Wireless access network, node thereof, data collection and processing method and system

Abstract

The present disclosure relates to a wireless access network (RAN), its nodes, and a data collection and processing method and system. The RAN data collection and processing method includes: a RAN node receiving an artificial intelligence (AI) function request sent by a peer RAN node based on demand; and the RAN node accepting or rejecting the AI ​​function request based on its own circumstances. The present disclosure can support NG-RAN triggering or rejecting AI functions on demand from other NG-RAN nodes.

Description

Technical Field

[0001] The present disclosure relates to the fields of 5G, B5G and 6G wireless communication systems, and in particular to a wireless access network and its nodes, as well as a data collection and processing method and system. Background Art

[0002] Wireless networks will incorporate artificial intelligence and big data technologies to cope with increasingly complex heterogeneous networks and diverse communication scenarios. Data can be collected from terminals, network equipment (such as RAN (Radio Access Network), CN (Core Network), and OAM (Operation Administration and Maintenance)), as well as external devices (such as sensors, third-party applications, infrastructure, and other types of networks). Artificial intelligence (AI) algorithms can classify, analyze, and reason based on this data, ultimately generating conclusions such as analysis, prediction, and recommendations. Summary of the Invention

[0003] The present disclosure provides a wireless access network and its nodes, as well as a data collection and processing method and system, which support network nodes to trigger or reject AI functions to other network nodes according to needs.

[0004] According to one aspect of the present disclosure, a method for collecting and processing wireless access network data is provided, comprising:

[0005] The wireless access network node receives an artificial intelligence function request sent by the opposite wireless access network node according to demand;

[0006] The wireless access network node accepts or refuses to receive the artificial intelligence function request based on the node's own situation.

[0007] In some embodiments of the present disclosure, the artificial intelligence function request includes one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

[0008] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0009] When the wireless access network node accepts the artificial intelligence function request, it sends the measurement configuration related to this artificial intelligence function request to the user terminal;

[0010] The radio access network node receives measurement data and information reported by the user terminal.

[0011] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0012] Wireless access network nodes obtain network data and information used for AI model training from adjacent nodes through AI-related request signaling.

[0013] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0014] Wireless access network nodes train AI models based on the information required for different scenarios;

[0015] The wireless access network node uses artificial intelligence model deployment signaling to send the trained artificial intelligence model to the peer wireless access network node;

[0016] The wireless access network node receives availability information of the artificial intelligence model fed back by the opposite wireless access network node.

[0017] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0018] The wireless access network node performs model inference based on the necessary information and the trained artificial intelligence model, and outputs the inference result information;

[0019] The wireless access network node adjusts its own configuration or measurement based on the inference result information, or instructs the user terminal to take corresponding actions.

[0020] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0021] The wireless access network node receives performance feedback from the peer wireless access network node regarding the current artificial intelligence model. For specific artificial intelligence use cases, the peer wireless access network node also performs model inference based on necessary information and the trained artificial intelligence model, and outputs inference result information.

[0022] According to another aspect of the present disclosure, a method for collecting and processing wireless access network data is provided, comprising:

[0023] The wireless access network node sends an artificial intelligence function request to the wireless access network node at the opposite end according to the demand;

[0024] The wireless access network node receives the request feedback information sent by the opposite wireless access network node, wherein the request feedback information includes the acceptance or rejection information of the opposite wireless access network node to the artificial intelligence function request based on the node's own situation.

[0025] In some embodiments of the present disclosure, the artificial intelligence function request includes one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

[0026] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0027] The wireless access network node receives artificial intelligence related request signaling sent by the adjacent node;

[0028] The wireless access network node feeds back the network data and information used for artificial intelligence model training to the adjacent node.

[0029] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0030] The wireless access network node receives the trained artificial intelligence model sent by the peer wireless access network node through artificial intelligence model deployment signaling;

[0031] The wireless access network node feeds back the availability information of the artificial intelligence model to the opposite wireless access network node.

[0032] In some embodiments of the present disclosure, the wireless access network data collection and processing method further includes:

[0033] For specific AI use cases, the wireless access network node performs model inference based on the necessary information and the trained AI model, and outputs the inference result information;

[0034] The wireless access network node feeds back the performance of the artificial intelligence model to the wireless access network node at the other end.

[0035] According to another aspect of the present disclosure, a wireless access network node is provided, including:

[0036] A request function receiving module is used to receive an artificial intelligence function request sent by a wireless access network node on the opposite end according to demand;

[0037] The request function feedback module is used to accept or reject the artificial intelligence function request based on the node's own situation.

[0038] In some embodiments of the present disclosure, the wireless access network node is used to perform operations to implement the wireless access network data collection and processing method as described in any of the above embodiments.

[0039] According to another aspect of the present disclosure, a wireless access network node is provided, including:

[0040] A function request sending module is used to send an artificial intelligence function request to the wireless access network node at the opposite end according to demand;

[0041] A request feedback information receiving module is used to receive request feedback information sent by the opposite wireless access network node, wherein the request feedback information includes acceptance or rejection information of the opposite wireless access network node for the artificial intelligence function request based on the node's own situation.

[0042] In some embodiments of the present disclosure, the wireless access network node is used to perform operations to implement the wireless access network data collection and processing method as described in any of the above embodiments.

[0043] According to another aspect of the present disclosure, a wireless access network node is provided, including:

[0044] a memory for storing instructions;

[0045] The processor is configured to execute the instruction so that the wireless access network node performs operations to implement the wireless access network data collection and processing method as described in any one of the above embodiments.

[0046] According to another aspect of the present disclosure, a wireless access network data collection and processing system is provided, including the wireless access network node as described in any one of the above embodiments.

[0047] According to another aspect of the present disclosure, a wireless access network is provided, comprising the wireless access network node as described in any one of the above embodiments, or comprising the wireless access network data collection and processing system as described in any one of the above embodiments.

[0048] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the wireless access network data collection and processing method as described in any of the above embodiments is implemented.

[0049] The present disclosure may support NG-RAN to trigger or reject AI functions to other NG-RAN nodes as needed. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0051] Figure 1 The figure is a schematic diagram of some embodiments of the wireless access network data collection and processing system disclosed in the present invention.

[0052] Figure 2The present invention provides a schematic diagram of some embodiments of the method for collecting and processing wireless access network data.

[0053] Figure 3 Schematic diagram of other embodiments of the method for collecting and processing wireless access network data disclosed in the present invention.

[0054] Figure 4 Schematic diagram of some further embodiments of the method for collecting and processing wireless access network data disclosed herein.

[0055] Figure 5 Schematic diagram of some further embodiments of the method for collecting and processing wireless access network data disclosed herein.

[0056] Figure 6 Schematic diagram of some embodiments of a wireless access network node disclosed herein.

[0057] Figure 7 Schematic diagram of some other embodiments of the wireless access network node disclosed in the present invention.

[0058] Figure 8 Schematic diagram of the structure of some further embodiments of the wireless access network node disclosed in the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0060] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0061] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0062] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0063] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0064] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0065] Through research, the inventors discovered that the 3GPP RAN3 working group is also currently studying technical solutions for wireless network big data collection and intelligent processing. This project aims to study the intelligent framework of RAN through use cases, analyze the impact on existing protocol interfaces, discuss the collection of wireless network data, and discuss system optimization solutions based on AI technology. The main application scenarios include network energy saving, mobility optimization, load balancing, etc.

[0066] Figure 1 The figure is a schematic diagram of some embodiments of the wireless access network data collection and processing system disclosed in the present invention. Figure 1 A schematic diagram of the related technology Radio Access Network (RAN) intelligent functional framework (Functional Framework for RAN Intelligence) is also given.

[0067] like Figure 1 As shown, the wireless access network data collection and processing system disclosed herein may include a data collection module 100, a model training module 200, a model inference module 300, an execution module 400, and a feedback module 500, wherein:

[0068] The Data Collection module 100 is a functional module that provides input data to the Model Training module 200 and the Model Inference module 300. Input data may include measurements from UEs (User Equipment) or different network entities, performance feedback, and AI / ML (Machine Learning) model outputs. Data types include training data (information required for model training) and inference data (input information required for model inference).

[0069] The model inference module 200 is a functional module that performs ML model training. The model inference module 200 can also complete data preparation work as needed, where data preparation work can include data preprocessing and cleaning, formatting, and raw data conversion.

[0070] In some embodiments of the present disclosure, the model training module 200 can also be used to deploy or update the trained model to the model reasoning module 300.

[0071] The model inference module 300 is a functional module that provides AI / ML model inference output (e.g., prediction or decision). The model inference module 300 can also be used to complete data preparation tasks as needed, including data preprocessing and cleaning, formatting, and raw data conversion.

[0072] In some embodiments of the present disclosure, the model reasoning module 300 can also be used to provide model performance feedback to the model training module 200.

[0073] The execution module (Actor) 400 is a functional module for receiving the output from the Model reasoning function and triggering or executing corresponding operations, which can trigger actions of other entities or itself.

[0074] Feedback module 500 is used to obtain information that may be needed for training or inference data or performance feedback.

[0075] In some embodiments of the related technology, during the model training process, the transmission of a large amount of user and network data will cause transmission delays. For some specific use cases, such as UE trajectory prediction, base station traffic prediction, etc., there are high requirements for real-time data processing, and the network's corresponding actions based on AI output results are also expected to be completed in a shorter time. Therefore, in such use cases, the model training module needs to be deployed on the NG-RAN (5G wireless access network) side.

[0076] In some embodiments of the related technology, model reasoning is mainly based on real-time network data and trained AI models to infer corresponding outputs (such as predictions or decisions, etc.). Considering the timeliness of data collection and decision implementation, the model reasoning module is generally deployed on the RAN node.

[0077] Based on this, this disclosure mainly focuses on the deployment model in which both the model training module and the model inference module are located in the RAN node, and designs the network signaling process related to AI management to support the intelligence of the wireless network. In turn, the network can leverage the advantages of AI algorithms in prediction and recommendation to optimize the wireless network configuration and improve the performance of the wireless network system.

[0078] The present disclosure is described below through specific embodiments.

[0079] Figure 2 The present invention is a schematic diagram of some embodiments of the wireless access network data collection and processing method. Preferably, this embodiment can be implemented by the wireless access network of the present invention, the wireless access network node of the present invention, the wireless access network data collection and processing system of the present invention, or the wireless access network node of the present invention. Figure 5The method may include at least one of steps 201 to 202, wherein:

[0080] In step 201, a wireless access network node receives an artificial intelligence function request sent by a peer wireless access network node according to demand.

[0081] In some embodiments of the present disclosure, the wireless access network node may be a base station.

[0082] In some embodiments of the present disclosure, the radio access network node may be a NG-RAN node.

[0083] In some embodiments of the present disclosure, the artificial intelligence function request includes one or more artificial intelligence use cases, wherein the artificial intelligence use case may include at least one of use cases such as mobility enhancement, load balancing, and network energy saving.

[0084] In some embodiments of the present disclosure, during the AI ​​function initialization phase, an AI function request signaling is added to the Xn interface to indicate that the peer wireless access network node (base station 2) is applying to trigger the AI ​​function. The signaling name may be AI FunctionRequest (AI function request) / AI Function Required (AI function requirement) or other signaling names with the same meaning as the AI ​​function request. Similarly, a reverse feedback signaling is added to indicate whether the source node's request is accepted. The signaling name may be AI Function Response / Command (AI function reply or command) or other signaling names with similar meanings.

[0085] Step 202: The wireless access network node accepts or rejects the artificial intelligence function request based on the node's own situation.

[0086] In the above-mentioned embodiment of the present disclosure, the NG-RAN can trigger the AI ​​function to other NG-RAN nodes through the newly added Xn signaling as needed. The node that triggers the request sends the AI ​​function request signaling to the opposite node. The opposite node can accept or reject the request through the newly added Xn signaling according to its own situation.

[0087] Figure 3 Schematic diagram of other embodiments of the wireless access network data collection and processing method of the present disclosure. Preferably, this embodiment can be implemented by the wireless access network of the present disclosure, the wireless access network node of the present disclosure, the wireless access network data collection and processing system of the present disclosure, or the wireless access network node of the present disclosure. Figure 5 The method may include at least one of steps 301 to 311, wherein:

[0088] In step 301, a wireless access network node receives an artificial intelligence function request sent by a peer wireless access network node according to demand.

[0089] In some embodiments of the present disclosure, one or more AI use cases may be included in the newly added AI request signaling (Xn signaling).

[0090] Step 302: The wireless access network node accepts or rejects the artificial intelligence function request based on the node's own situation.

[0091] Step 303: When the wireless access network node accepts the artificial intelligence function request, it sends the measurement configuration related to the artificial intelligence function request to the user terminal.

[0092] In some embodiments of the present disclosure, the NG-RAN node may send corresponding measurement configuration to the UE based on the AI ​​use case passed by this request.

[0093] Step 304: The radio access network node receives the measurement data and information reported by the user terminal.

[0094] In some embodiments of the present disclosure, step 304 may include: the NG-RAN node obtains network data / information for AI model training from a neighboring node through AI-related request signaling.

[0095] In some embodiments of the present disclosure, step 304 may include: adding AI-related information request signaling to the Xn interface at the AI-related information acquisition node to indicate that the current node (base station 1) requests the adjacent node (base station 2) to feedback relevant network data / information for AI model training. The signaling name may be AI-related information request or other signaling names with the same meaning as AI-related information request. Similarly, adding reverse feedback signaling for the corresponding node to feedback relevant network data. The signaling name may be AI-related information response or other signaling names with similar meanings.

[0096] In step 305, the wireless access network node obtains network data and information for artificial intelligence model training from adjacent nodes through artificial intelligence-related request signaling.

[0097] In step 306, the wireless access network node performs artificial intelligence model training based on the information required for different scenarios.

[0098] In step 307, the wireless access network node sends the trained artificial intelligence model to the wireless access network node at the opposite end through artificial intelligence model deployment signaling.

[0099] In step 308, the wireless access network node receives the availability information of the artificial intelligence model fed back by the opposite wireless access network node.

[0100] In some embodiments of the present disclosure, steps 307 and 308 may include: the NG-RAN node sends the trained AI model to the peer NG-RAN node through AI model deployment signaling, and the peer NG-RAN node feedbacks whether the received AI model is usable through newly added Xn signaling.

[0101] In some embodiments of the present disclosure, steps 307 and 308 may include: in the AI ​​algorithm deployment phase, adding AI model deployment signaling to the Xn interface for the source node (base station 1) to send the trained model to the peer node (base station 2). The signaling name may be AI Model Deployment or other signaling names with the same meaning as the AI ​​function request. Similarly, a reverse feedback signaling is added to indicate whether the source node's AI model deployment is accepted. The signaling name may be AI Model Deployment Success / Failure or other signaling names with similar meanings.

[0102] In step 309, the wireless access network node performs model inference based on the necessary information and the trained artificial intelligence model, and outputs inference result information.

[0103] In step 310, the radio access network node adjusts its own configuration or measurement according to the inference result information, or instructs the user terminal to perform corresponding actions.

[0104] In step 311, the wireless access network node receives performance feedback from the peer wireless access network node regarding the current artificial intelligence model. For specific artificial intelligence use cases, the peer wireless access network node also performs model inference based on necessary information and the trained artificial intelligence model, and outputs inference result information.

[0105] The above-mentioned embodiments of the present disclosure enhance the capabilities of radio access network nodes, such as base stations. These embodiments support the NG-RAN triggering or rejecting AI functions to other NG-RAN nodes as needed; support the NG-RAN requesting or feeding back AI-related data / information to neighboring nodes; and support the NG-RAN determining the availability of received AI models and providing feedback to the peer node via Xn signaling.

[0106] The above embodiments of the present disclosure can realize RAN wireless network data collection and intelligent processing.

[0107] Figure 4Schematic diagram of some other embodiments of the wireless access network data collection and processing method of the present disclosure. Preferably, this embodiment can be implemented by the wireless access network of the present disclosure, the wireless access network node of the present disclosure, the wireless access network data collection and processing system of the present disclosure, or the wireless access network node of the present disclosure. Figure 5 The method may include at least one of steps 401 to 408, wherein:

[0108] Step 401: The wireless access network node sends an artificial intelligence function request to the opposite wireless access network node according to demand.

[0109] In step 402, the wireless access network node receives request feedback information sent by the opposite wireless access network node, wherein the request feedback information includes acceptance or rejection information of the opposite wireless access network node for the artificial intelligence function request based on the node's own situation.

[0110] Step 403: The wireless access network node receives artificial intelligence related request signaling sent by the adjacent node.

[0111] In step 404, the wireless access network node feeds back the network data and information used for artificial intelligence model training to the adjacent node.

[0112] In step 405, the wireless access network node receives the trained artificial intelligence model sent by the opposite wireless access network node through artificial intelligence model deployment signaling.

[0113] In step 406, the wireless access network node feeds back the availability information of the artificial intelligence model to the opposite wireless access network node.

[0114] Step 407: For a specific artificial intelligence use case, the wireless access network node performs model inference based on the necessary information and the trained artificial intelligence model, and outputs inference result information.

[0115] In step 408, the wireless access network node feeds back the performance of the artificial intelligence model to the peer wireless access network node.

[0116] To meet the needs of wireless network intelligence, the above-mentioned embodiments of the present disclosure, based on the related technical wireless network intelligent architecture, are designed for a deployment mode in which both the model training functional entity and the model inference functional entity are located in the RAN node. In combination with the architectural characteristics of the wireless network, a new signaling process is designed, which includes key steps such as AI function initialization, neighboring cell data request, and AI model deployment. This enables the wireless network to support the use of AI technology to achieve goals such as mobility optimization, load balancing, and network energy saving.

[0117] Figure 5The following is a schematic diagram of further embodiments of the wireless access network data collection and processing method disclosed herein. Preferably, this embodiment can be performed by the wireless access network disclosed herein, or a wireless access network node disclosed herein, or a wireless access network data collection and processing system disclosed herein. The method may include at least one of steps 1 to 11, wherein:

[0118] Step 1: Base station 2 sends an AI function request signaling to base station 1. The signaling carries the use case applied for this time (use cases include but are not limited to: mobility enhancement, load balancing, network energy saving). One request can apply for one use case, or multiple use cases can be applied according to demand.

[0119] Step 2a: This step is performed on demand. After receiving the request, if base station 2 can accept this AI function request, it will feedback AI function feedback signaling and carry the use case of accepting the request in the signaling. Base station 2 can also carry auxiliary information that helps AI model training (such as the current base station load status, etc.) in the signaling according to the use case requirements.

[0120] Step 2b: This step is performed on demand. If base station 2 does not support the AI ​​function or cannot accept the AI ​​request based on resource conditions, it will feedback AI function failure signaling to base station 1.

[0121] In some embodiments of the present disclosure, steps 1 and 2 mainly complete AI function initialization, which is used to align AI functions between NG-RAN nodes.

[0122] Step 3: Measurement configuration: base station 1 sends measurement configuration to UE. The relevant measurement configuration can be configured differently according to different use cases. This step can be combined with the MDT (Minimization of Drive Tests) mechanism.

[0123] Step 4: Reporting of measurement results: The UE collects and reports relevant measurement data / information based on the measurement information received.

[0124] Step 5a: Base station 1 requests base station 2 to feedback network data / information related to AI training based on the use case.

[0125] Step 5b: Base station 2 feeds back relevant network data / x information to base station 1.

[0126] In some embodiments of the present disclosure, step 5 mainly completes obtaining network data for AI training from neighboring cells. For example, in a load balancing use case, base station 1 obtains the real-time load of base station 2 as input data for AI model training, which helps to improve the accuracy of AI model output parameters.

[0127] Step 6: AI model training. Base station 1 performs AI model training based on the information required for different scenarios.

[0128] Step 7: AI model deployment, base station 1 sends the trained model to base station 2 via Xn signaling.

[0129] Step 8a: This step is performed on demand. If base station 2 successfully receives the trained AI model and can correctly understand and use the model, base station 2 will feedback the AI ​​model deployment success signaling to base station 1.

[0130] Step 8b: This step is performed on demand. If base station 2 cannot recognize the received AI model, or there is a parameter configuration mismatch, or other situations occur that cause base station 2 to be unable to perform the model inference step, base station 2 will feedback AI model deployment failure signaling to base station 1.

[0131] In some embodiments of the present disclosure, steps 7 and 8 mainly complete the AI ​​model deployment, with the purpose of synchronizing the AI ​​model between base stations. In some specific use cases, it is necessary to ensure that the AI ​​models used between base stations are consistent.

[0132] Step 9a: AI model reasoning: Base station 1 performs reasoning based on the necessary information and the trained AI model, and outputs prediction or recommendation information (such as the recommended target base station, or the load status of the base station in the future).

[0133] Step 9b: This step is performed on demand. For some specific AI use cases (such as AI-based base station load prediction), it is necessary to ensure that the same AI model is used between base stations. Therefore, base station 2 also needs to use the model trained by base station 1 for AI inference.

[0134] Step 10: Execution step. Based on the output of AI reasoning, the NG-RAN node can adjust its own configuration (such as the handover threshold) / policy (base station energy saving strategy, such as whether to shut down the base station), or instruct the UE to perform relevant actions (such as instructing the UE to perform handover) through RRC (Radio Resource Control) signaling.

[0135] Step 11: This step is performed on demand. For base station 2 that has executed step 9b, the performance of the AI ​​model is fed back to base station 1, such as the prediction accuracy and algorithm execution time, so that the base station can optimize and update the AI ​​model in a timely manner.

[0136] In the above embodiments of the present disclosure, steps 1-2, 5, and 7-8 are enhancements to the relevant technical standard protocol processes in combination with RAN intelligence requirements in the above embodiments of the present disclosure.

[0137] The technical solutions involved in the above-mentioned embodiments of this disclosure are key research areas within the 3GPP RAN3 Working Group's "Enhancement for Data Collection for NR and EN-DC" project and will impact 3GPP standards. These embodiments primarily address wireless air interface configuration and UE reporting, RAN node capability enhancement, and Xn interface signaling enhancements.

[0138] 3GPP standardization has not yet clarified the impact of introducing AI functions on the RAN side on wireless interfaces and signaling, and related scenarios and requirements are under discussion. The signaling process designed in the above-mentioned embodiments of the present disclosure is highly compatible with the relevant 3GPP interface protocols, conforming to the evolutionary thinking of 3GPP standardization, and well adapted to the requirements of the RAN intelligent use cases (such as mobility enhancement, load balancing, and network energy saving) currently defined by the RAN Working Group.

[0139] Figure 6 Schematic diagram of some embodiments of the wireless access network node disclosed in the present invention. Figure 6 As shown, the wireless access network node (eg Figure 5 The base station 1) of the embodiment may include a request function receiving module 61 and a request function feedback module 62, wherein:

[0140] The request function receiving module 61 is used to receive an artificial intelligence function request sent by the opposite wireless access network node according to demand.

[0141] In some embodiments of the present disclosure, the artificial intelligence function request may include one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

[0142] The request function feedback module 62 is used to accept or reject the artificial intelligence function request based on the node's own situation.

[0143] In the above-mentioned embodiment of the present disclosure, the NG-RAN can trigger the AI ​​function to other NG-RAN nodes through the newly added Xn signaling as needed. The node that triggers the request sends the AI ​​function request signaling to the opposite node. The opposite node can accept or reject the request through the newly added Xn signaling according to its own situation.

[0144] In some embodiments of the present disclosure, Figure 6 As shown, the wireless access network node of the present disclosure may include a measurement configuration module 63, wherein:

[0145] The measurement configuration module 63 is used to send the measurement configuration related to the artificial intelligence function request to the user terminal when accepting the artificial intelligence function request; and receive the measurement data and information reported by the user terminal.

[0146] In some embodiments of the present disclosure, Figure 6 As shown, the wireless access network node of the present disclosure may include a training data acquisition module 64, wherein:

[0147] The training data acquisition module 64 is used to obtain network data and information used for artificial intelligence model training from adjacent nodes through artificial intelligence related request signaling.

[0148] In some embodiments of the present disclosure, Figure 6 As shown, the wireless access network node of the present disclosure may include a model training module 65 and a model deployment module 66, wherein:

[0149] The model training module 65 is used to train the artificial intelligence model based on the information required for different scenarios.

[0150] The model deployment module 66 is used to send the trained artificial intelligence model to the opposite wireless access network node through artificial intelligence model deployment signaling; and receive the availability information of the artificial intelligence model fed back by the opposite wireless access network node.

[0151] In some embodiments of the present disclosure, Figure 6 As shown, the wireless access network node of the present disclosure may include a model reasoning module 67 and an execution module 68, wherein:

[0152] The model reasoning module 67 is used to perform model reasoning based on necessary information and the trained artificial intelligence model, and output reasoning result information.

[0153] The execution module 68 is used to adjust its own configuration or measurement according to the inference result information, or instruct the user terminal to perform corresponding actions.

[0154] In some embodiments of the present disclosure, Figure 6 As shown, the wireless access network node of the present disclosure may include a feedback performance receiving module 69, wherein:

[0155] The feedback performance receiving module 69 is used to receive performance feedback from the peer wireless access network node on the current artificial intelligence model. For specific artificial intelligence use cases, the peer wireless access network node also performs model inference based on necessary information and the trained artificial intelligence model, and outputs inference result information.

[0156] In some embodiments of the present disclosure, the wireless access network node is used to implement any of the above embodiments (for example Figure 2-Figure 5The operation of the wireless access network data collection and processing method described in any embodiment).

[0157] The above-mentioned embodiments of the present disclosure enhance the capabilities of radio access network nodes, such as base stations. These embodiments support the NG-RAN triggering or rejecting AI functions to other NG-RAN nodes as needed; support the NG-RAN requesting or feeding back AI-related data / information to neighboring nodes; and support the NG-RAN determining the availability of received AI models and providing feedback to the peer node via Xn signaling.

[0158] The above embodiments of the present disclosure can realize RAN wireless network data collection and intelligent processing.

[0159] Figure 7 Schematic diagram of some other embodiments of the wireless access network node disclosed in the present invention. Figure 7 As shown, the wireless access network node (eg Figure 5 The base station 2) of the embodiment may include a function request sending module 71 and a feedback request information receiving module 72, wherein:

[0160] The function request sending module 71 is used to send an artificial intelligence function request to the wireless access network node at the opposite end according to demand.

[0161] In some embodiments of the present disclosure, the artificial intelligence function request may include one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

[0162] The request feedback information receiving module 72 is used to receive the request feedback information sent by the opposite wireless access network node, wherein the request feedback information includes the acceptance or rejection information of the opposite wireless access network node to the artificial intelligence function request based on the node's own situation.

[0163] In some embodiments of the present disclosure, Figure 7 As shown, the wireless access network node of the present disclosure may further include a training data feedback module 73, wherein:

[0164] The training data feedback module 73 is used to receive artificial intelligence-related request signaling sent by adjacent nodes; and feed back network data and information used for artificial intelligence model training to the adjacent nodes.

[0165] In some embodiments of the present disclosure, Figure 7 As shown, the wireless access network node of the present disclosure may further include a model receiving module 74 and a model performance feedback module 75, wherein:

[0166] The model receiving module 74 is used to receive the trained artificial intelligence model sent by the opposite wireless access network node through artificial intelligence model deployment signaling.

[0167] The model performance feedback module 75 is used to feedback the availability information of the artificial intelligence model to the wireless access network node at the opposite end.

[0168] In some embodiments of the present disclosure, Figure 7 As shown, the wireless access network node of the present disclosure may further include a model reasoning module 76, wherein:

[0169] The model reasoning module 76 is used to perform model reasoning for a specific artificial intelligence use case based on the necessary information and the trained artificial intelligence model, and output the reasoning result information; and feed back the performance of this artificial intelligence model to the wireless access network node at the opposite end.

[0170] In some embodiments of the present disclosure, the wireless access network node is used to implement any of the above embodiments (for example Figure 1-Figure 5 The operation of the wireless access network data collection and processing method described in any embodiment).

[0171] To meet the needs of wireless network intelligence, the above-mentioned embodiments of the present disclosure, based on the related technical wireless network intelligent architecture, are designed for a deployment mode in which both the model training functional entity and the model inference functional entity are located in the RAN node. In combination with the architectural characteristics of the wireless network, a new signaling process is designed, which includes key steps such as AI function initialization, neighboring cell data request, and AI model deployment. This enables the wireless network to support the use of AI technology to achieve goals such as mobility optimization, load balancing, and network energy saving.

[0172] Figure 8 FIG. 1 is a schematic diagram showing the structure of some embodiments of the wireless access network node disclosed in the present invention. Figure 8 As shown, the wireless access network node (eg Figure 5 The base station 1 or base station 2 of the embodiment may include a memory 81 and a processor 82 .

[0173] The memory 81 is used to store instructions. The processor 82 is coupled to the memory 81. The processor 82 is configured to execute the instructions stored in the memory to implement any of the above embodiments (for example, Figure 1-Figure 5 The wireless access network data collection and processing method described in any embodiment).

[0174] like Figure 8As shown, the wireless access network node also includes a communication interface 83 for exchanging information with other devices. At the same time, the wireless access network node also includes a bus 84, through which the processor 82, the communication interface 83, and the memory 81 communicate with each other.

[0175] Memory 81 may include high-speed RAM memory or non-volatile memory, such as at least one disk storage device. Memory 81 may also be a memory array. Memory 81 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0176] Furthermore, the processor 82 may be a central processing unit (CPU), or may be an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the present disclosure.

[0177] The technical solutions involved in the above-mentioned embodiments of this disclosure are key research areas within the 3GPP RAN3 Working Group's "Enhancement for Data Collection for NR and EN-DC" project and will impact 3GPP standards. These embodiments primarily address wireless air interface configuration and UE reporting, RAN node capability enhancement, and Xn interface signaling enhancements.

[0178] According to another aspect of the present disclosure, a wireless access network data collection and processing system is provided, including any one of the above embodiments (e.g. Figure 6-Figure 8 The wireless access network node described in any embodiment).

[0179] 3GPP standardization has not yet clarified the impact of introducing AI functions on the RAN side on wireless interfaces and signaling, and related scenarios and requirements are under discussion. The signaling process designed in the above-mentioned embodiments of the present disclosure is highly compatible with the relevant 3GPP interface protocols, conforming to the evolutionary thinking of 3GPP standardization, and well adapted to the requirements of the RAN intelligent use cases (such as mobility enhancement, load balancing, and network energy saving) currently defined by the RAN Working Group.

[0180] According to another aspect of the present disclosure, a wireless access network is provided, including any one of the above embodiments (e.g. Figure 6-Figure 8 The wireless access network node as described in any embodiment), or the wireless access network data collection and processing system as described in any of the above embodiments.

[0181] The above embodiments of the present disclosure are designed for the signaling process of initializing and executing AI functions for the intelligent architecture of wireless networks, which can be adapted to different application scenarios.

[0182] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the computer-readable storage medium implements any of the above embodiments (e.g., Figure 1-Figure 5 The wireless access network data collection and processing method described in any embodiment).

[0183] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, apparatus, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0184] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0185] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0187] The wireless access network node described above may be implemented as a general-purpose processor, a programmable logic controller (PLC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or any appropriate combination thereof for performing the functions described in this application.

[0188] The present disclosure has been described in detail so far. To avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0189] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a non-transitory computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0190] The description of the present disclosure is provided for purposes of illustration and description and is not intended to be exhaustive or to limit the disclosure to the disclosed form. Many modifications and variations will be apparent to those skilled in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure and to enable those skilled in the art to understand the present disclosure and design various embodiments with various modifications suitable for specific applications.

Claims

1. A method for collecting and processing wireless access network data, characterized in that: include: The wireless access network node receives an artificial intelligence function request sent by the opposite wireless access network node according to demand; The wireless access network node accepts or rejects the artificial intelligence function request based on the node's own situation; The wireless access network data collection and processing method further includes: The wireless access network node uses artificial intelligence model deployment signaling to send the trained artificial intelligence model to the peer wireless access network node; The wireless access network node receives availability information of the artificial intelligence model fed back by the opposite wireless access network node.

2. The method for collecting and processing wireless access network data according to claim 1, wherein: The artificial intelligence function request includes one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

3. The method for collecting and processing wireless access network data according to claim 1 or 2, wherein: Also includes: When the wireless access network node accepts the artificial intelligence function request, it sends the measurement configuration related to this artificial intelligence function request to the user terminal; The radio access network node receives measurement data and information reported by the user terminal.

4. The method for collecting and processing wireless access network data according to claim 1 or 2, wherein: Also includes: Wireless access network nodes obtain network data and information used for AI model training from adjacent nodes through AI-related request signaling.

5. The method for collecting and processing wireless access network data according to claim 4, wherein: Also includes: Wireless access network nodes train artificial intelligence models based on the information required for different scenarios.

6. The method for collecting and processing wireless access network data according to claim 5, wherein: Also includes: The wireless access network node performs model inference based on the necessary information and the trained artificial intelligence model, and outputs the inference result information; The wireless access network node adjusts its own configuration or measurement based on the inference result information, or instructs the user terminal to take corresponding actions.

7. The method for collecting and processing wireless access network data according to claim 6, wherein: Also includes: The wireless access network node receives performance feedback from the peer wireless access network node regarding the current artificial intelligence model. For specific artificial intelligence use cases, the peer wireless access network node also performs model inference based on necessary information and the trained artificial intelligence model, and outputs inference result information.

8. A method for collecting and processing wireless access network data, characterized in that: include: The wireless access network node sends an artificial intelligence function request to the wireless access network node at the opposite end according to the demand; The wireless access network node receives request feedback information sent by the opposite wireless access network node, wherein the request feedback information includes acceptance or rejection information of the opposite wireless access network node for the artificial intelligence function request based on the node's own situation; The wireless access network data collection and processing method further includes: The wireless access network node receives the trained artificial intelligence model sent by the peer wireless access network node through artificial intelligence model deployment signaling; The wireless access network node feeds back the availability information of the artificial intelligence model to the opposite wireless access network node.

9. The method for collecting and processing wireless access network data according to claim 8, wherein: The artificial intelligence function request includes one or more artificial intelligence use cases, wherein the artificial intelligence use cases include at least one of mobility enhancement, load balancing, and network energy saving.

10. The method for collecting and processing wireless access network data according to claim 8 or 9, characterized in that: Also includes: The wireless access network node receives artificial intelligence related request signaling sent by the adjacent node; The wireless access network node feeds back the network data and information used for artificial intelligence model training to the adjacent node.

11. The method for collecting and processing wireless access network data according to claim 8 or 9, characterized in that: Also includes: For specific AI use cases, the wireless access network node performs model inference based on the necessary information and the trained AI model, and outputs the inference result information; The wireless access network node feeds back the performance of the artificial intelligence model to the wireless access network node at the other end.

12. A wireless access network node, characterized in that: include: A request function receiving module is used to receive an artificial intelligence function request sent by a wireless access network node on the opposite end according to demand; A request function feedback module is used to accept or reject the artificial intelligence function request based on the node's own situation; The model deployment module is used to send the trained artificial intelligence model to the peer wireless access network node through artificial intelligence model deployment signaling; and receive the availability information of the artificial intelligence model fed back by the peer wireless access network node.

13. The wireless access network node according to claim 12, wherein: The wireless access network node is used to execute operations to implement the wireless access network data collection and processing method according to any one of claims 1 to 11.

14. A wireless access network node, characterized in that: include: A function request sending module is used to send an artificial intelligence function request to the wireless access network node at the opposite end according to demand; a request feedback information receiving module, configured to receive request feedback information sent by a peer wireless access network node, wherein the request feedback information includes information on whether the peer wireless access network node accepts or rejects the artificial intelligence function request based on the node's own situation; A model receiving module is used to receive the trained artificial intelligence model sent by the peer wireless access network node through artificial intelligence model deployment signaling; The model performance feedback module is used to feedback the availability information of the artificial intelligence model to the peer wireless access network node.

15. The wireless access network node according to claim 14, wherein: The wireless access network node is used to execute operations to implement the wireless access network data collection and processing method according to any one of claims 1 to 11.

16. A wireless access network node, characterized in that: include: a memory for storing instructions; The processor is configured to execute the instruction so that the wireless access network node performs operations to implement the wireless access network data collection and processing method according to any one of claims 1 to 11.

17. A wireless access network data collection and processing system, characterized in that: The method comprises the radio access network node according to any one of claims 12 to 16.

18. A wireless access network, characterized in that: The method comprises the wireless access network node according to any one of claims 12 to 16, or the wireless access network data collection and processing system according to claim 17.

19. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the method for collecting and processing wireless access network data according to any one of claims 1 to 11 is implemented.

Images