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

Abstract

This disclosure provides a communication method, communication device, storage medium, and program product, relating to the field of communication technology, and can solve the technical problem of poor user experience in related technologies. The method is applied to a first node, and includes: collecting first data; the first data being data used by a second node to perform prediction; and sending a first report to the second node, the first report including the first data.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, storage medium, and program product. Background Technology

[0002] With the rapid development of mobile communication technology and the increasing complexity of wireless networks, traditional network management and optimization methods are facing more and more challenges.

[0003] Currently, there are issues with the user experience in related technologies. Summary of the Invention

[0004] This disclosure provides a communication method, communication device, storage medium, and program product, which can solve the technical problem of poor user experience in related technologies.

[0005] On the one hand, a communication method is provided, applied to the first node, the method including:

[0006] Collect the first data; the first data is used for the second node to perform prediction.

[0007] Send the first report to the second node. The first report includes the first data.

[0008] On the other hand, a communication device is provided, which includes a processing module and a transmitting module.

[0009] The processing module is used to collect the first data; the first data is the data used by the second node to perform prediction.

[0010] The sending module is used to send a first report to the second node. The first report includes first data.

[0011] On the other hand, a communication method is provided for application to a second node, the method including:

[0012] Receive a report from the first node; the report includes first data and / or second data; the first data is the data used to perform the prediction; the second data is the data predicted by the first node.

[0013] Based on the report, a third set of data is predicted; the third set of data is the predicted data related to the future demand of the first node.

[0014] In another aspect, a communication device is provided, comprising: a receiving module and a processing module;

[0015] A receiving module is used to receive a report from a first node; the report includes first data and / or second data; the first data is data used to perform prediction; the second data is data predicted by the first node.

[0016] The processing module is used to predict and obtain third data based on the report; the third data is the predicted data related to the future demand of the first node.

[0017] On the other hand, a communication method is provided for application to core network elements, the method including:

[0018] Receive third data from the second node, which is a forecast of the second node's future demand related to the first node.

[0019] In another aspect, a communication device is provided, comprising: a receiving module;

[0020] The receiving module is used to receive third data from the second node, which is the predicted data of the second node related to the future demand of the first node.

[0021] In another aspect, a communication device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store a computer program; and the processor, when executing the computer program, implements the method described in any of the above embodiments.

[0022] In another aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the method described in any of the above embodiments.

[0023] In another aspect, a computer program product is provided, the computer program product including computer program instructions that, when executed by a processor, implement the method described in any of the above embodiments.

[0024] This disclosure provides a communication method in which a second node first sends / reports first data, and the second node can perform predictions based on the data collected by the first node. The second node can obtain relevant information about the future tasks of the first node, and thus, the second node can proactively plan and prepare for the possible service needs of the first node. In this way, the service quality of the second node to the first node can be improved, and the user experience can be enhanced. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings.

[0026] Figure 1 This disclosure provides a system architecture diagram of a communication system.

[0027] Figure 2This is a schematic diagram illustrating a terminal-based forward-looking prediction method provided in this disclosure;

[0028] Figure 3 This is a schematic diagram of the elemental logic of an intelligent agent provided in this disclosure;

[0029] Figure 4 A flowchart illustrating a communication method provided in this disclosure;

[0030] Figure 5 A flowchart illustrating another communication method provided in this disclosure;

[0031] Figure 6 A flowchart illustrating another communication method provided in this disclosure;

[0032] Figure 7 A flowchart illustrating another communication method provided in this disclosure;

[0033] Figure 8 A flowchart illustrating another communication method provided in this disclosure;

[0034] Figure 9 A flowchart illustrating another communication method provided in this disclosure;

[0035] Figure 10 A flowchart illustrating another communication method provided in this disclosure;

[0036] Figure 11 A flowchart illustrating another communication method provided in this disclosure;

[0037] Figure 12 This is a schematic diagram of the structure of a communication device provided in this disclosure;

[0038] Figure 13 A schematic diagram of another communication device provided in this disclosure;

[0039] Figure 14 A schematic diagram of another communication device provided in this disclosure;

[0040] Figure 15 A schematic diagram of another communication device provided in this disclosure. Detailed Implementation

[0041] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0042] It should be noted that, in this disclosure, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0043] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0044] In the description of this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "more than one" means two or more.

[0045] In some embodiments, the term "determine" may encompass a wide variety of actions. For example, "determine" may include calculation, processing, deduction, investigation, instruction, lookup (e.g., searching in a table, database, or other data structure), etc. Furthermore, "determine" may include sending (e.g., sending information), receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Additionally, "determine" may include resolving, selecting, establishing, etc.

[0046] In current 5G-A and future 6G wireless communication systems, numerous new forms of functional applications, such as AI / ML models and large-scale intelligent agents, will be gradually integrated. These aim to empower and enhance the performance of various network elements and protocol functions within the wireless system, such as improving intelligent decision-making at network elements, increasing the performance efficiency of wireless communication, and achieving energy savings. Among these, intelligent agents (AA: AI Agents), possessing powerful hyper-converged capabilities such as sensing, computing, and intelligence, can perform real-time monitoring, analysis, evaluation, and decision-making guidance at various levels within the wireless network and terminals. This results in more reasonable and accurate network empowerment and intelligence enhancement, improving wireless system performance and mobile user experience. However, some related technologies suffer from poor user experience.

[0047] To address the aforementioned technical problems, this disclosure provides a communication method in which a second node first sends / reports first data. The second node can then perform predictions based on the data collected by the first node, and obtain relevant information about the future tasks of the first node. Consequently, the second node can proactively plan and prepare for the possible service needs of the first node, thereby improving the service quality of the second node to the first node and enhancing the user experience.

[0048] The communication method provided in this disclosure can be applied to systems with various communication standards. For example, the systems to which the communication method provided in this disclosure is applicable include, but are not limited to, long-term evolution (LTE) systems, various versions based on LTE evolution, 5G systems, future mobile communication networks (such as 6G mobile communication networks), or multiple converged communication systems. Furthermore, the communication method provided in this disclosure can also be applied to future-oriented communication systems.

[0049] For example, the above communication method can be applied to, for example, Figure 1 In the aforementioned communication system, such as Figure 1 As shown, the communication system includes: a first node 101, a second node 102, and a core network element 103.

[0050] Among them, the first node 101 is used to collect the first data; the first data is the data used by the second node 102 to perform prediction.

[0051] Send a first report to the second node 102. The first report includes the first data.

[0052] The second node 102 is used to receive a report from the first node 101; the report includes first data and / or second data; the first data is data used to perform prediction; the second data is data predicted by the first node 101.

[0053] Based on the report, the third data is predicted; the third data is the predicted data related to the future demand of the first node 101.

[0054] The core network element 103 is used to receive third data from the second node 120. The third data is the predicted data related to the future needs of the first node, which is predicted by the second node 102.

[0055] In one possible implementation, the communication system may also include a third node, which assists the first node in performing prediction or task planning.

[0056] In some embodiments, the first node 101, the second node 102, and the core network element 103 can be intelligent agent network nodes. An intelligent agent network node refers to a new type of intelligent network node that integrates (or merges) "intelligent agent functional entities" capable of supporting specific intelligent agent tasks, based on the functions of a traditional wireless network node. A network intelligent agent is an entity deployed on a specific intelligent agent network node that possesses autonomous learning and decision-making capabilities. Network intelligent agents involve at least, but are not limited to, terminal UE intelligent agents and network intelligent agents. Examples of network intelligent agents include base stations (xNBs), base station centralized units (CUs), base station distributed units (DUs), and core network elements (such as network functions like Access and Mobility Management Function (AMF), Session Management Function (SMF), and Policy Control Function (PCF)).

[0057] In some embodiments, the first node 101 can be a terminal and the second node 102 can be a base station.

[0058] In one possible implementation, the terminal can be a terminal with an intelligent agent.

[0059] In one possible implementation, the network to which the base station belongs can be an agent network (or an intelligent network).

[0060] In some embodiments, the terminal can be a device with wireless transceiver capabilities, which can be deployed on land, including indoors or outdoors, handheld, wearable, or vehicle-mounted; it can also be deployed on water (such as on ships); and it can also be deployed in the air (e.g., on airplanes, balloons, and satellites). The terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. The embodiments of this application do not limit the application scenarios. The term "terminal" can sometimes also refer to a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication device, UE agent, or UE device, etc., but the embodiments of this application do not limit this to these terms.

[0061] In some embodiments, the base station may be a base station in Long Term Evolution (LTE), Long Term Evolution Advanced (LTEA), or an evolved Node B (eNB or eNodeB), a base station device in a 5G network, or a base station in a future communication system. The base station may include various macro base stations, micro base stations, home base stations, wireless remote extensions, reconfigurable intelligent surfaces (RISs), routers, wireless fidelity (WIFI) devices, or various network-side devices such as primary cells and secondary cells.

[0062] It should be noted that with the rapid development of mobile communication technology and the increasing complexity of wireless networks, traditional network management and optimization methods are facing more and more challenges. Especially in 5G networks, due to diverse application scenarios (eMBB, URLLC, mMTC) and the dynamic and complex nature of network resource demands, existing network optimization solutions have certain limitations in addressing multi-dimensional, real-time, and global requirements. To improve network performance and meet user experience needs, artificial intelligence (AI) technology is gradually being introduced into network management and has been applied to some extent in the standardization process. In standards, AI technology is being gradually integrated into wireless networks to solve problems such as resource scheduling, mobility management, network prediction, and optimization.

[0063] Some typical AI applications include:

[0064] Base station-level AI prediction and optimization: Base stations utilize machine learning models to predict cell load, user distribution, and interference, thereby optimizing scheduling strategies. AI models are used to predict user movement paths (e.g., highway and subway scenarios) to improve handover management success rates.

[0065] AI applications in QoS assurance: For specific applications (such as video streaming), AI is used to predict traffic demand and dynamically adjust QoS parameters to optimize user experience.

[0066] Network energy saving and resource allocation: AI is used to predict changes in cell traffic, enabling intelligent shutdown and energy saving. In network slicing, network resources are dynamically allocated based on historical data to predict slice demand.

[0067] AI-assisted functions in the core network: The core network utilizes AI for network path optimization, such as optimizing transmission paths through traffic prediction and path load prediction. In edge computing scenarios, AI predicts user service needs and dynamically allocates computing tasks to edge nodes.

[0068] Although the standard incorporates AI technology and proposes some application scenarios and technical specifications, existing AI solutions still have the following shortcomings in predictive ability, dimensional coverage, and global optimization:

[0069] Limitations of single-dimensional prediction: Current AI applications mostly focus on single-dimensional predictions, such as traffic demand prediction, mobility prediction, or resource load prediction. However, in real-world network scenarios, various dimensions of demand (such as user behavior, service intent, and environmental changes) are highly coupled, and single-dimensional predictions cannot fully reflect complex scenarios.

[0070] Insufficient local optimization and global coordination: Most AI prediction and optimization solutions are limited to local optimization within a single network element (such as a base station), lacking coordination mechanisms between network elements. For example, in scenarios involving cross-base station handover or cross-domain resource coordination, existing solutions struggle to achieve efficient global optimization, easily leading to resource conflicts or service interruptions.

[0071] Limited time scale and accuracy of predictions: Most existing prediction models are based on short-term historical data (such as minute-level or hour-level data), and have limited ability to predict long-term trends (such as changes in user behavior and scene evolution). At the same time, the accuracy of predictions is difficult to guarantee in complex dynamic scenarios, such as trajectory prediction of high-speed mobile users or end-to-end QoS requirement prediction.

[0072] Lack of understanding of user intent and contextual semantics: Existing solutions are mainly based on traditional statistical features or shallow machine learning models, making it difficult to capture the service intent or contextual semantics behind user behavior. For example, for users' navigation needs, existing models cannot understand their travel purpose, service priority, or key time points, thus making it difficult to provide targeted service guarantees.

[0073] Insufficient dynamic adaptability: Dynamic changes in the network environment and user needs (such as sudden traffic peaks and abnormal network events) place higher demands on the real-time performance and adaptability of AI models, but existing solutions still fall short in terms of rapid dynamic adjustment and real-time optimization.

[0074] With the rapid development of smart terminals and embodied intelligent agent technologies, the predictability of terminal behavior has significantly improved, providing a more solid foundation for network intelligent agent prediction and service assurance. Modern smart terminals exhibit obvious behavioral patterns and predictability, mainly reflected in the following aspects:

[0075] Regular activity patterns: Users’ daily activities exhibit a high degree of spatiotemporal regularity, such as fixed commuting routes, stable working hours, and periodic leisure activities.

[0076] Application usage periodicity: The use of terminal applications exhibits obvious time periodicity and context relevance. For example, navigation applications are used frequently during commuting hours, social media usage increases during rest periods, and work applications are active during office hours.

[0077] Context-dependent behavior: Terminal behavior is highly correlated with its environment, time, location, and other contextual factors. When a user enters a specific location (such as an airport, conference room, or stadium), their application usage patterns and network requirements become highly predictable.

[0078] Intent-driven behavior chains: User behavior is usually driven by a clear intent, forming an identifiable behavior chain. For example, "booking a flight - viewing an itinerary - navigating to the airport - checking in" constitutes a typical "airport travel" intent chain.

[0079] Embodied intelligent agents (such as intelligent robots, autonomous vehicles, and industrial automation equipment) exhibit higher behavioral predictability compared to ordinary agents. Their characteristics include: task definition—embodied agents typically execute predefined tasks, with more clearly defined behavioral goals and execution paths; plan-driven behavior—embodied agents operate based on internal planning systems, their behavioral decision-making processes are transparent and accessible, and they can proactively share their action plans, enabling the network to anticipate future resource needs; and closed-loop control logic—embodied agents employ closed-loop control logic, and their response patterns are highly consistent with specific inputs. This determinism makes their network behavior repeatable and predictable under similar conditions.

[0080] Based on the highly predictable characteristics of terminal behavior, network intelligent agents can achieve intent recognition and service pre-configuration, trajectory and dwell point prediction, resource demand fluctuation prediction, and service recognition at critical moments, thereby realizing precise and differentiated service guarantee strategies.

[0081] For example, such as Figure 2 The diagram illustrates a terminal-to-terminal predictive capability according to an embodiment of this disclosure, showing the process of a smart agent terminal and a smart agent network for terminal-to-terminal predictive capability. The smart agent terminal may have task requirements planned for specific scenarios, and the smart agent network can proactively respond in a forward-looking manner, specifically including:

[0082] The intelligent agent terminal reports auxiliary information such as task planning and orchestration to the intelligent agent network;

[0083] The intelligent agent network performs parsing, response, and determination of auxiliary information.

[0084] The intelligent agent network uses regular detection to determine the requests of the intelligent agent terminal.

[0085] The intelligent agent terminal sends a self-checking and confirmation response to the intelligent agent network, providing information about the regularity of network services.

[0086] In one possible implementation, the tasks of the intelligent agent terminal can correspond to a regular task service flow.

[0087] In one possible implementation, the agent network may include network nodes such as base stations with agents and core network elements.

[0088] Intelligent agents possess the ability to perceive their environment, make autonomous decisions, and continuously learn, and have achieved groundbreaking progress in several fields in recent years. Applying intelligent agent technology to wireless networks can enable proactive task orchestration and resource planning by combining user behavior prediction.

[0089] Intelligent agents possess advanced autonomous generalized intelligence and can provide hyper-converged capabilities throughout the entire lifecycle, from user requests and intentions, sensory command input to target task decomposition, orchestration, and closed-loop execution.

[0090] For example, such as Figure 3 The diagram shown is a schematic diagram of the elements of an intelligent agent provided in an embodiment of this disclosure. The core elements of the intelligent agent AA include: various inputs (perceptual input, intention input, instruction input, etc.), task objectives, role settings (for large domain models), task orchestration, tools, knowledge and experience database, local task execution, and networked task collaboration.

[0091] It should be noted that, Figure 1 This is just an example framework diagram. Figure 1 The number of devices included and the names of each device are unlimited.

[0092] The application scenarios of the embodiments disclosed herein are not limited. The system architecture and business scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0093] The communication method provided in the embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0094] The communication method provided in this disclosure can be applied to... Figure 1 The first node 101 in the communication system shown. Figure 4 A flowchart of a communication method is shown, such as... Figure 4 As shown, the communication method includes the following S401-S402:

[0095] S401, Collect the first data.

[0096] The first data is used for the second node to perform predictions.

[0097] S402, Send the first report to the second node.

[0098] The first report includes the first data.

[0099] It should be noted that by sending / reporting the first data to the second node, the second node can perform predictions based on the data collected by the first node. The second node can obtain relevant information about the future tasks of the first node. As a result, the second node can proactively plan and prepare for the possible service needs of the first node. In this way, the service quality of the second node to the first node can be improved, and the user experience can be enhanced.

[0100] It should be noted that, correspondingly, the second node can receive the first report sent by the first node.

[0101] In some embodiments, the first data includes at least one of the following: physical layer measurement data, mobility management data, application data, application context data, cache state, behavior state data, user context data, and performance and power consumption data of the first node.

[0102] In one possible implementation, the relevant data measured at the physical layer includes at least one of the following: reference signal received power, reference signal received quality, signal-to-interference-plus-noise ratio, beam measurement results, timing advance, etc.

[0103] In one possible implementation, the mobility management data includes at least one of the following: mobility state estimation, cell reselection priority, cell reselection count and history, and cell global identifier (CGI) related information.

[0104] In one possible implementation, the performance and power consumption data of the first node may include at least one of the following: battery status and power saving preference settings.

[0105] In one possible implementation, the application data may include at least one of the following: Quality of Service Flow Identifier (QFI) and characteristics, Service Data Flow (SDF) mode, business processing priority, and latency tolerance.

[0106] In one possible implementation, the buffer status may include at least one of the following: Buffer Status Report (BSR) data, Logical Channel Prioritization (LCP) information, and data availability status.

[0107] In one possible implementation, the behavioral state data (or other behavioral state data) may include at least one of the following: multi-connectivity state (connection quality of all available Radio Access Technology (RAT)), location change trends, wireless environment classification (environmental characteristics), signal quality change patterns, etc.

[0108] In one possible implementation, application context data may include at least one of the following: application type classification, expected session duration, data burst prediction, service quality sensitivity, bandwidth utilization pattern (constant / variable / bursting characteristics, etc.).

[0109] In one possible implementation, user context data may include at least one of the following: activity state, location context (semantic location such as home / office / commuting), usage pattern (single-task / multi-task parallel usage pattern, etc.), time context (time period characteristics and regular patterns), etc.

[0110] In some embodiments, the first report may further include at least one of the following: an identifier of the first node, an identifier of the session associated with the first report.

[0111] In some embodiments, a first report is sent to the second node under one of the following circumstances: the first node requests to report a first report; the second node requests the first node to report a first report; or the first report is triggered by a reporting condition. That is, the first node can actively report a first report, the second node can request and trigger the first node to report, or the reporting condition can control the first node to report.

[0112] In some embodiments, the reporting of the first report in response to reporting conditions includes at least one of the following: timed triggering, periodic triggering, response to a specific behavior, or response to a change in a specific behavior.

[0113] In some embodiments, when the first node requests to report a first report, the method further includes: sending a first request to a second node. The first request is used to request the reporting of the first report. The corresponding second node receives the first request sent by the first node.

[0114] In some embodiments, the first request includes at least one of the following: the identifier of the first node, the type of the first data, the timestamp of the first data, the size of the first data, and the priority of the first report.

[0115] In some embodiments, the method further includes: receiving a first response from a second node; the first response being used to indicate whether the first node is allowed to report a first report; and the corresponding second node may send the first response to the first node.

[0116] Sending the first report to the second node includes: sending the first report to the second node in the event that the first response indicates permission for the first node to report the first report.

[0117] In some embodiments, where the first response is used to indicate permission for the first node to report the first report, the first response includes reporting configuration information; sending the first report to the second node includes: sending the first report to the second node based on the reporting configuration information. This ensures that the first node completes the reporting of the first report according to the configuration of the second node, guaranteeing resource allocation when the first node reports the first report.

[0118] In some embodiments, when the second node requests the first node to report a first report, the method further includes:

[0119] Receive a second request from the second node; the second request is used to request the first node to send the first report; the corresponding second node sends the second request;

[0120] Sending the first report to the second node includes: sending the first report to the second node based on the second request.

[0121] In some embodiments, the second request includes at least one of the following: a request identifier, a request priority, a data type to be reported, and a response deadline. The request priority allows the first node to process the second request based on priority when resource contention exists, ensuring that the requirements corresponding to the second request are handled reliably and reasonably. The data type to be reported ensures that the first node reports the data type expected by the second node.

[0122] In some embodiments, sending a first report to a second node based on a second request includes: sending the first report to the second node if it is determined, based on the second request, that sending the first report is permissible. Thus, the first node can send the first report if it determines, based on its own specific circumstances, that sending is permissible. For example, if the first node lacks data collection capabilities, cannot complete subsequent interactions with the second node, or has no need for the second node to provide forward-looking services, the first report will not be sent.

[0123] In some embodiments, when a report is triggered in response to a reporting condition, the method further includes: receiving a first signaling; the first signaling is used to configure the reporting conditions. Thus, the configuration of the reporting conditions can be completed through the first signaling. In some embodiments, the first signaling can be sent by a second node, or by other nodes or devices; this disclosure does not limit this.

[0124] In some embodiments, the first signaling is also used to configure reporting resources and / or reporting methods. This allows the resources or methods required for the first report to be configured in advance.

[0125] In some embodiments, the method further includes: predicting second data; and sending a second report to a second node, the second report including the second data. Thus, the first node can perform the prediction locally and send it to the second node, thereby saving overhead on the second node. In some embodiments, the second data is predicted from the first data. In some embodiments, the second data is predicted based on an agent on the first node.

[0126] In some embodiments, the second data includes at least one of the following: service task profile, mobility task profile, business importance assessment information, and resource demand forecast information.

[0127] It should be noted that a user task profile refers to a structured description and prediction of a user's current and expected network usage behavior, scenario requirements, and resource characteristics based on multi-dimensional data collected from the terminal. It includes elements such as the environmental characteristics of user activities, behavioral patterns, application requirements, and quality expectations, used to guide the predictive allocation of network resources and service quality assurance. Similarly, a service task profile is a predictive profile of business services based on the user task profile, and a mobility task profile is a predictive profile of mobility services based on the user task profile.

[0128] In some embodiments, the service task profile includes at least one of the following: service scenario information, task profile features, environmental context information, resource requirement information, priority information, policy preference information, and other scenario-based task profile information besides the service scenario.

[0129] In some embodiments, the second report is sent together with the first report; or, the second report and the first report are sent independently.

[0130] The communication method provided in this disclosure can be applied to... Figure 1 The second node 102 in the communication system shown. Figure 5 A flowchart illustrating another communication method is shown, such as... Figure 5 As shown, the communication method includes the following S501-S502:

[0131] S501, Receive a report from the first node.

[0132] The report includes first data and / or second data; the first data is the data used to perform the prediction; the second data is the data obtained from the prediction of the first node.

[0133] S502. Based on the report, the third data is predicted.

[0134] The third data is the forecast data related to the future demand of the first node.

[0135] In some embodiments, predicting third data based on the report includes: acquiring fourth data; the fourth data being auxiliary data collected or stored by the second node for performing task profile prediction; and obtaining the third data based on the report and the fourth data. For example, the fourth data may include cell status data and / or network configuration and topology information.

[0136] In some embodiments, the third data includes the behavior prediction data of the first node and / or the task profile prediction report of the first node.

[0137] In some embodiments, the behavior prediction data of the first node includes at least one of the following:

[0138] Predicted information on cell status corresponding to the first node, predicted information on user distribution pattern corresponding to the first node, predicted information on service demand of the first node, predicted information on interference scenario corresponding to the first node, and predicted information on scenario evolution of the first node.

[0139] In some embodiments, the task profile prediction report of the first node includes at least one of the following: scenario description information, risk assessment information, resource status information, and service assurance assessment information.

[0140] In some embodiments, the method further includes: generating fifth data based on third data; the fifth data being used to indicate relevant prediction information for the future scenario of the first node; and sending the fifth data to the first node. The corresponding first node can receive the fifth data.

[0141] In some embodiments, the fifth data includes at least one of the following: a prediction result of the future scenario for the first node, confidence information of the prediction result, and a planning strategy for the future scenario for the first node. Thus, the first node can know the above information and further perform subsequent related processing, such as judging / checking the prediction result, providing verification information of the prediction result, or replying with a confirmation message.

[0142] In some embodiments, the third data is obtained through collaborative prediction by the second node and the third node; the method further includes:

[0143] A third request is sent to the third node; the third request is used to request the third node to cooperate in prediction; the corresponding third node receives the third request;

[0144] Receive a third response from a third node; the third response is the third node's response to the third request; the corresponding third node sends a third response.

[0145] In one possible implementation, when the second and third nodes collaboratively predict the third data, the second node can predict a portion of the third data itself and request the third node to predict the remaining portion. This allows the second node to leverage the resources of the third node to better complete the prediction of the third data. In another possible implementation, the second node can send relevant data for performing the collaborative prediction to the third node, such as prediction requirements, the data used for prediction, and auxiliary information required for prediction.

[0146] In some embodiments, the third request includes at least one of the following: task profile information, collaborative prediction strategy, collaborative prediction scenario type, collaborative prediction scope, and collaborative prediction priority. Thus, the third node can understand the collaborative prediction requirement and perform corresponding processing, such as determining whether the requirement can be met, or responding with collaborative prediction content.

[0147] In some embodiments, the third response includes at least one of the following: the third node agrees to the collaboration, the information predicted by the third node, the amount of available resources of the third node, the reservation validity period of the available resources of the third node, and the limiting factors corresponding to the third node; thus, the second node can obtain the collaborative prediction capabilities or limitations that the third node can provide, and can better complete the subsequent collaborative prediction process.

[0148] The third node refuses to cooperate.

[0149] In some embodiments, the third data is predicted collaboratively by the second node and core network elements; the method further includes:

[0150] Send a fourth request to the core network element; the fourth request is used to request the core network element to cooperate in prediction.

[0151] Receive a fourth response from a core network element; the fourth response is the core network element's response to the third request. The corresponding core network element can receive the fourth request and send a fourth response.

[0152] In some embodiments, the fourth request includes at least one of the following: task profile information, status information of the second node, and service assurance request. In this way, core network elements can accurately determine the need for collaborative prediction.

[0153] In some embodiments, the fourth response includes at least one of the following: core network element agreeing to cooperate, information predicted by the core network element, and resource service strategy; or core network element refusing to cooperate.

[0154] In some embodiments, the third data includes at least one of the following: behavior prediction information of the first node, business demand prediction information of the first node, prediction confidence, and the priority of the predicted business.

[0155] In some embodiments, the method further includes: determining sixth data based on third data; the sixth data includes task planning information and resource reservation strategies for future scenarios of the first node.

[0156] In some embodiments, the method further includes: sending task planning information for a future scenario to a first node. The corresponding first node receives the task planning information for the future scenario. Thus, the first node can know the task planning information for the future scenario generated by the second node, and therefore, the first node can perform subsequent processing accordingly, such as completing subsequent tasks based on the task planning information, or sending information to the second node to adjust the task planning.

[0157] In some embodiments, the sixth data is determined collaboratively by the second node and the third node. The method further includes: sending a fifth request to the third node; the fifth request is used to request the third node to collaboratively determine the sixth data; receiving a fifth response from the third node; the fifth response is the third node's response to the fifth request. The corresponding third node receives the fifth request and sends a fifth response. In one possible implementation, the second node may send relevant data for performing collaborative determination to the third node, such as collaborative determination requirements, data used for collaborative determination (which may be part of the third data or include other data that can assist in the determination), and auxiliary information required for collaborative determination.

[0158] In some embodiments, the fifth request includes at least one of the following: the third node agrees to collaboration, a resource reservation strategy, a parameter collaboration strategy, a prediction identifier, and a prediction time window; the third node refuses to collaborate.

[0159] In some embodiments, the fifth response includes at least one of the following: resource status information, and the reservation validity period of the reserved resources.

[0160] In some embodiments, the sixth data is determined collaboratively by the second node and the core network element. The method further includes: sending a sixth request to the core network element; the sixth request is used to request the core network element to collaboratively determine the sixth data; receiving a sixth response from the core network element; the sixth response is the core network element's response to the sixth request. The corresponding fifth response receives the sixth request and sends the sixth response.

[0161] In some embodiments, the sixth request includes at least one of the following: task profile information, service quality flow demand forecast information, time window planning information, and resource coordination suggestion information.

[0162] In some embodiments, the sixth response includes at least one of the following: core network element agreeing to cooperate, core network element resource status information, transmission path readiness, and quality of service flow guarantee capability; or core network element refusing to cooperate.

[0163] In some embodiments, the method further includes: obtaining seventh data; the seventh data being the actual data corresponding to the third data; and updating the model that predicted the third data based on the seventh data. This improves the model's predictive ability.

[0164] In some embodiments, the seventh data is a report sent by the first node that includes service experience information; the service experience information is determined based on a future scenario planning scheme sent by the second node for the first node.

[0165] In some embodiments, service experience information includes at least one of the following: the satisfaction of needs corresponding to future scenarios, measurement information corresponding to future scenarios, resource usage for planning schemes, the status of services corresponding to future scenarios, quantitative indicators of application experience for services corresponding to future scenarios, experience quality of services corresponding to future scenarios, connection stability, and satisfaction of task profiles corresponding to future scenarios.

[0166] In some embodiments, the third data is obtained by the second node and the third node or the core network element through collaborative prediction; the method further includes: sending a report including collaborative prediction information to the third node or the core network element; the collaborative prediction information includes at least one of the following: prediction accuracy information, model correction suggestions.

[0167] In some embodiments, the method further includes: sending third data to a core network element. The corresponding core network element receives the third data.

[0168] It should be noted that it is applied to Figure 1 The explanation of an embodiment of the communication method of the second node 102 in the communication system shown can be found in the following reference. Figure 1 Explanation of an embodiment of the communication method of the first node 101 in the communication system shown.

[0169] The communication method provided in this disclosure can be applied to... Figure 1 The core network element 103 in the communication system shown. Figure 6 A flowchart illustrating another communication method is shown, such as... Figure 6 As shown, the communication method includes the following S601:

[0170] S601, Receive third data from the second node.

[0171] The third data is the forecast data related to the future demand of the first node, which is predicted by the second node.

[0172] It should be noted that it is applied to Figure 1 The explanation of the embodiment of the communication method of the core network element 103 in the communication system shown can be found in the following reference: Figure 1The explanation of an embodiment of the communication method of the first node 101 in the communication system shown, or refer to... Figure 1 Explanation of an embodiment of the communication method of the second node 102 in the communication system shown.

[0173] The following is an exemplary description of the embodiments provided in this disclosure: It is assumed that the first node is a terminal and the second node is a network agent, hereinafter referred to as a base station agent or base station.

[0174] 1. The terminal performs feature data collection and reporting. The network element intelligent agent can acquire the behavioral feature data of the terminal.

[0175] The 1-1 terminal can collect characteristic data with user authorization. This includes, but is not limited to, physical layer measurements such as reference signal received power, reference signal received quality, signal-to-interference-plus-noise ratio, beam measurement results, timing advance, etc.; mobility-related data such as mobility state estimation, cell reselection priority, cell reselection count and historical records, Cell Global Identifier (CGI) related information, etc.; performance and power consumption data such as battery status, power-saving preference settings, etc.; other behavioral state data such as multi-connectivity status (connection quality of all available RATs), location change trends, wireless environment classification (environmental characteristics), signal quality change patterns, etc.; and application data such as QoS Flow Identifier (QFI) and... Features, Service Data Flow (SDF) patterns, service processing priorities, latency tolerance; cache status, such as Cache Status Report (BSR) data, Logical Channel Priority (LCP) information, data availability status, etc.; application context data, such as application type classification, expected session duration, data burst prediction, service quality sensitivity, bandwidth utilization patterns (constant / variable / bursting characteristics, etc.); user context data, such as activity status, location context (semantic location such as home / office / commuting), usage patterns (single-task / multi-task parallel usage patterns, etc.), time context (time period characteristics and regular patterns, etc.).

[0176] 1-2 Terminals report feature data under specific conditions. The triggering conditions (i.e., the above reporting conditions) include: terminal request to report, condition trigger (timed trigger, periodic trigger, specific behavior or behavior change trigger), and network element intelligent agent request to report.

[0177] Terminals 1-3 send a feature data reporting request (i.e., the first request mentioned above) to the base station agent. The request may include terminal ID, data type, data timestamp, data size, priority, etc.

[0178] After receiving the terminal's feature data reporting request, the base station returns the reporting parameter configuration (i.e., the above-mentioned reporting configuration information) to the terminal, including configuration information such as reporting period, reporting priority, and transmission QoS parameters.

[0179] After receiving the reported parameter configuration, the terminal sends a feature data report to the base station according to the configuration. The report may contain information such as terminal ID, session ID, and feature data.

[0180] The network agents 1-4 can configure the data reporting trigger conditions through feature data reporting configuration signaling. The data reporting configuration signaling may include reporting conditions, reporting period, reporting time window, etc.

[0181] The terminal reports feature data when the reporting conditions are met, based on the parameters configured by the network agent. The feature data report sent to the network agent may include data such as terminal ID, session ID, and behavioral feature data.

[0182] 1-5 The network intelligent agent can send a feature data reporting request (i.e., the second request mentioned above) to the terminal. The request may include parameters such as request ID, request priority, request data type, and response deadline.

[0183] Upon receiving the request, the terminal determines whether to accept it. If accepted, it sends a feature data reporting response to the network agent, which may include a feature data report. The feature data report may contain data such as the terminal ID, session ID, and behavioral feature data.

[0184] Terminal agents 1-6 can also perform local task profile prediction based on collected data, such as analyzing and identifying service task profiles (the user's current main service objective) and mobility task profiles, and conducting business importance assessments and resource requirement predictions. The terminal agent generates a service task profile prediction report, which may include service scenario descriptions, task profile features, environmental context summaries, resource requirements, priorities, strategy preferences, and other scenario-based task profile information (i.e., the aforementioned second data).

[0185] The terminal can send a task profile prediction report to the base station via RRC messages. This report can be sent independently or submitted together with a feature data report.

[0186] For example, such as Figure 7 The diagram shown is a flowchart of another communication method provided in this embodiment of the present disclosure, illustrating a data reporting process initiated by a terminal, including:

[0187] The terminal performs data collection;

[0188] The terminal sends a feature data reporting request to the base station;

[0189] The base station sends feature data to the terminal to report configuration.

[0190] Terminals report feature data;

[0191] Optionally, the terminal reports a task profile prediction report.

[0192] For example, such as Figure 8 The diagram shown is a flowchart of another communication method provided in this embodiment of the present disclosure, illustrating a data reporting process initiated by a base station, including:

[0193] The base station sends a feature data reporting request to the terminal;

[0194] The terminal performs data collection;

[0195] The terminal reports feature data and / or task profile prediction reports.

[0196] The 2-base station intelligent agent combines terminal feature data to predict terminal behavior and analyze task profiles, and distributes the analysis and prediction results to the corresponding network elements.

[0197] 2-1 The base station agent receives and parses data reports and / or task profile prediction reports submitted by the terminal. Based on the service task profile requirements, the base station can utilize existing base station data or collect other necessary data, such as relevant cell status data, network configuration and topology information, etc.

[0198] 2-2 Based on the collected and reported data, the base station agent integrates multi-dimensional data and performs scene recognition and prediction. It predicts cell status, user distribution pattern recognition, service demand, interference scenarios, and scenario evolution (i.e., the aforementioned behavior prediction data), and matches them with terminal task profiles and network status. The base station agent generates a terminal task profile prediction report, which may include scene descriptors, risk assessments, resource status summaries, service assurance assessments, etc. (i.e., the aforementioned task profile prediction report).

[0199] Base stations 2-3 can send prediction results for the expected scenario (such as scenario identification results, network status prediction, terminal adaptation suggestions, prediction confidence indicators, etc.) to the terminal via RRC messages (i.e., the fifth data mentioned above).

[0200] 2-4 For cross-base station scenarios, the base station can send a prediction coordination request (i.e., the third request mentioned above) to neighboring stations via Xn interface messages, which may include task profile information, scenario-based status information, coordination scenario type, resource coordination scope, priority, etc. The neighboring base station receives the coordination request and, after assessing its local resource status and coordination capabilities, replies with a coordination response (i.e., the third response mentioned above). The message may include: an agreement or rejection instruction, coordination prediction results, resource availability, limiting factors, etc.

[0201] 2-5 For scenarios that require core network participation or reporting to the core network, the base station agent generates an end-to-end collaboration requirement description and sends a predictive collaboration request (i.e., the fourth request mentioned above) to the core network NF. The message includes: task profile, RAN status report, service assurance request, etc.

[0202] The core network NF analyzes the coordination request, designs an end-to-end service guarantee scheme, and replies to the base station with a predicted coordination response (i.e., the fourth response mentioned above). The message includes: coordination prediction results, resource service strategy scheme, etc.

[0203] For example, such as Figure 9 The diagram shown is a flowchart of another communication method provided in this embodiment of the present disclosure. It illustrates the prediction process involving a terminal, base station 1, base station 2 (a base station cooperating with base station 1 to perform prediction), and core network elements, including:

[0204] Base station 1 receives reports from terminals;

[0205] Base station 1 performs data acquisition;

[0206] Base station 1 performs prediction;

[0207] Base station 1 sends the prediction results to the terminal;

[0208] Cooperative prediction process between base station 1 and base station 2:

[0209] Base station 1 sends a predictive coordination request to base station 2;

[0210] Base station 2 sends a predicted coordinated response to base station 1;

[0211] Cooperative prediction process between base station 1 and core network elements:

[0212] Base station 1 sends a predictive coordination request to the core network element;

[0213] The core network element sends a predictive coordination response to base station 1.

[0214] 3. Based on the behavior prediction results, the network intelligent agent plans and reserves resources in advance to prepare for the future needs of the terminal.

[0215] 3-1 The network intelligent agent maps the predicted terminal behavior and service requirements into specific network resource requirements, and formulates task planning and resource reservation strategies based on prediction reliability, service priority and resource availability, and determines the possible tasks and time points to be executed, the types, quantities and durations of reserved resources, etc. (i.e., the sixth data mentioned above).

[0216] Base station 3-2 sends task planning information for the expected scenario to the terminal via RRC message, such as parameter (pre)configuration (e.g., wireless parameter configuration, QoS parameter configuration), resource pre-authorization and other applicable suggestions (i.e. the task planning information for the future scenario of the first node mentioned above).

[0217] The terminal confirms the parameter application to the base station via RRC messages and replies with the reception status and execution capability.

[0218] 3-3 For cross-base station scenarios, the base station can send task planning coordination request information (i.e., the fifth request mentioned above) to the target base station through the Xn interface, which includes resource reservation strategy, parameter coordination strategy, prediction identifier, prediction time window, etc.

[0219] The target base station responds with a task planning coordination response (i.e., the fifth response mentioned above) via the X interface, which includes resource status, reservation validity period, etc.

[0220] 3-4 For cross-domain scenarios, the base station sends a task planning coordination request (i.e., the sixth request mentioned above) to the core network NF through the NG interface, which includes task profile identification, QoS requirement prediction, time window planning and resource coordination suggestions.

[0221] The core network (NF) responds to the base station with a task planning coordination response (i.e., the sixth response mentioned above) through the NG interface, which includes the status of network slice resources, transmission path preparation status, and end-to-end QoS guarantee capabilities.

[0222] For example, such as Figure 10 The diagram shown is a flowchart of another communication method provided in this embodiment of the present disclosure, illustrating the planning and prediction process of a terminal, base station 1, base station 2 (a base station cooperating with base station 1 to perform planning), and core network elements, including:

[0223] Base station 1 performs task planning;

[0224] Base station 1 sends task planning configuration to the terminal;

[0225] The terminal sends a task planning response to base station 1;

[0226] Collaborative planning process between base station 1 and base station 2:

[0227] Base station 1 sends a task planning coordination request to base station 2;

[0228] Base station 2 sends a task planning coordination response to base station 1;

[0229] Task planning process between base station 1 and core network elements:

[0230] Base station 1 sends a task planning coordination request to the core network element;

[0231] The core network element sends a task planning and coordination response to base station 1.

[0232] The four base station agents dynamically change the prediction results and planning schemes based on the actual situation and prediction deviations, and revise the prediction planning model and strategy.

[0233] 4-1 Terminal collects measurement reports and application layer service experience indicators. Additionally, the terminal agent can compare and analyze the actual experience with the original task profile to generate an experience report, including quantitative and qualitative assessments. The terminal sends a service experience report to the base station, which may include measurement information, resource usage, service status, application experience quantitative indicators, experience quality, connection stability, experience bottleneck analysis, task profile fulfillment status, etc.

[0234] 4-2 The base station agent verifies the prediction and planning results, calculates multi-dimensional prediction errors such as time dimension deviation, spatial dimension deviation, and type dimension deviation, and dynamically adjusts the planning scheme based on the prediction deviation, triggering prediction / planning updates when necessary. After the task is completed, the base station agent identifies the prediction deviation and its cause, optimizes the prediction model based on the evaluation results, and generates a prediction verification report.

[0235] 4-3 For cross-base station scenarios, the base station sends a prediction verification report to neighboring stations through the Xn interface, which includes prediction accuracy measurement, model correction suggestions, etc.

[0236] 4-4 For core network collaboration scenarios, base stations report prediction verification reports to the core network through NG interfaces, etc., including end-to-end prediction accuracy, domain-specific performance evaluation, model improvement directions, etc.

[0237] For example, such as Figure 11 The diagram shown is a flowchart of another communication method provided in this embodiment of the present disclosure, illustrating the model update process of the terminal, base station 1, base station 2 (the base station cooperating with base station 1 to execute the plan), and core network elements, including:

[0238] The terminal continuously collects data;

[0239] The terminal reports data to base station 1;

[0240] Base Station 1 Dynamic Adjustment Model;

[0241] Verification of the execution results of base station 1;

[0242] Base station 1 sends a prediction verification report to base station 2;

[0243] Base station 1 sends a prediction verification report to the core network elements.

[0244] For example, suppose in a video conferencing service quality prediction and assurance scenario (terminal and base station single-site scenario), a user is conducting an important video conference in an office building, and the agent predicts that the conference will continue and requires stable connection quality. This scenario involves the interaction between the terminal agent and a single base station agent.

[0245] at this time,

[0246] The terminal agent collects physical layer measurement data, application data, cache status (BSR indicates frequent uplink cache growth, with 8-10KB bursts every 300ms), application context (e.g., application type = "video conferencing", expected duration = 45 minutes, bandwidth mode = "two-way interactive"), and user context (e.g., activity status = "stationary", location context = "office", time context = "working hours"). The terminal sends a feature data report to the base station via RRC messages, which includes the terminal ID and the above data.

[0247] The terminal intelligent agent performs local task profile inference and generates a task profile prediction report, which includes a service scenario description (an important video conference in progress), task profile features (maintaining stable two-way communication), resource requirements (uplink GBR = 2Mbps, downlink GBR = 5Mbps, maximum jitter tolerance = 30ms), priority (high), and policy preference (stability is preferred over peak performance).

[0248] The terminal sends a task profile prediction report message to the base station via RRC messages. The message includes the terminal ID, session ID, task profile prediction report, etc.

[0249] The base station intelligent agent receives and parses the task profile prediction report reported by the terminal, integrates cell status data (current load = 45%, predicted load trend for the next 20 minutes = 10% increase) to perform scene recognition and prediction, identifies the "peak video conferencing period during working hours" scenario, and formulates resource planning schemes, including uplink reservation, downlink reservation, QoS parameters and wireless parameter adjustments.

[0250] The base station sends configurations for the expected scenario to the terminal through RRC reconfiguration messages. The messages include configuration ID, prediction base flag, radio parameters, QoS parameters, and resource pre-authorization information.

[0251] The terminal receives the configuration and applies the relevant parameters. The terminal confirms the parameter application status to the base station through the RRC response message, which includes information such as configuration ID, application status and capability matching.

[0252] The base station performs resource allocation according to the intelligent agent plan and monitors the actual cell load changes. When the cell load is detected to rise to 65%, the resource strategy is automatically adjusted.

[0253] The terminal intelligent agent monitors the meeting experience quality, collecting data such as application-layer frame rate, audio quality metrics, video freeze events, and end-to-end latency. The terminal reports experience metrics to the base station via status reports, including session ID, service quality metrics, task profile satisfaction, and resource utilization.

[0254] The base station agent validates the prediction and planning results by comparing the actual conference duration, actual resource requirements, and cell load prediction errors. Based on the validation results, the prediction model is updated, and the base station agent can adjust the conference duration model parameters, working time load prediction weights, and video conference traffic characteristic models.

[0255] For example, consider terminal mobility management in a cross-base station collaborative scenario. A user is traveling on a high-speed train and uses streaming media services while moving at high speed. The intelligent agent predicts the user's trajectory and handover timing, coordinating with multiple base stations to achieve seamless service continuity. This scenario involves collaboration between the terminal intelligent agent and multiple base station intelligent agents.

[0256] at this time,

[0257] The terminal intelligent agent collects data such as physical layer measurements, mobility-related data, location change trends, wireless environment classification (along high-speed railway lines), application data, and GPS coordinate history (if authorized by the user).

[0258] The terminal intelligent agent performs mobility task profile reasoning and generates a mobility task profile prediction report, which includes information such as mobile scene, trajectory prediction, speed prediction and service continuity requirements.

[0259] The terminal sends routine measurement results and mobility prediction information to the serving base station via RRC messages, including terminal ID, serving cell measurement value, neighboring cell measurement value, mobility context, and mobility task profile prediction report.

[0260] Terminals report service continuity requirements via RRC messages, including information such as service context, continuity requirements, buffer capacity, and handover tolerance configuration.

[0261] The serving base station agent receives and parses the mobility prediction information reported by the terminal, combines the cell topology and historical high-speed movement patterns to improve mobility prediction, confirm that the terminal is located on the high-speed rail line, estimate the handover time point, and analyze potential coverage challenges.

[0262] The serving base station (gNB1) sends a prediction coordination request to the target base station on the prediction path through Xn interface messages, which includes information such as request ID, request priority, mobility context, coordination request type and resource coordination scope.

[0263] The target base station (gNB2) assesses the local resource status and replies with a prediction coordination response message through the Xn interface, which includes information such as response ID, coordination prediction result, resource availability and handover parameters.

[0264] The serving base station (gNB1) can similarly perform the same operation as other base stations (gNB3, gNB4) on the predicted path.

[0265] Based on the collaborative results with the target base station, the serving base station agent formulates a complete mobility plan, including handover sequence and timing, parameter adjustment scheme, critical area processing, and resource reservation coordination.

[0266] The serving base station (gNB1) sends mobility parameters to the terminal via RRC reconfiguration messages, including configuration ID, prediction base flag, mobility parameters, and predictive guidance information.

[0267] The terminal generates a measurement report according to the optimized configuration. At the predicted time point, cell handover is triggered.

[0268] The terminal intelligent agent monitors service continuity throughout the high-speed rail journey, including indicators such as streaming media playback interruptions, buffering events, and switching completion times.

[0269] The terminal sends a service quality report to the current serving base station via RRC messages, which includes information such as session ID, mobility performance, and service impact assessment.

[0270] The base station intelligent agent verifies the accuracy of predictions and evaluates cell sequence prediction, timing prediction errors, and handover optimization effects.

[0271] Example 3: Airport Travel Scenario Service Guarantee

[0272] Scene Description

[0273] A user is traveling from the city center to the airport and is expected to require uninterrupted map navigation, instant messaging, and flight information services. The intelligent agent predicts changes in the user's movement trajectory, network coverage, and service demands, and coordinates multiple base stations and core network resources to ensure continuous service throughout the journey and guarantee service quality during critical moments.

[0274] Implementation steps

[0275] With user authorization, the terminal intelligent agent collects data such as physical layer measurements, location change trends (location trajectory shows the user moving along the main urban road, pointing towards the airport), application usage (navigation application is active, airline APP is recently opened, and messaging application is active in the background), calendar and travel data, and movement speed (35km / h, indicating that the user may be in a vehicle).

[0276] The terminal intelligent agent performs journey task profile reasoning and generates a travel task profile prediction report, which includes information such as journey destination, expected route, time constraints and key service requirements.

[0277] The terminal sends a journey profile report to the serving base station via RRC messages, which includes information such as terminal ID, session ID, journey type, destination type, time window constraints, and priority services.

[0278] The terminal also reports route prediction information, including predicted route coordinates, estimated transit time, predicted stop points, and prediction reliability.

[0279] The base station agent receives and parses the journey task profile information reported by the terminal, and combines it with road topology and historical travel data to improve path prediction (such as the most likely route, key coverage challenge areas, predicted arrival time at the airport, and service changes).

[0280] The serving base station (gNB1) sends a prediction coordination request to the base stations on the prediction path through Xn interface messages, which includes information such as request ID, journey information, prediction path, estimated transit time and service guarantee requirements.

[0281] Base stations along the path assess local resource conditions and respond with predictive collaborative response messages via the Xn interface, including information such as coverage status, resource availability, potential risk points, and optimization suggestions.

[0282] For areas with weak tunnel coverage, an optimization scheme for negotiation and handover parameters between base stations was developed.

[0283] The serving base station (gNB1) sends a service assurance request to the core network through NG interface messages, which includes information such as terminal ID, journey type, time sensitivity, service continuity requirements and key service identifiers.

[0284] The core network agent analyzes travel needs and identifies potential risks in the high-density network of the airport area.

[0285] The core network NF responds to the predicted coordination request response message through the NG interface and other means, which includes information such as end-to-end service guarantee scheme, priority adjustment strategy, network slicing configuration and airport area resource reservation.

[0286] The base station agent, combining cross-base station collaboration and core network collaboration results, formulates a complete journey assurance plan and sends journey optimization configurations to the terminal via RRC reconfiguration messages. This configuration includes configuration IDs, mobility parameters, quality of service parameters, and network prediction information. The configuration may include network prediction guidance information, informing the location of weak tunnel coverage, high-density areas near airports, and targeted adaptation suggestions.

[0287] The terminal receives the configuration and confirms the application status via an RRC response message.

[0288] When a user enters a highway section, the terminal measurement report shows that the moving speed increases to 80 km / h. The serving base station uses handover parameters optimized for highway scenarios and sends a preparation message to the preceding base station in advance.

[0289] Before the user approaches the tunnel, the terminal agent can provide navigation application with pre-buffered route data based on network predictions.

[0290] The base station agent detects that a user has entered the airport area and activates the pre-coordinated airport area service enhancement configuration.

[0291] The terminal receives the RRC reconfiguration message, applies airport area-specific parameters, and prioritizes the application of communication and flight information.

[0292] The core network NF also applies the airport area service strategy, using session management functions to prioritize flight information and communication applications.

[0293] The terminal intelligent agent monitors the service experience throughout the journey and provides feedback to the current service base station through status reports, including information such as journey segment assessment, service continuity score, and key service performance.

[0294] The base station agent verifies the accuracy of journey prediction, updates the individual travel model, and adjusts the commuter-airport route model and time estimation parameters.

[0295] The base station agent sends a journey prediction verification report to the core network via the NG interface, which includes information such as prediction verification results, model adjustment suggestions, and service mode insights.

[0296] The disclosed embodiments can divide the communication device into functional modules according to the above method embodiments. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one functional module. The integrated module can be implemented in hardware or software. It should be noted that the module division in this disclosed embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the example of dividing each functional module according to each function.

[0297] Figure 12 This is a schematic diagram of a communication device provided in an embodiment of this disclosure. The communication device can execute the communication method provided in the above-described method embodiments. Figure 12 As shown, the communication device includes a processing module 1201 and a transmitting module 1202.

[0298] Processing module 1201 is used to collect first data; the first data is the data used for the second node to perform prediction.

[0299] The sending module 1202 is used to send a first report to the second node, the first report including first data.

[0300] In some embodiments, the first data includes at least one of the following:

[0301] Data related to physical layer measurements, mobility management, application data, application context data, cache status, behavior status data, user context data, and performance and power consumption data of the first node.

[0302] In some embodiments, the first report also includes at least one of the following:

[0303] The identifier of the first node, and the identifier of the session associated with the first report.

[0304] In some embodiments, a first report is sent to the second node in one of the following cases:

[0305] The first node requests to submit the first report;

[0306] The second node requests the first node to submit the first report;

[0307] The first report is submitted in response to the reporting conditions triggering the reporting.

[0308] In some embodiments, the reporting of a first report in response to reporting conditions includes at least one of the following:

[0309] Timed triggering, periodic triggering, response to specific behavior, response to changes in specific behavior.

[0310] In some embodiments, the sending module 1202 is specifically used to send a first request to the second node; the first request is used to request the reporting of a first report.

[0311] In some embodiments, the first request includes at least one of the following: the identifier of the first node, the type of the first data, the timestamp of the first data, the size of the first data, and the priority of the first report.

[0312] In some embodiments, the communication device further includes a receiving module 1203, which is configured to receive a first response from a second node; the first response is used to indicate whether the first node is allowed to report a first report.

[0313] The sending module 1202 is specifically used to send a first report to a second node when the first response indicates that the first node is allowed to report a first report.

[0314] In some embodiments, where the first response is used to indicate permission for the first node to report a first report, the first response includes reporting configuration information;

[0315] The sending module 1202 is specifically used to send the first report to the second node based on the reported configuration information.

[0316] In some embodiments, when the second node requests the first node to report a first report, the receiving module 1203 is configured to receive a second request from the second node; the second request is used to request the first node to send the first report.

[0317] The sending module 1202 is used to send a first report to the second node based on the second request.

[0318] In some embodiments, the second request includes at least one of the following: a request identifier, a request priority, a data type to be reported, and a response deadline.

[0319] In some embodiments, the sending module 1202 is configured to send a first report to a second node if it is determined, based on a second request, that a first report can be sent.

[0320] In some embodiments, when a report is triggered in response to a reporting condition, the receiving module 1203 is further configured to receive a first signaling; the first signaling is configured to configure the reporting conditions.

[0321] In some embodiments, the first signaling is also used to configure the reporting resources and / or reporting methods.

[0322] In some embodiments, the processing module 1201 is further configured to predict and obtain second data;

[0323] The sending module 1202 is also used to send a second report to the second node, the second report including second data.

[0324] In some embodiments, the second data includes at least one of the following:

[0325] Service task profiles, mobility task profiles, business importance assessment information, and resource demand forecasting information.

[0326] In some embodiments, the service task profile includes at least one of the following:

[0327] Service scenario information, task profile features, environmental context information, resource requirement information, priority information, strategy preference information, and other scenario-based task profile information besides service scenarios.

[0328] In some embodiments, the second report is sent together with the first report; or...

[0329] The second report was sent independently from the first report.

[0330] Figure 13 This is a schematic diagram of another communication device provided in an embodiment of this disclosure. The communication device can execute the communication method provided in the above-described method embodiments. Figure 13As shown, the communication device includes a receiving module 1301 and a processing module 1302.

[0331] The receiving module 1301 is configured to receive a report from the first node; the report includes first data and / or second data; the first data is data used to perform prediction; the second data is data predicted by the first node;

[0332] The processing module 1302 is used to predict and obtain third data based on the report; the third data is the predicted data related to the future demand of the first node.

[0333] In some embodiments, the processing module 1302 is specifically used to acquire fourth data; the fourth data is auxiliary data collected or stored by the second node for performing task profile prediction; and the third data is obtained based on the report and the fourth data.

[0334] In some embodiments, the third data includes the behavior prediction data of the first node and / or the task profile prediction report of the first node.

[0335] In some embodiments, the behavior prediction data of the first node includes at least one of the following:

[0336] Predicted information on cell status corresponding to the first node, predicted information on user distribution pattern corresponding to the first node, predicted information on service demand of the first node, predicted information on interference scenario corresponding to the first node, and predicted information on scenario evolution of the first node.

[0337] In some embodiments, the task profile prediction report of the first node includes at least one of the following:

[0338] Scenario description information, risk assessment information, resource status information, and service guarantee assessment information.

[0339] In some embodiments, the processing module 1302 is further configured to generate fifth data based on the third data; the fifth data is used to indicate relevant prediction information for the future scenario of the first node;

[0340] The communication device also includes a transmitting module 1303, which is used to transmit fifth data to the first node.

[0341] In some embodiments, the fifth data includes at least one of the following: prediction results of the future scenario of the first node, confidence information of the prediction results, and planning strategies for the future scenario of the first node.

[0342] In some embodiments, the third data is obtained by the second node and the third node through collaborative prediction; the sending module 1303 is further configured to send a third request to the third node; the third request is used to request the third node to conduct collaborative prediction.

[0343] The receiving module 1301 is also used to receive a third response from a third node; the third response is the third node's response to the third request.

[0344] In some embodiments, the third request includes at least one of the following:

[0345] Task profile information, collaborative prediction strategy, collaborative prediction scenario type, collaborative prediction scope, and collaborative prediction priority.

[0346] In some embodiments, the third response includes one of the following:

[0347] The third node agrees to collaboration, the information predicted by the third node, the amount of available resources of the third node, the reservation validity period of the available resources of the third node, and the corresponding limiting factors of the third node.

[0348] The third node refuses to cooperate.

[0349] In some embodiments, the third data is obtained by the second node and the core network element through collaborative prediction; the sending module 1303 is further configured to send a fourth request to the core network element; the fourth request is used to request the core network element to conduct collaborative prediction.

[0350] The receiving module 1301 is also used to receive a fourth response from a core network element; the fourth response is the core network element's response to the third request.

[0351] In some embodiments, the fourth request includes at least one of the following:

[0352] Task profile information, status information of the second node, and service support requests.

[0353] In some embodiments, the fourth response includes one of the following:

[0354] At least one of the following: core network element coordination, core network element prediction information, and resource service strategy;

[0355] Core network elements refuse to cooperate.

[0356] In some embodiments, the third data includes at least one of the following: behavior prediction information of the first node, business demand prediction information of the first node, prediction confidence, and the priority of the predicted business.

[0357] In some embodiments, the processing module 1302 is further configured to determine sixth data based on the third data; the sixth data includes task planning information and resource reservation strategies for future scenarios of the first node.

[0358] In some embodiments, the sending module 1303 is further configured to send task planning information for the future scenario of the first node to the first node.

[0359] In some embodiments, the sixth data is determined collaboratively by the second node and the third node. The sending module 1303 is further configured to send a fifth request to the third node; the fifth request is used to request the third node to collaboratively determine the sixth data.

[0360] The receiving module 1301 is also used to receive a fifth response from the third node; the fifth response is the third node's response to the fifth request.

[0361] In some embodiments, the fifth request includes one of the following:

[0362] The third node agrees to at least one of the following: coordination, resource reservation strategy, parameter coordination strategy, prediction identifier, and prediction time window;

[0363] The third node refuses to cooperate.

[0364] In some embodiments, the fifth response includes at least one of the following: resource status information, and the reservation validity period of the reserved resources.

[0365] In some embodiments, the sixth data is determined collaboratively by the second node and the core network element. The sending module 1303 is further configured to send a sixth request to the core network element; the sixth request is used to request the core network element to collaboratively determine the sixth data.

[0366] The receiving module 1301 is also used to receive a sixth response from a core network element; the sixth response is the core network element's response to the sixth request.

[0367] In some embodiments, the sixth request includes at least one of the following:

[0368] Task profile information, service quality flow demand forecast information, time window planning information, and resource collaboration suggestion information.

[0369] In some embodiments, the sixth response includes one of the following:

[0370] At least one of the following: core network element coordination, core network element resource status information, transmission path readiness, and quality of service flow assurance capability;

[0371] Core network elements refuse to cooperate.

[0372] In some embodiments, the processing module 1302 is further configured to acquire seventh data; the seventh data is the actual data corresponding to the third data; and based on the seventh data, to update the model that predicts the third data.

[0373] In some embodiments, the seventh data is a report sent by the first node that includes service experience information; the service experience information is determined based on a future scenario planning scheme sent by the second node for the first node.

[0374] In some embodiments, service experience information includes at least one of the following:

[0375] The following information is provided: the satisfaction of needs corresponding to future scenarios, measurement information corresponding to future scenarios, resource usage for planning schemes, business status corresponding to future scenarios, quantitative indicators of application experience for business corresponding to future scenarios, experience quality of business corresponding to future scenarios, connection stability, and satisfaction of task profiles corresponding to future scenarios.

[0376] In some embodiments, the third data is obtained by the second node and the third node or the core network element through collaborative prediction; the sending module 1303 is further configured to send a report including collaborative prediction information to the third node or the core network element; the collaborative prediction information includes at least one of the following: prediction accuracy information, model correction suggestions.

[0377] In some embodiments, the sending module 1303 is further configured to send third data to the core network element.

[0378] Figure 14 This is a schematic diagram of another communication device provided in an embodiment of this disclosure. The communication device can execute the communication method provided in the above-described method embodiments. Figure 14 As shown, the communication device includes: a receiving module 1401.

[0379] The receiving module 1401 is used to receive third data from the second node, which is the predicted data of the second node related to the future demand of the first node.

[0380] In implementing the functionality of the integrated modules described above using hardware, this disclosure provides another possible structure for the communication device involved in the above embodiments. For example... Figure 15 As shown, the communication device includes: a processor 1502 and a bus 1504. Optionally, the communication device may also include a memory 1501; alternatively, the communication device may also include a communication interface 1503.

[0381] Processor 1502 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 1502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 1502 may also be a combination of functions implementing computation, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0382] The communication interface 1503 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0383] The memory 1501 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0384] In one possible implementation, the memory 1501 can exist independently of the processor 1502. The memory 1501 can be connected to the processor 1502 via a bus 1504 and is used to store instructions or program code. When the processor 1502 calls and executes the instructions or program code stored in the memory 1501, it can implement the method provided in the embodiments of this disclosure.

[0385] In another possible implementation, the memory 1501 can also be integrated with the processor 1502.

[0386] The 1504 bus can be an extended industry standard architecture (EISA) bus, etc. The 1504 bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 15 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0387] Some embodiments of this disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) storing computer program instructions that, when executed on a computer, cause the computer to perform the methods described in any of the above embodiments.

[0388] For example, the computer-readable storage media described above may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical disks (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0389] This disclosure provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in any of the above embodiments.

[0390] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applied to the first node, the method includes: Collect the first data; the first data is used for the second node to perform prediction. Send a first report to the second node, the first report including the first data.

2. The method according to claim 1, characterized in that, The first data includes at least one of the following: Data related to physical layer measurements, mobility management, application data, application context data, cache status, behavior status data, user context data, and the performance and power consumption data of the first node.

3. The method according to claim 1, characterized in that, The first report also includes at least one of the following: The identifier of the first node and the identifier of the session associated with the first report.

4. The method according to claim 1, characterized in that, Send the first report to the second node under one of the following circumstances: The first node requests to report the first report; The second node requests the first node to report the first report; The first report is submitted in response to the reporting conditions that trigger the submission.

5. The method according to claim 4, characterized in that, The response to the reporting condition triggering the reporting of the first report includes at least one of the following: Timed triggering, periodic triggering, response to specific behavior, response to changes in specific behavior.

6. The method according to claim 4, characterized in that, When the first node requests to report the first report, the method further includes: Send a first request to the second node; the first request is used to request the reporting of the first report.

7. The method according to claim 6, characterized in that, The first request includes at least one of the following: the identifier of the first node, the type of the first data, the timestamp of the first data, the size of the first data, and the priority of the first report.

8. The method according to claim 6, characterized in that, The method further includes: Receive a first response from the second node; the first response is used to indicate whether the first node is allowed to report the first report. Sending the first report to the second node includes: If the first response indicates that the first node is allowed to report the first report, the first report is sent to the second node.

9. The method according to claim 8, characterized in that, When the first response is used to indicate that the first node is allowed to report the first report, the first response includes reporting configuration information; Sending the first report to the second node includes: Based on the reported configuration information, a first report is sent to the second node.

10. The method according to claim 4, characterized in that, When the second node requests the first node to report the first report, the method further includes: Receive a second request from the second node; the second request is used to request the first node to send the first report; Sending the first report to the second node includes: sending the first report to the second node based on the second request.

11. The method according to claim 10, characterized in that, The second request includes at least one of the following: request identifier, request priority, data type of the request, and response deadline.

12. The method according to claim 10, characterized in that, Sending the first report to the second node based on the second request includes: If it is determined that the first report can be sent based on the second request, the first report is sent to the second node.

13. The method according to claim 4, characterized in that, In response to a reporting condition triggering the reporting of the report, the method further includes: Receive the first signaling; the first signaling is used to configure the reporting conditions.

14. The method according to claim 13, characterized in that, The first signaling is also used to configure the reporting resources and / or reporting methods.

15. The method according to claim 1, characterized in that, The method further includes: The second data was obtained from the prediction; A second report is sent to the second node, the second report including the second data.

16. The method according to claim 15, characterized in that, The second data includes at least one of the following: Service task profiles, mobility task profiles, business importance assessment information, and resource demand forecasting information.

17. The method according to claim 16, characterized in that, The service task profile includes at least one of the following: Service scenario information, task profile features, environmental context information, resource requirement information, priority information, strategy preference information, and other scenario-based task profile information besides service scenarios.

18. The method according to claim 15, characterized in that, The second report is sent together with the first report; or, The second report is sent independently from the first report.

19. A communication method, characterized in that, Applied to the second node, the method includes: Receive a report from a first node; the report includes first data and / or second data; the first data is data used to perform a prediction; the second data is data predicted by the first node. Based on the report, a third set of data is predicted; the third set of data is the predicted data related to the future demand of the first node.

20. The method according to claim 19, characterized in that, The prediction of third data based on the report includes: Acquire the fourth data; the fourth data is auxiliary data collected or stored by the second node for performing task profile prediction; The third data is obtained based on the report and the fourth data.

21. The method according to claim 19, characterized in that, The third data includes the behavior prediction data of the first node and / or the task profile prediction report of the first node.

22. The method according to claim 21, characterized in that, The behavior prediction data of the first node includes at least one of the following: The predicted information includes the cell status corresponding to the first node, the predicted user distribution pattern corresponding to the first node, the predicted service demand of the first node, the predicted interference scenario corresponding to the first node, and the predicted scenario evolution of the first node.

23. The method according to claim 21, characterized in that, The task profile prediction report of the first node includes at least one of the following: Scenario description information, risk assessment information, resource status information, and service guarantee assessment information.

24. The method according to claim 19, characterized in that, The method further includes: Fifth data is generated based on the third data; the fifth data is used to indicate relevant prediction information for the future scenario of the first node. Send the fifth data to the first node.

25. The method according to claim 24, characterized in that, The fifth data includes at least one of the following: the prediction result of the future scenario of the first node, the credibility information of the prediction result, and the planning strategy for the future scenario of the first node.

26. The method according to claim 19, characterized in that, The third data is obtained through collaborative prediction by the second node and the third node; the method further includes: Send a third request to the third node; the third request is used to request the third node to cooperate in prediction; Receive a third response from the third node; the third response is the third node's response to the third request.

27. The method according to claim 26, characterized in that, The third request includes at least one of the following: Task profile information, collaborative prediction strategy, collaborative prediction scenario type, collaborative prediction scope, and collaborative prediction priority.

28. The method according to claim 26, characterized in that, The third response includes one of the following: The third node agrees to collaborate, the information predicted by the third node, the number of available resources of the third node, the reservation validity period of the available resources of the third node, and the limiting factors corresponding to the third node; at least one of these is required. The third node refused to cooperate.

29. The method according to claim 19, characterized in that, The third data is obtained through collaborative prediction between the second node and core network elements; the method further includes: A fourth request is sent to the core network element; the fourth request is used to request the core network element to cooperate in prediction. Receive a fourth response from the core network element; the fourth response is the core network element's response to the third request.

30. The method according to claim 29, characterized in that, The fourth request includes at least one of the following: Task profile information, status information of the second node, and service assurance request.

31. The method according to claim 29, characterized in that, The fourth response includes one of the following: At least one of the following: core network element agreement and coordination, information predicted by the core network element, and resource service strategy; The core network element refused to cooperate.

32. The method according to claim 19, characterized in that, The third data includes at least one of the following: behavior prediction information of the first node, business demand prediction information of the first node, prediction credibility, and the priority of the predicted business.

33. The method according to claim 32, characterized in that, The method further includes: The sixth data is determined based on the third data; the sixth data includes task planning information and resource reservation strategies for the future scenarios of the first node.

34. The method according to claim 33, characterized in that, The method further includes: Send the task planning information for the future scenario of the first node to the first node.

35. The method according to claim 33, characterized in that, The sixth data is determined collaboratively by the second node and the third node, and the method further includes: Send a fifth request to the third node; the fifth request is used to request the third node to cooperate in determining the sixth data; Receive a fifth response from the third node; the fifth response is the third node's response to the fifth request.

36. The method according to claim 35, characterized in that, The fifth request includes one of the following: The third node agrees to at least one of the following: coordination, resource reservation strategy, parameter coordination strategy, prediction identifier, and prediction time window; The third node refused to cooperate.

37. The method according to claim 35, characterized in that, The fifth response includes at least one of the following: resource status information, and the reservation validity period of reserved resources.

38. The method according to claim 33, characterized in that, The sixth data is determined collaboratively by the second node and the core network elements, and the method further includes: A sixth request is sent to the core network element; the sixth request is used to request the core network element to collaboratively determine the sixth data. Receive a sixth response from the core network element; the sixth response is the core network element's response to the sixth request.

39. The method according to claim 38, characterized in that, The sixth request includes at least one of the following: Task profile information, service quality flow demand forecast information, time window planning information, and resource collaboration suggestion information.

40. The method according to claim 38, characterized in that, The sixth response includes one of the following: The core network element agrees to coordinate, the core network element's resource status information, transmission path preparation status, and service quality flow guarantee capability are at least one of the following: The core network element refused to cooperate.

41. The method according to claim 19, characterized in that, The method further includes: Obtain the seventh data; the seventh data is the actual data corresponding to the third data. Based on the seventh data, the model that predicted the third data is updated.

42. The method according to claim 41, characterized in that, The seventh data is a report sent by the first node that includes service experience information; the service experience information is determined based on a future scenario planning scheme sent by the second node for the first node.

43. The method according to claim 42, characterized in that, The service experience information includes at least one of the following: The following information is provided: the satisfaction status of the requirements corresponding to the future scenario, the measurement information corresponding to the future scenario, the resource usage of the planning scheme, the status of the business corresponding to the future scenario, the application experience quantitative indicators of the business corresponding to the future scenario, the experience quality of the business corresponding to the future scenario, the connection stability, and the satisfaction status of the task profile corresponding to the future scenario.

44. The method according to claim 19, characterized in that, The third data is obtained through collaborative prediction between the second node and the third node or core network elements; the method further includes: Send a report including collaborative prediction information to the third node or core network element; the collaborative prediction information includes at least one of the following: prediction accuracy information, model correction suggestions.

45. The method according to claim 19, characterized in that, The method further includes: The third data is sent to the core network element.

46. ​​A communication method, characterized in that, Applied to core network elements, the method includes: Receive third data from the second node, which is a prediction by the second node related to the future demand of the first node.

47. A communication device, characterized in that, include: Memory and processor; Memory and processor are coupled; The memory is used to store instructions that can be executed by the processor; When the processor executes the instructions, it performs the method as described in any one of claims 1-18, or the method as described in any one of claims 19-45, or the method as described in claim 46.

48. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-18, or the method as described in any one of claims 19-45, or the method as described in claim 46.

49. A computer program product, characterized in that, The computer program product includes computing technology program instructions, which, when executed by a processor, implement the method as described in any one of claims 1-18, or implement the method as described in any one of claims 19-45, or implement the method as described in claim 46.

Images