminal 101 uses a sliding filter, the first device 102 will select the last 6 samples and average them to obtain the true value of L3-RSRP. As another example, when the terminal 101 uses a non-sliding filter, the first device 102 will select the last 10 samples and average them to obtain the true value of L3-RSRP.

[0191] In one example, the first device 102 can calculate L3-RSRP using Formula 1:

[0192] F n = (1-a)×F n-1 +a×M n Formula 1

[0193] Where a is the layer 3 filter factor, F n It is the L3-RSRP (corresponding to a layer 1 sample) that needs to be calculated, F n-1 It is the L3-RSRP obtained from the previous calculation (corresponding to the previous layer 1 sample), M n It is the Layer 1 measurement value received by the first device 101, namely L1-RSRP.

[0194] The first device 102 calculates n L3-RSRPs based on Formula 1, and then averages these n L3-RSRPs to obtain the true value of the L3-RSRP at the first time step. Here, n is determined based on the number of Layer 1 samples included in each Layer 1 filtering window. For example, if each Layer 1 filtering window includes 5 Layer 1 samples, n is 6 in the sliding filter method and 10 in the non-sliding filter method. As another example, if each Layer 1 filtering window includes 3 Layer 1 samples, n is 4 in the sliding filter method and 6 in the non-sliding filter method.

[0195] In one example, the first device 102 can be set to a = 0, at which point the L3-RSRP is equal to the L1-RSRP sample value (or layer 1 measurement) at that time, and the true value of the L3-RSRP at the first moment is equal to the average of n L1-RSRP sample values. Here, n is determined based on the number of layer 1 samples included in each layer 1 filtering window.

[0196] In one example, the first device 102 can determine the second beamforming gain value of the terminal 101 based on the first information, and adjust the true value based on the second beamforming gain value to improve the accuracy of the AI ​​model's prediction of L3-RSRP.

[0197] For example, the first information includes a first beamforming gain value, which is the beamforming gain value corresponding to the Rx beam determined by the terminal. The first device 102 can directly determine the first beamforming gain value as the second beamforming gain value.

[0198] For example, the first information includes a first beamforming gain value. The first device 102 can determine a first offset range based on a predefined method, such as [Gmin, Gmax]. The first device 102 can increase or decrease G' based on the first beamforming gain value to obtain a second beamforming gain value, wherein the range of values ​​for G' is the first offset range.

[0199] For example, the first information includes a second value, and the first device 102 can calculate a second beamforming gain value based on the second value and the first value. The second beamforming gain value can be equal to the ratio of the second value to the first value.

[0200] The above is merely an illustrative example, and this disclosure does not limit the method by which the first device 102 determines the second beamforming gain value.

[0201] For example, the first device 102 may consider the second beamforming gain value to adjust the above true value, and the adjustment method is not limited in this disclosure.

[0202] In some embodiments, the first device 102 may receive the truth value sent by the terminal 101.

[0203] In one example, the first device 102 may receive one or more truth values. In step S2107, the first device 102 determines the accuracy of the AI ​​model's prediction of L3-RSRP.

[0204] In some embodiments, the first device 102 can determine the accuracy of the AI ​​model's prediction of L3-RSRP based on the estimated value and the true value.

[0205] In one example, this precision can be calculated based on Equation 2:

[0206] Accuracy = Estimated Value - True Value (Formula 2)

[0207] In calculating the accuracy, the difference between the predicted value and the true value of L3-RSRP at the same time can be calculated to obtain the accuracy at that time.

[0208] For example, if the first moment includes time T, then terminal 101 can calculate the difference between the estimated value and the true value of L3-RSRP at time T, thereby determining the accuracy corresponding to time T.

[0209] For example, if the first time step includes multiple time steps, then the final accuracy of the AI ​​model predicting L3-RSRP can be the average, maximum, or minimum accuracy corresponding to the multiple time steps, and this disclosure does not limit it in this way.

[0210] In some embodiments, the first device 102 may instruct the terminal 101 to retrain the AI ​​model if the accuracy is determined to be low.

[0211] In some embodiments, when the first device 102 is a network device, the terminal 101 can be used for mobility management by selecting the predicted value of the AI ​​model or the measurement value reported by the terminal 101 based on the determined accuracy.

[0212] For example, if the determined accuracy exceeds a threshold, the first device 102 determines that the AI ​​model's prediction of L3-RSRP is highly accurate, and can perform mobility management on the terminal 101 based on the AI ​​model's prediction.

[0213] For example, if the determined accuracy does not exceed the threshold, the first device 102 determines that the AI ​​model's prediction of L3-RSRP is low and can perform mobility management on the terminal 101 based on the L3-RSRP measurement value reported by the terminal 101.

[0214] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0215] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0216] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0217] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0218] In some embodiments, the communication method involved in this disclosure may include at least one of steps S2101 to S2107. For example, step S2101 may be implemented as a standalone embodiment, step S2102 may be implemented as a standalone embodiment, step S2101+S2102 may be implemented as a standalone embodiment, step S2103 may be implemented as a standalone embodiment, step S2101+S2102+S2103 may be implemented as a standalone embodiment, step S2104 may be implemented as a standalone embodiment, step S2105 may be implemented as a standalone embodiment, and steps S2101 to S2104 may be implemented as... As an independent embodiment, steps S2101+S2102+S2103+S2105 can be implemented as an independent embodiment, step S2106 can be implemented as an independent embodiment, steps S2104+S2106 can be implemented as an independent embodiment, steps S2105+S2106 can be implemented as an independent embodiment, step S2107 can be implemented as an independent embodiment, and steps S2101 to S2107 can be implemented as independent embodiments, but are not limited thereto.

[0219] In some embodiments, steps S2101 to S2107 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0220] In some embodiments, the execution order of steps S2101 to S2107 is not limited.

[0221] The above embodiments improve the integration of AI technology and communication mechanisms, enhance the availability and reliability of AI-based mobility management, and help improve the efficiency, performance, and scalability of wireless networks.

[0222] Figure 3A This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 3A As shown, this disclosure relates to a communication method, which can be executed by terminal 101. The method includes:

[0223] Step S3101: Determine the estimated value.

[0224] In some embodiments, terminal 101 can estimate the L3-RSRP at the first moment by deploying an AI model, thereby obtaining an estimated value.

[0225] In one example, the first moment includes a moment, so terminal 101 can obtain the estimated value of L3-RSRP corresponding to that moment through the AI ​​model, that is, obtain an estimated value.

[0226] In one example, the first moment includes multiple moments, so terminal 101 can obtain the L3-RSRP prediction value corresponding to each of the multiple moments through the AI ​​model, that is, obtain multiple prediction values.

[0227] In one example, the AI ​​model can be used to infer or predict the L3-RSRP of terminal 101 at different times on the fading channel.

[0228] In one example, the input parameters of the AI ​​model may include at least one of the following: the L3-RSRP measurement at the second time step; the type of terminal 101; and the channel quality parameters of the fading channel.

[0229] The second moment can include historical moments and / or the current moment.

[0230] Among them, the type of terminal 101 can be IoT device, passive IoT device, ordinary terminal, etc.

[0231] Among them, the channel quality parameters of the fading channel may include, but are not limited to, Channel Quality Indicator (CQI), Signal to Interference plus Noise Ratio (SINR), Block Error Rate (BLER), etc.

[0232] In one example, the output of the AI ​​model can be a prediction of the L3-RSRP at the first time step.

[0233] Step S3102: Send the estimated value.

[0234] In some embodiments, terminal 101 sends an estimated value to first device 102.

[0235] In some embodiments, the first device 102 receives an estimated value.

[0236] In one example, the first moment includes a moment when terminal 101 sends an estimated value to first device 102.

[0237] In one example, the first moment includes multiple moments, and terminal 101 sends multiple estimated values ​​to first device 102.

[0238] In some embodiments, steps S3101 to S3102 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0239] In some embodiments, the execution order of steps S3101 to S3102 is not limited.

[0240] The above embodiments improve the integration of AI technology and communication mechanisms, enhance the availability and reliability of AI-based mobility management, and help improve the efficiency, performance, and scalability of wireless networks.

[0241] Figure 3B This is an interactive schematic diagram illustrating a communication method according to an embodiment of this disclosure. For example... Figure 3B As shown, this disclosure relates to a communication method, which can be executed by a network device 102. The method includes:

[0242] Step S3201: Obtain the estimated value.

[0243] In some embodiments, the first device 102 obtains an estimated value from the terminal 101.

[0244] In some embodiments, terminal 101 can estimate the L3-RSRP at the first moment by deploying an AI model, thereby obtaining an estimated value.

[0245] In one example, the first moment includes a moment when the first device 102 receives an estimate from the terminal 101.

[0246] In one example, if the first moment includes multiple moments, then the first device 102 receives multiple estimates from the terminal 101.

[0247] In one example, the AI ​​model can be used to infer or predict the L3-RSRP of terminal 101 at different times on the fading channel.

[0248] In one example, the input parameters of the AI ​​model may include at least one of the following: the L3-RSRP measurement at the second time step; the type of terminal 101; and the channel quality parameters of the fading channel.

[0249] The second moment can include historical moments and / or the current moment.

[0250] Among them, the type of terminal 101 can be IoT device, passive IoT device, ordinary terminal, etc.

[0251] Among them, the channel quality parameters of the fading channel may include, but are not limited to, Channel Quality Indicator (CQI), Signal to Interference plus Noise Ratio (SINR), Block Error Rate (BLER), etc.

[0252] In one example, the output of the AI ​​model can be a prediction of the L3-RSRP at the first time step.

[0253] In some embodiments, terminal 101 sends an estimated value to first device 102.

[0254] In some embodiments, the first device 102 receives an estimated value.

[0255] Step S3202: Determine the truth value.

[0256] In some embodiments, the first device 102 may calculate the truth value based on the first information.

[0257] In one example, the first device 102 can determine the layer 3 filtering factor and / or the specific layer 1 samples to be selected based on the layer 3 filtering method used by the terminal 101, thereby calculating the true value.

[0258] In one example, the first device 102 can determine the number of layer 1 samples to be selected based on the number of layer 1 samples included in each layer 1 filtering window, thereby calculating the true value.

[0259] In one example, the first device 102 may determine the second beamforming gain value of the terminal 101 based on either the first or the second beamforming gain value, thereby calculating the true value.

[0260] In one example, the L3-RSRP after L3 filtering will depend on the previous filtering result and the new L3-RSRP measurement. Assuming two L3-RSRP samples are used to derive the filtered L3-RSRP, as follows... Figure 4C As shown.

[0261] Different L3 filtering methods affect the true value of the L3-RSRP calculated by the first device 102. For example, suppose the L3-RSRP corresponds to time T (i.e., the first moment is time T). To derive the true value of the L3-RSRP at time T, for non-slipping filtering, 10 L1 samples are used to generate the true value of the L3-RSRP at time T. For sliding filtering, 6 L1 samples are used to generate the true value of the L3-RSRP at time T. Therefore, the true value of L3-RSRP at time T is different in the sliding and non-slipping cases.

[0262] To ensure that the first device 102 accurately calculates the true value of L3-RSRP, the first device 102 can determine which layer 1 samples are needed to calculate the true value of L3-RSRP based on the layer 3 filtering method used by the terminal 101. For example, when the terminal 101 uses a sliding filter, the first device 102 will select the last 6 samples and average them to obtain the true value of L3-RSRP. As another example, when the terminal 101 uses a non-sliding filter, the first device 102 will select the last 10 samples and average them to obtain the true value of L3-RSRP.

[0263] In one example, the first device 102 can calculate L3-RSRP using Formula 1:

[0264] F n = (1-a)×F n-1 +a×M n Formula 1

[0265] Where a is the layer 3 filter factor, F n It is the L3-RSRP (corresponding to a layer 1 sample) that needs to be calculated, F n-1 It is the L3-RSRP obtained from the previous calculation (corresponding to the previous layer 1 sample), M n It is the Layer 1 measurement value received by the first device 101, namely L1-RSRP.

[0266] The first device 102 calculates n L3-RSRPs based on Formula 1, and then averages these n L3-RSRPs to obtain the true value of the L3-RSRP at the first time step. Here, n is determined based on the number of Layer 1 samples included in each Layer 1 filtering window. For example, if each Layer 1 filtering window includes 5 Layer 1 samples, n is 6 in the sliding filter method and 10 in the non-sliding filter method. As another example, if each Layer 1 filtering window includes 3 Layer 1 samples, n is 4 in the sliding filter method and 6 in the non-sliding filter method.

[0267] In one example, the first device 102 can be set to a = 0, at which point the L3-RSRP is equal to the L1-RSRP sample value (or layer 1 measurement) at that time, and the true value of the L3-RSRP at the first moment is equal to the average of n L1-RSRP sample values. Here, n is determined based on the number of layer 1 samples included in each layer 1 filtering window.

[0268] In one example, the first device 102 can determine the second beamforming gain value of the terminal 101 based on the first information, and adjust the true value based on the second beamforming gain value to improve the accuracy of the AI ​​model's prediction of L3-RSRP.

[0269] For example, the first information includes a first beamforming gain value, which is the beamforming gain value corresponding to the Rx beam determined by the terminal. The first device 102 can directly determine the first beamforming gain value as the second beamforming gain value.

[0270] For example, the first information includes a first beamforming gain value. The first device 102 can determine a first offset range based on a predefined method, such as [Gmin, Gmax]. The first device 102 can increase or decrease G' based on the first beamforming gain value to obtain a second beamforming gain value, wherein the range of values ​​for G' is the first offset range.

[0271] For example, the first information includes a second value, and the first device 102 can calculate a second beamforming gain value based on the second value and the first value. The second beamforming gain value can be equal to the ratio of the second value to the first value.

[0272] The above is merely an illustrative example, and this disclosure does not limit the method by which the first device 102 determines the second beamforming gain value.

[0273] For example, the first device 102 may consider the second beamforming gain value to adjust the above true value, and the adjustment method is not limited in this disclosure.

[0274] In some embodiments, the first device 102 may receive the truth value sent by the terminal 101.

[0275] In one example, the number of truth values ​​received by the first device 102 can be one or more.

[0276] Step S3203: Determine the accuracy of the AI ​​model's prediction of L3-RSRP.

[0277] In some embodiments, the first device 102 can determine the accuracy of the AI ​​model's prediction of L3-RSRP based on the estimated value and the true value.

[0278] In one example, this precision can be calculated based on Equation 2:

[0279] Accuracy = Estimated Value - True Value (Formula 2)

[0280] In calculating the accuracy, the difference between the predicted value and the true value of L3-RSRP at the same time can be calculated to obtain the accuracy at that time.

[0281] For example, if the first moment includes time T, then terminal 101 can calculate the difference between the estimated value and the true value of L3-RSRP at time T, thereby determining the accuracy corresponding to time T.

[0282] For example, if the first time point includes multiple time points, the final accuracy of the AI ​​model predicting L3-RSRP can be the average, maximum, or minimum accuracy corresponding to each of the multiple time points, and this disclosure does not limit this. In some embodiments, the first device 102 can instruct the terminal 101 to retrain the AI ​​model if the determined accuracy is low.

[0283] In some embodiments, when the first device 102 is a network device, the terminal 101 can be used for mobility management by selecting the predicted value of the AI ​​model or the measurement value reported by the terminal 101 based on the determined accuracy.

[0284] For example, if the determined accuracy exceeds a threshold, the first device 102 determines that the AI ​​model's prediction of L3-RSRP is highly accurate, and can perform mobility management on the terminal 101 based on the AI ​​model's prediction.

[0285] For example, if the determined accuracy does not exceed the threshold, the first device 102 determines that the AI ​​model's prediction of L3-RSRP is low and can perform mobility management on the terminal 101 based on the L3-RSRP measurement value reported by the terminal 101.

[0286] In some embodiments, steps S3201 to S3203 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0287] In some embodiments, the execution order of steps S3201 to S3203 is not limited.

[0288] The above embodiments improve the integration of AI technology and communication mechanisms, enhance the availability and reliability of AI-based mobility management, and help improve the efficiency, performance, and scalability of wireless networks.

[0289] The above process is further illustrated with examples below.

[0290] For AI-driven mobility, the performance metrics for L3-RSRP accuracy are:

[0291] • Absolute L3 prediction RSRP accuracy = Reported prediction L3 - RSR - L3 - RSRP true value

[0292] For the ground truth value of L3-RSRP, there are two possible definitions:

[0293] Option 1: The truth value of L3-RSRP is calculated by TE.

[0294] - Option 2: Terminal reports the truth value of L3-RSRP

[0295] For option 1, the method is similar to the traditional method. However, there is a key difference in the channel model used for L3-RSRP accuracy testing. In traditional testing, an AWGN channel is used, which means there are no channel fluctuations in the time domain. Therefore, TE can always determine the true value of L3-RSRP.

[0296] In contrast, the AI ​​mobility testing metric introduces a fading channel. This channel introduces time-domain fluctuations, making the calculation of the ideal L3-RSRP more challenging. If TE wants to know and be able to calculate the ideal L3-RSRP, it needs to solve several problems:

[0297] - Question 1: L3-RSRP time instance alignment;

[0298] - Question 2: UE L1 / L3 filtering method;

[0299] - Question 3: Number of samples filtered by terminal L1;

[0300] - Question 4: Rx beamforming gain of FR2.

[0301] Regarding question 1:

[0302] For fading channels, because the channel changes over time, to compare L3-RSRP results, taking the TE as the first device as an example, the TE and the UE must explicitly align the specific time instance corresponding to the reported L3-RSRP. The TE can identify the truth value of L3-RSRP in the time domain. Then, the TE should indicate the detailed time instance of the L3-RSRP result.

[0303] Example 1: Time alignment of L3-RSRP reporting results between TE and UE

[0304] To ensure accurate synchronization, the TE needs to align the timing of the L3-RSRP report results with the UE. The TE should specify the specific time when the UE should report the L3-RSRP value. One possible method is as follows: the TE instructs the UE to report the L3-RSRP value corresponding to a specific SFN (System Frame Number), slot number, and symbol index.

[0305] Regarding question 2:

[0306] L1 / L3 non-sliding filtering methods, for example Figure 4A As shown, the sliding filter method is, for example... Figure 4B As shown.

[0307] The key difference between non-sliding filtering and sliding filtering is:

[0308] - For L1 / L3 filtering non-sliding windows, an L3 RSRP will be generated for every 5 L1 samples.

[0309] - For an L1 / L3 filtering sliding window, each L1 sample will generate an L3 RSRP.

[0310] If the TE does not know the L1 / L3 filtering method, it will not know how to calculate the ideal L3-RSRP. Therefore, the UE needs to send an L1 / L3 filtering method instruction to the TE.

[0311] The L3 filter formula is shown in Formula 1.

[0312] F n = (1-a)×F n-1 +a×M n Formula 1

[0313] Among them, F n It is used to evaluate report conditions or to update and filter measurement results for measurement reports. n-1 This represents the previous filtered measurement results, with the initial value F0 set to the first measurement result M1 received from the physical layer. Mn is the latest measurement result received from the physical layer. a is the layer 3 filter coefficient.

[0314] The L3-RSRP after L3 filtering will depend on the previous filtering result and the new L3-RSRP measurement. For simplicity, let's assume that two L3-RSRP samples are used to derive the filtered L3-RSRP, such as... Figure 4C As shown.

[0315] Different L1 / L3 filtering methods affect the ideal L3-RSRP calculation. For example, suppose the L3-RSRP corresponds to time instance T. To derive the ideal L3-RSRP at time T, for non-sliding filtering, 10 L1 samples are used to generate the true value of the L3-RSRP at time T. However, for sliding filtering, only 6 L1 samples are used to generate the L3-RSRP at time T. Therefore, the true value of the L3-RSRP at time T is different in the sliding and non-sliding cases.

[0316] In order for the TE side to calculate the true value of L3-RSRP, the L1 / L3 filtering method needs to be indicated to the TE.

[0317] Example 2: If the L3 filtering factor α is to be considered, a signal needs to be designed for this function. The UE needs to report the L1 / L3 filtering method, such as sliding or non-sliding, to the TE.

[0318] Based on the L3-RSRP instance time and the UE's L1 / L3 filtering method, the TE can determine which samples are needed to calculate the L3-RSRP. For example, when using a sliding method, the TE will select the last 6 samples and average them to obtain the result.

[0319] Example 3: When defining a test method to verify the prediction performance of L3-RSRP, the L3 filter factor is set to 0, and the UE does not need to report the L1 / L3 filtering method to the TE.

[0320] Another option is to disregard the L3 filter factor a in L3-RSRP.

[0321] Regardless of the method used, L3-RSRP is equal to the average of M instantaneous L1-RSRP samples.

[0322] Regarding question 3:

[0323] In the current measurement cycle requirements, five samples are defined for L1 filtering. In reality, some advanced UEs can achieve RSRP accuracy with fewer samples, i.e., three samples, and can send the filtered L1-RSRP to higher layers much faster. If this is the case, the ideal L3-RSRP would be calculated based on the average of three samples instead of five. In the current AI mobility studies in RAN2, if they consider L3-RSRP to predict L3-RSRP, they have no limit on the number of samples for L1 filtering; it depends on the UE implementation.

[0324] If L3-RSRP can be calculated on the TE side, it means the TE needs to know how many L1 samples will be used to generate the ideal L3-RSRP. This will impose significant limitations on the UE implementation. It means the UE must average based on 5 samples; otherwise, a mismatch will occur.

[0325] Example 4: The UE needs to report the number of L1 filtered samples to the TE via signaling. For example, the TE can send a command to the UE to report the number of L1 filtered samples. The UE can then provide feedback.

[0326] Example 5: For FR2, since the TE does not know the UE's Rx beamforming gain, there are three options for the TE to derive the Rx beamforming gain:

[0327] 1. Set the predefined range of Rx beamforming gain from Gmin to Gmax.

[0328] 2. The UE reports the RX beamforming gain to the TE.

[0329] 3. The TE sends Tx power with a predefined value to the UE, the UE reports the received power to the TE, and the TE derives the Rx beamforming gain.

[0330] After obtaining all the necessary information, TE can calculate the true value of L3-RSRP corresponding to time T.

[0331] Example 6: Under high signal-to-noise ratio conditions, the UE measures the L1-RRP of multiple reference signals at different times and combines these measurement results to calculate the ideal L3-RSRP. Then, it reports the L3-RSRP value as the true value.

[0332] This disclosure also proposes an apparatus for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by each node (e.g., a terminal, a network device) in any of the above methods.

[0333] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0334] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0335] Figure 5A This is a schematic diagram of the structure of a passive Internet of Things (IoT) device proposed in an embodiment of this disclosure. Figure 5A As shown, the passive IoT device 5100 may include at least one of a processing module 5101 and a transceiver module 5102.

[0336] In some embodiments, the processing module 5101 is configured to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment using an artificial intelligence (AI) model, and obtain an estimated value.

[0337] In some embodiments, the transceiver module 5102 is configured to send the estimated value to the first device.

[0338] In some embodiments, the processing module 5101 described above is used to execute at least one of the other steps (such as step S2102, but not limited thereto) executed by the terminal 5100 in any of the above methods, which will not be described in detail here.

[0339] In some embodiments, the transceiver module 5102 is used to perform at least one of the communication steps such as sending and / or receiving performed by the terminal device 5100 in any of the above methods (e.g., steps S2101, S2103, S2104, S2105, but not limited thereto), which will not be described in detail here.

[0340] Figure 5B This is a schematic diagram of the structure of the first device proposed in an embodiment of this disclosure. Figure 5B As shown, the first device 5200 may include: a transceiver module 5201 and a processing module 5202.

[0341] In some embodiments, the transceiver module 5201 is configured to receive an estimated value sent by the terminal, the estimated value being obtained by the terminal through an artificial intelligence (AI) model to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at a first moment.

[0342] In some embodiments, the processing module 5202 is configured to determine the true value, which is the true value of L3-RSRP at the first time step; and to determine the accuracy of the AI ​​model in predicting L3-RSRP based on the predicted value and the true value.

[0343] In some embodiments, the transceiver module 5201 is used to perform at least one of the communication steps such as sending and / or receiving performed by the first device 5200 in any of the above methods (e.g., steps S2101, S2103, S2104, S2105, but not limited thereto), which will not be described in detail here.

[0344] In some embodiments, the processing module 5202 is used to execute at least one of the other steps (such as step S2106, step S2107, but not limited thereto) executed by the first device 5200 in any of the above methods, which will not be described in detail here.

[0345] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0346] Figure 6A This is a schematic diagram of the structure of the communication device 6100 proposed in this embodiment. The communication device 6100 can be a device (e.g., a terminal, a first device), or a chip, chip system, or processor that supports the device in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0347] like Figure 6AAs shown, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 can be used to execute any of the above methods. Optionally, one or more processors 6101 can be used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0348] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2103, S2104, S2105, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps S2102, S2106, S2107, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0349] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Optionally, all or part of the memories 6103 may be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuits 6104 are connected to the memories 6103 and can be used to receive data from the memories 6103 or other devices, and to send data to the memories 6103 or other devices. For example, the interface circuits 6104 can read data stored in the memories 6103 and send that data to the processor 6101.

[0350] The communication device 6100 described in the above embodiments may be a network device, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may vary. Figure 6AThe limitations. Communication equipment can be a standalone device or part of a larger device. For example, communication equipment can be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally including storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0351] Figure 6B This is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to... Figure 6B The diagram shown is a schematic representation of the structure of chip 6200, but it is not limited to this.

[0352] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0353] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data. Optionally, all or part of the memories 6203 may be located outside chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data from memory 6203 or other devices, and interface circuit 6202 can be used to send data to memory 6203 or other devices. For example, interface circuit 6202 can read data stored in memory 6203 and send the data to processor 6201.

[0354] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101, S2103, S2104, and S2105, but not limited thereto). For example, the interface circuit 6202 performing the communication steps such as sending and / or receiving in the above method means that the interface circuit 6202 performs data interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps S2102, S2106, and S2107, but not limited thereto).

[0355] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0356] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0357] This disclosure also provides a program product that, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0358] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0359] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A communication method, characterized in that, The method is executed by a terminal, and the method includes: Using an artificial intelligence (AI) model, the L3-RSRP (L3 Reference Signal Received Power) at the first moment is estimated, and the estimated value is obtained. The estimated value is sent to the first device.

2. The method according to claim 1, characterized in that, The estimated value and the true value are used by the first device to determine the accuracy of the AI ​​model's prediction of L3-RSRP, and the true value is the true value of L3-RSRP at the first time point.

3. The method according to claim 2, characterized in that, The method further includes: Send first information to the first device; wherein the first information is used by the first device to determine the truth value.

4. The method according to claim 3, characterized in that, The first information includes at least one of the following: The terminal uses a layer 3 filtering method; The number of Layer 1 samples included in each Layer 1 filtering window; The first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal. The second value is the received power value of the terminal, which corresponds to the first value, which is the transmitted power value of the first device.

5. The method according to claim 2, characterized in that, The method further includes: The L3-RSRP value corresponding to the first time point is measured to obtain the measured value; The measured value is determined as the true value; Send the truth value to the first device.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Receive first indication information sent by the first device; wherein the first indication information is used to indicate the first moment.

7. A communication method, characterized in that, The method is performed by a first device, and the method includes: The estimated value sent by the receiving terminal is obtained by the terminal through an artificial intelligence (AI) model to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment. Determine the truth value, which is the truth value of L3-RSRP at the first time step; Based on the estimated value and the true value, the accuracy of the AI ​​model in predicting L3-RSRP is determined.

8. The method according to claim 7, characterized in that, The method further includes: The device receives first information sent by the terminal; wherein the first information is used by the first device to determine the truth value. Determining the truth value includes: Based on the first information, the truth value is calculated.

9. The method according to claim 8, characterized in that, The first information includes at least one of the following: The terminal uses a layer 3 filtering method; The number of Layer 1 samples included in each Layer 1 filtering window; The first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal. The second value is the received power value of the terminal, which corresponds to the first value, which is the transmitted power value of the first device.

10. The method according to claim 8 or 9, characterized in that, The method further includes: Set the layer 3 filter factor to 0; It is determined that the first information does not include the layer 3 filtering method used by the terminal.

11. The method according to any one of claims 8-10, characterized in that, The method further includes any one of the following: Based on the first beamforming gain value included in the first information, the second beamforming gain value of the terminal is determined, wherein the first beamforming gain value is the beamforming gain value corresponding to the Rx beam determined by the terminal. Based on the first beamforming gain value and the first offset range included in the first information, the second beamforming gain value of the terminal is determined, wherein the first beamforming gain value is the beamforming gain value corresponding to the received Rx beam determined by the terminal. Based on the second value and the first value included in the first information, a second beamforming gain value of the terminal is determined; wherein, the second value is the received power value of the terminal, the second value corresponds to the first value, and the first value is the transmitted power value of the first device.

12. The method according to claim 7, characterized in that, The method further includes: Receive the truth value sent by the terminal.

13. The method according to any one of claims 7-12, characterized in that, The method further includes: Send a first indication message to the first device; wherein the first indication message is used to indicate the first moment.

14. A terminal, characterized in that, include: The processing module is configured to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment using an artificial intelligence (AI) model, and obtain the estimated value. The transceiver module is configured to send the estimated value to the first device.

15. A first device, characterized in that, include: The transceiver module is configured to receive an estimated value sent by the terminal, which is obtained by the terminal through an artificial intelligence (AI) model to estimate the Layer 3 Reference Signal Received Power (L3-RSRP) at the first moment. The processing module is configured to determine the truth value, which is the truth value of L3-RSRP at the first time step; The processing module is further configured to determine the accuracy of the AI ​​model's prediction of L3-RSRP based on the estimated value and the true value.

16. A terminal, characterized in that, include: One or more processors; The processor is used to execute the method according to any one of claims 1-6.

17. A first device, characterized in that, include: One or more processors; The processor is used to execute the communication method according to any one of claims 7-12.

18. A communication system, characterized in that, include: A terminal configured to implement the communication method according to any one of claims 1-6; A first device is configured to implement the communication method according to any one of claims 7-12.

19. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the communication method as described in any one of claims 1-6 or 7-12.

20. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program is used to implement the communication method according to any one of claims 1-6 or 7-12.

Images