Artificial intelligence (ai) related signaling flow on backhaul interface

Abstract

This patent document describes, among other things, techniques and apparatuses for providing artificial intelligence to improve wireless network efficiency and performance. In an aspect, a method of wireless communication is disclosed. The method includes transmitting, from a first network node to a second network node, a first network control message requesting initiation of an artificial intelligence process, the first network control message including an artificial intelligence objective or an identification code. The method further includes receiving, at the first network node from the second network node, a first reply message indicating at least one of that the artificial intelligence process has been initiated, an identifier, a request indicator for a model for the artificial intelligence process, or a failure message.

Description

TECHNICAL FIELD

[0001] This patent document generally relates to wireless communication. BACKGROUND

[0002] Mobile communication technology is pushing the world towards an increasingly interconnected and networked society. The rapid growth of mobile communications and advances in technology have led to greater demands for capacity and connectivity. Other aspects, such as energy consumption, device cost, spectral efficiency, and latency, are also important to meet the needs of various communication scenarios. Various technologies are being discussed, including new approaches that provide higher quality services, longer battery life, and improved performance. SUMMARY

[0003] This patent document describes, among other things, techniques and apparatuses for providing artificial intelligence to improve wireless network efficiency and performance.

[0004] In an aspect, a method of wireless communication is disclosed. The method includes transmitting, from a first network node to a second network node, a first network control message requesting to start an artificial intelligence procedure, the first network control message including an artificial intelligence target or an identification code. The method further includes receiving, at the first network node from the second network node, a first reply message indicating at least one of the artificial intelligence procedure has started, an identifier, a request indicator for a model of the artificial intelligence procedure, or a failure message.

[0005] In another aspect, another method for wireless communication is disclosed. The method includes transmitting, from a first network node to a second network node, a network control message including an artificial intelligence model type or artificial intelligence model data. The method further includes receiving, at the first network node from the second network node, a reply message indicating a confirmation of the artificial intelligence model type, an identifier, or a failure message.

[0006] In another aspect, another method for wireless communication is disclosed. The method includes transmitting, from a first network node to a second network node, a request message for artificial intelligence measurements, the request message including an artificial intelligence measurement target, an artificial intelligence reporting configuration, or an artificial intelligence reporting granularity. The method further includes receiving, at the first network node from the second network node, an artificial intelligence measurement reply message indicating the artificial intelligence measurements have started or a failure message.

[0007] These and other aspects are described in the patent document. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 An example of an AI-based RAN architecture is shown;

[0009] Figure 2An AI management element associated with two base stations is shown;

[0010] Figure 3 AI-related control plane signaling between two base stations is shown;

[0011] Figure 4 An example of a method for wireless communication is shown;

[0012] Figure 5 Another example of a method for wireless communication is shown;

[0013] Figure 6 Another example of a method for wireless communication is shown;

[0014] Figure 7 A wireless communication system is shown;

[0015] Figure 8 A block diagram of a portion of a radio system is shown. DETAILED DESCRIPTION

[0016] Certain features are described using an example of a fifth generation (5G) wireless protocol. However, the disclosed technology is not limited in its applicability only to 5G wireless systems.

[0017] 5G systems (5GS) support self-organizing networks (SON) introduced in LTE to support deployment and performance optimization of the system. The first SON features included physical cell identity (PCI) allocation and automatic neighbor relation (ANR). The success of these two features encouraged further research on the topic and implementation of three additional SON features: mobility robustness optimization (MRO), mobility load balancing (MLB), and random access channel (RACH) optimization. MRO and MLB were enablers for long term evolution (LTE) and were further enhanced to match the growing complexity of LTE. In addition to ANR, MRO, MLB, and RACH optimization, other features that implement specific aspects of self-optimization of the network were discussed and implemented in separate SIs / WIs: minimization of drive tests (MDT), energy savings (ES), interference cancellation (ICIC, eICIC), etc. These SON features are executed based on statistics from a large amount of data from the network and UEs, sourced from data usage in the radio access network (RAN).

[0018] Further enhancements to data collection have been approved in some standards. The difference between current network optimization with SON / MDT and networks based on artificial intelligence (AI) is that AI-based networks evolve from a reactive to a proactive paradigm.

[0019] Disclosed herein are techniques for using AI models, functions, and management to provide AI improvements to system efficiency.

[0020] System changes that add AI capabilities to network capabilities include:

[0021] - Full intelligence of current network state leading to more valuable information collected from various network elements including user equipment (UE), RAN nodes, or core network (CN).

[0022] - Ability to predict network load, predict UE behavior, predict user experience;

[0023] - Ability to dynamically correlate network response with network key performance indicators (KPIs) using a closed loop approach.

[0024] Figure 1 An example of an AI-based RAN architecture 100 is shown in FIG. 1. The example architecture includes a 5G core network (5GC) 110, next generation radio access networks (NG-RANs) 130 and 140 each having AI entities or capabilities 135 and 145, respectively. The example architecture includes an operations management and maintenance (OAM) system 120 that also has an AI entity 115. This architecture takes into account the current NG-RAN architecture and interfaces to enable AI support for 5G deployments. Figure 1 Shown in FIG. 1 is a non-split RAN architecture. For use cases for RAN optimization, data collection and operations can be located in the NG-RAN nodes. Model training and model inference can be performed at a single node (e.g., OAM system or NG-RAN node), or model training can be performed at the OAM system and model inference can be performed at the NG-RAN node.

[0025] Figure 1 The AI entities 125, 135, and 145 in FIG. 1 include at least one AI management element described below with respect to Figure 2 FIG. 2.

[0026] Figure 2 NG-RAN node 1 140 and associated AI entity 145 are shown interacting with NG-RAN node 1 130 and associated AI entity 135 through AI management elements. The AI management elements include one or more of: AI function management 210, AI model management 220, and / or AI measurement management 230. These management elements are described further below.

[0027] Regardless of what AI management element(s) the AI entities 125 / 135 / 145 include, the backhaul interface between NG-RAN nodes should be enhanced to enable AI functionality. The Xn interface provides a control plane interface between radio access nodes (e.g., NG-RAN). In the disclosed subject matter, the Xn interface is enhanced to include the following functionality in order to support AI:

[0028] The Xn control plane (Xn-C) interface supports the following functions:

[0029] - AI function management 210: This function enables the AI function(s) between NG-RAN nodes supported by two nodes to be started and / or stopped.

[0030] - AI model management 220: This function enables one NG-RAN node to retrieve machine learning (ML) models from a peer NG-RAN node. With this function, updated ML models can be synchronized between NG-RAN nodes.

[0031] - AI measurement management 230: This function allows AI measurement reporting between NG-RAN nodes.

[0032] Figure 3 AI related Xn Application Protocol (XnAP) signaling that can be transported over a specific Stream Control Transmission Protocol (SCTP) association between NG-RAN node 1 and NG-RAN node 2 is depicted. This SCTP association is established for AI signaling purposes.

[0033] In Figure 3 NG-RAN node 1 310 interacts with NG-RAN node 2 315 through AI management elements, which include one or more of the following: AI function management 210, AI model management 220, and / or AI measurement management 230.

[0034] The signaling flow method 210 for AI function management includes the following elements.

[0035] At 212, NG-RAN node 1 310 sends an AI start message to NG-RAN node 2 315. The start message includes at least one of the following: an AI function target to start and / or a vendor code. The AI function target is an AI function supported by the NG-RAN node, such as AI based ES, AI based UE trajectory prediction, AI based load prediction, AI based mobility optimization, etc. The vendor code can be a value used to identify a manufacturer or vendor. For example, value 1 for vendor A and value 2 for vendor B.

[0036] At 214, NG-RAN node 2 315 replies with a confirmation message (e.g., AI start confirmation message). The confirmation message includes at least one of the following: an AI function target successful start indication, a vendor code, and / or a model request. If NG-RAN node 2 wants to retrieve machine learning (ML) / AI model information from NG-RAN node 1 310, the confirmation message will include model request information related to the requested AI function target.

[0037] At 216, if the AI start fails, the NG-RAN node 2 315 replies with a failure message (e.g., AI start failure message) with an indication of the cause of the failure.

[0038] The signaling flow method for AI function management 225 includes the following elements.

[0039] After the AI function is initialized, an AI stop procedure can be used to stop one or more AI functions between the NG-RAN node 1 310 and the NG-RAN node 2 315.

[0040] At 227, the NG-RAN node 1 310 sends an AI stop message to the NG-RAN node 2 315. The message includes at least one of the following: AI function targets to stop and / or vendor code. The AI function targets are AI functions supported by the NG-RAN node, such as AI-based ES, AI-based UE trajectory prediction, AI-based load prediction, AI-based mobility optimization, etc. The vendor code can be a value used to identify a manufacturer or vendor. For example, value 1 for vendor A, value 2 for vendor B.

[0041] At 228, the NG-RAN node 2 315 replies with a confirmation message (e.g., AI stop confirmation message). The message includes at least one of the following: AI function targets successfully stopped, and / or vendor code.

[0042] At 229, if the AI stop fails, the NG-RAN node 2 315 replies with a failure message (e.g., AI stop failure message) with an indication of the cause of the failure.

[0043] The signaling flow method for AI model management 220 includes the following elements.

[0044] At 221, the NG-RAN node 1 310 sends a model distribution message (e.g., AI model distribution message) to the NG-RAN node 2 315. The message includes at least one of the following: model type, event type, and / or model data. The model type corresponds to each requested AI function target, where the AI / ML model includes supervised learning, unsupervised learning, reinforcement learning, deep neural network. The event type indicates whether the model management message is related to model initialization or model update. The model data can be transferred via the AI model distribution message via the control plane, or via the user plane.

[0045] At 222, the NG-RAN node 2 315 replies with an acknowledgement message (e.g., an AI model acknowledgement message). The message can include a vendor code.

[0046] At 223, if the AI model fails, the NG-RAN node 2 315 replies with a failure message (e.g., an AI model failure message) with an indication of the cause of the failure.

[0047] The signaling flow method for AI measurement management 230 includes the following elements.

[0048] At 232, the NG-RAN node 1 310 sends a measurement request message (e.g., an AI measurement request message) to the NG-RAN node 2 315. The message includes at least one of the following: measurement object, reporting configuration, reporting granularity. The measurement object indicates the measurement object that the peer node is requested to report. The reporting configuration indicates the configuration for periodic reporting, time period reporting, and / or event triggered reporting. The reporting granularity includes, but is not limited to, UE granularity, cell granularity, node granularity, and / or slice granularity.

[0049] At 234, the NG-RAN node 2 315 replies with an acknowledgement message (e.g., an AI measurement request acknowledgement message). The message can indicate that the requested measurement has been successfully initiated.

[0050] At 236, if the AI measurement request fails, the NG-RAN node 2 315 replies with a failure message (e.g., an AI measurement request failure message) with an indication of the cause of the failure.

[0051] At 238, the NG-RAN node 2 315 initiates reporting the measurement in a reporting message (e.g., an AI measurement report message). The message includes at least one of the following: measurement result, reporting granularity. Detailed measurement data can be transferred in this control plane message or via user plane.

[0052] In addition, the above signaling methods can be used between a 5G core network (5GC) node and a NG-RAN node.

[0053] In addition, a measurement ID can be used in the above signaling methods to identify a specific measurement.

[0054] In addition, a transaction ID can be used in the above signaling methods to identify a procedure among ongoing parallel procedures of the same type initiated by the same protocol peer. Messages belonging to the same procedure can use the same transaction ID, which is determined by the initiating peer of the procedure.

[0055] Figure 4An example of a method 400 for wireless communication is shown. At 410, in some embodiments of the technology disclosed, the method includes transmitting, from a first network node to a second network node, a first network control message requesting initiation of an artificial intelligence method, the first network control message including an artificial intelligence target or an identification code. At 420, the method further includes receiving, at the first network node from the second network node, a first reply message indicating at least one of the artificial intelligence method has been initiated, an identifier, a request indicator for a model of the artificial intelligence method, or a failure message.

[0056] Figure 5 Another example of a method 500 for wireless communication is shown. At 510, in some embodiments of the technology disclosed, the method includes transmitting, from a first network node to a second network node, a network control message including an artificial intelligence model type or artificial intelligence model data. At 520, the method further includes receiving, at the first network node from the second network node, a reply message indicating a confirmation of the artificial intelligence model type, an identifier, or a failure message.

[0057] Figure 6 Another example of a method 600 for wireless communication is shown. At 610, in some embodiments of the technology disclosed, the method includes transmitting, from a first network node to a second network node, a request message for artificial intelligence measurements, the request message including an artificial intelligence measurement target, an artificial intelligence reporting configuration, or an artificial intelligence reporting granularity. At 620, the method further includes receiving, at the first network node from the second network node, an artificial intelligence measurement reply message indicating the artificial intelligence measurements have been initiated or a failure message.

[0058] Figure 7 An example of a wireless communication system 700 in which techniques in accordance with one or more embodiments of the technology can be applied is shown. The wireless communication system 700 can include one or more base stations (BSs) 705a, 705b, one or more wireless devices 710a, 710b, 710c, 710d, and a core network 725. The base stations 705a, 705b can provide wireless service to the wireless devices 710a, 710b, 710c, and 710d in one or more wireless sectors. In some implementations, the base stations 705a, 705b include directional antennas to produce two or more directional beams to provide wireless coverage in different sectors. The base stations 705a, 705b can communicate directly with each other wirelessly or via a wired interface, including a direct wired interface, a wired network, or the Internet.

[0059] The core network 725 can communicate with one or more base stations 705a, 705b. The core network 725 provides connectivity to other wireless and wired communication systems. The core network may include one or more service subscription databases to store information related to subscribed wireless devices 710a, 710b, 710c, and 710d. The first base station 705a can provide wireless services based on a first radio access technology, while the second base station 705b can provide wireless services based on a second radio access technology. Depending on the deployment scenario, base stations 705a and 705b can be located together or can be installed separately in the field. Wireless devices 710a, 710b, 710c, and 710d can support a variety of different radio access technologies. The technologies and embodiments described in this document can be implemented by the base stations described in this document or by the wireless devices.

[0060] Figure 8 This is a block diagram representation of a part of a radio station where one or more embodiments of the technology according to this invention can be applied. Radio device 805 (such as a base station or wireless device (or UE)) may include electronic device 810, such as a microprocessor implementing one or more of the wireless technologies presented herein. Radio device 805 may include transceiver electronics 815 for transmitting and / or receiving wireless signals via one or more communication interfaces, such as antenna 820. Radio device 805 may include other communication interfaces for transmitting and receiving data. Radio device 805 may include one or more memories (not explicitly shown) configured to store information such as data and / or instructions. In some embodiments, processor electronics 810 may include at least a portion of transceiver electronics 815. In some embodiments, radio device 805 is used to implement at least some of the disclosed technologies, modules, or functions. In some embodiments, radio device 805 may be configured to perform the methods described in this document.

[0061] The technical solutions described in the following clauses can preferably be implemented through some embodiments.

[0062] Clause 1. A method of wireless communication, comprising: transmitting from a first network node to a second network node a first network control message requesting the initiation of an artificial intelligence process, the first network control message including an artificial intelligence target or identifier; and receiving at the first network node a first response message from the second network node indicating that the artificial intelligence process has been initiated, an identifier, a request indicator for a model for the artificial intelligence process, or a failure message, at least one of these.

[0063] Clause 2. The method of wireless communication of Clause 1, further comprising: transmitting, from the first network node to the second network node, a second network control message requesting to stop an artificial intelligence process, wherein the second network message indicates at least one of an artificial intelligence target or an identification code to be stopped; and receiving, at the first network node from the second network node, a second reply message indicating at least one of an artificial intelligence stop message, an identifier, or another failure message.

[0064] Clause 3. The method of wireless communication of Clause 1 or 2, wherein the artificial intelligence process comprises at least one of: an artificial intelligence expert system, an artificial intelligence based user equipment mobility prediction, an artificial intelligence based network load prediction, or an artificial intelligence based mobility optimization.

[0065] Clause 4. A method of wireless communication, comprising: transmitting, from a first network node to a second network node, a network control message comprising at least one of an artificial intelligence model type or artificial intelligence model data; and receiving, at the first network node from the second network node, a reply message indicating at least one of a confirmation of the artificial intelligence model type, an identifier, or a failure message.

[0066] Clause 5. The method of wireless communication of Clause 4, wherein the artificial intelligence model comprises at least one of: a supervised learning model, an unsupervised learning model, a reinforcement learning model, or a deep neural network model.

[0067] Clause 6. A method of wireless communication, comprising: transmitting, from a first network node to a second network node, an artificial intelligence measurement request message comprising an artificial intelligence measurement target, an artificial intelligence reporting configuration, or an artificial intelligence reporting granularity; and receiving, at the first network node from the second network node, an artificial intelligence measurement reply indicating that the artificial intelligence measurement has been started or a failure message.

[0068] Clause 7. The method of wireless communication of Clause 6, wherein the artificial intelligence measurement target is a measurement object for which a peer node is requested to report.

[0069] Clause 8. The method of wireless communication of Clause 6, wherein the artificial intelligence reporting configuration indicates periodic reporting or event triggered reporting or time period reporting.

[0070] Clause 9. The method of wireless communication of Clause 6, wherein the artificial intelligence reporting granularity indicates a user equipment granularity, a cell granularity, a node granularity, or a slice granularity.

[0071] Clause 10. The method of wireless communication of Clause 6, further comprising: receiving, at the first network node from the second network node, the artificial intelligence measurement.

[0072] Clause 11. The method of wireless communication of any of clauses 6 to 10, wherein the measurement identifier identifies an artificial intelligence measurement.

[0073] Clause 12. The method of wireless communication of any of clauses 1 to 11, wherein the transaction identifier identifies a same type of ongoing parallel procedure initiated by a same protocol peer.

[0074] Clause 13. The method of wireless communication of any of clauses 1 to 12, wherein the first network node is a next generation radio access network node (NG-RAN node) and the second network node is a NG-RAN node, or the first network node is a NG-RAN node and the second network node is a core network node.

[0075] In the technical solutions described herein in clauses, the network node can be a network device or a network-side equipment such as a base station or the like. Figure 8 An example hardware platform for implementing a network node or wireless node is shown.

[0076] It should be understood that the present document discloses techniques that can be implemented in various embodiments to establish and manage AI functionality in a cellular network. The disclosed and other embodiments, modules and the functional operations described in this document can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this document and their structural equivalents, or in combinations of one or more of them. The disclosed and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more of them. The term “data processing apparatus” encompasses all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. The propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.

[0077] A computer program (which can also be referred to or referred to as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and are interconnected by a communication network.

[0078] The processes and logic flows described herein can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuitry, and that

[0079] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0080] Some embodiments can preferably implement one or more of the following solutions listed in the clauses format. In the above examples and throughout this document, the following clauses are supported and further described. As used in the following clauses and claims, a wireless terminal can be a user equipment, a mobile station, or any other wireless terminal including a fixed node such as a base station. A network node includes a base station, including a next generation Node B (gNB), an enhanced Node B (eNB), or any other device operating as a base station. A resource range can refer to a range of time-frequency resources or blocks.

Claims

1. A method for wireless communication, comprising: A first request message for artificial intelligence measurement is transmitted from the first network node to the second network node. The first request message includes an identifier and an artificial intelligence measurement target. The first request message also includes AI report configuration or AI report granularity, and The artificial intelligence measurement report is limited between the first network node and the second network node; At the first network node, a first AI measurement response message is received from the second network node. This first AI measurement response message indicates that the AI ​​measurement has been initiated and includes the identification code. The AI-based measurements include AI-based network load prediction and / or AI-based mobility optimization. A second request message is transmitted from the first network node to the second network node, requesting the cessation of artificial intelligence measurements. The second request message indicates the artificial intelligence target to be stopped and the identification code; and At the first network node, a second response message is received from the second network node, the second response message indicating that the artificial intelligence measurement target has successfully stopped and the identification code.

2. The wireless communication method according to claim 1, wherein the artificial intelligence measurement target is the measurement object that the peer node is requested to report.

3. The wireless communication method according to claim 1, wherein the artificial intelligence report configuration indicates periodic reporting, event-triggered reporting, or time-period reporting.

4. The wireless communication method according to claim 1, wherein the artificial intelligence report granularity indicates user equipment granularity, cell granularity, node granularity, or slice granularity.

5. The wireless communication method according to claim 1, further comprising: The artificial intelligence measurement is received from the second network node at the first network node.

6. The wireless communication method according to claim 1, further comprising: In response to a failure to initiate an AI measurement, a failure message is received at the first network node from the second network node, the failure message indicating the reason for the failure.

7. A wireless communication apparatus, comprising a processor and a memory, wherein the processor is configured to read computer-executable instructions from the memory and perform a wireless communication method, the method comprising: A first request message for artificial intelligence measurement is transmitted from the first network node to the second network node. The first request message includes an identifier and an artificial intelligence measurement target. The first request message also includes AI report configuration or AI report granularity, and The artificial intelligence measurement report is limited between the first network node and the second network node; At the first network node, a first AI measurement response message is received from the second network node. This first AI measurement response message indicates that the AI ​​measurement has been initiated and includes the identification code. The AI-based measurements include AI-based network load prediction and / or AI-based mobility optimization. A second request message is transmitted from the first network node to the second network node, requesting the cessation of artificial intelligence measurements. The second request message indicates the artificial intelligence target to be stopped and the identification code; and At the first network node, a second response message is received from the second network node, the second response message indicating that the artificial intelligence measurement target has successfully stopped and the identification code.

8. The wireless communication apparatus of claim 7, wherein the artificial intelligence measurement target is a measurement object that is requested to be reported by a peer node.

9. The wireless communication apparatus of claim 7, wherein the artificial intelligence report configuration indicates periodic reporting, event-triggered reporting, or time-period reporting.

10. The wireless communication apparatus of claim 7, wherein the artificial intelligence report granularity indicates user equipment granularity, cell granularity, node granularity, or slice granularity.

11. The wireless communication apparatus according to claim 7, wherein the method further comprises: The artificial intelligence measurement is received from the second network node at the first network node.

12. The wireless communication apparatus according to claim 7, wherein the method further comprises: In response to a failure to initiate an AI measurement, a failure message is received at the first network node from the second network node, the failure message indicating the reason for the failure.

13. A computer-readable storage medium storing computer-executable instructions, which, when executed, perform a method of wireless communication, the method comprising: A first request message for artificial intelligence measurement is transmitted from the first network node to the second network node. The first request message includes an identifier and an artificial intelligence measurement target. The first request message also includes AI report configuration or AI report granularity, and The artificial intelligence measurement report is limited between the first network node and the second network node; At the first network node, a first AI measurement response message is received from the second network node. This first AI measurement response message indicates that the AI ​​measurement has been initiated and includes the identification code. The AI-based measurements include AI-based network load prediction and / or AI-based mobility optimization. A second request message is transmitted from the first network node to the second network node, requesting the cessation of artificial intelligence measurements. The second request message indicates the artificial intelligence target to be stopped and the identification code; and At the first network node, a second response message is received from the second network node, the second response message indicating that the artificial intelligence measurement target has successfully stopped and the identification code.

14. The computer-readable storage medium of claim 13, wherein the artificial intelligence measurement target is a measurement object that is requested to be reported by a peer node.

15. The computer-readable storage medium of claim 13, wherein the artificial intelligence report configuration indicates periodic reporting, event-triggered reporting, or time-period reporting.

16. The computer-readable storage medium of claim 13, wherein the artificial intelligence report granularity indicates user equipment granularity, cell granularity, node granularity, or slice granularity.

17. The computer-readable storage medium of claim 13, wherein the method further comprises: The artificial intelligence measurement is received from the second network node at the first network node.

18. The computer-readable storage medium of claim 13, wherein the method further comprises: In response to a failure to initiate an AI measurement, a failure message is received at the first network node from the second network node, the failure message indicating the reason for the failure.

Images